diff --git a/ballerina/Ballerina.toml b/ballerina/Ballerina.toml index 6de12b4..6857f62 100644 --- a/ballerina/Ballerina.toml +++ b/ballerina/Ballerina.toml @@ -2,7 +2,7 @@ distribution = "2201.9.3" org = "ballerinax" name = "openai.chat" -version = "3.0.0" +version = "4.0.0" license = ["Apache-2.0"] authors = ["Ballerina"] keywords = ["AI/Chat", "OpenAI", "Cost/Paid", "GPT-4", "ChatGPT", "Vendor/OpenAI"] diff --git a/ballerina/Dependencies.toml b/ballerina/Dependencies.toml index ec3381e..86bd56e 100644 --- a/ballerina/Dependencies.toml +++ b/ballerina/Dependencies.toml @@ -64,7 +64,7 @@ dependencies = [ [[package]] org = "ballerina" name = "http" -version = "2.11.3" +version = "2.11.7" dependencies = [ {org = "ballerina", name = "auth"}, {org = "ballerina", name = "cache"}, @@ -96,7 +96,7 @@ modules = [ [[package]] org = "ballerina" name = "io" -version = "1.6.1" +version = "1.6.3" dependencies = [ {org = "ballerina", name = "jballerina.java"}, {org = "ballerina", name = "lang.value"} @@ -318,7 +318,7 @@ modules = [ [[package]] org = "ballerinax" name = "openai.chat" -version = "3.0.0" +version = "4.0.0" dependencies = [ {org = "ballerina", name = "constraint"}, {org = "ballerina", name = "http"}, diff --git a/ballerina/client.bal b/ballerina/client.bal index e33aee1..914b03e 100644 --- a/ballerina/client.bal +++ b/ballerina/client.bal @@ -55,7 +55,9 @@ public isolated client class Client { return; } - # Creates a model response for the given chat conversation. + # Creates a model response for the given chat conversation. Learn more in the + # [text generation](/docs/guides/text-generation), [vision](/docs/guides/vision), + # and [audio](/docs/guides/audio) guides. # # + headers - Headers to be sent with the request # + return - OK diff --git a/ballerina/types.bal b/ballerina/types.bal index fc40d30..156a8c0 100644 --- a/ballerina/types.bal +++ b/ballerina/types.bal @@ -20,41 +20,294 @@ import ballerina/constraint; import ballerina/http; +# If the audio output modality is requested, this object contains data +# about the audio response from the model. [Learn more](/docs/guides/audio). +public type ChatCompletionResponseMessage_audio record { + # Unique identifier for this audio response. + string id; + # The Unix timestamp (in seconds) for when this audio response will + # no longer be accessible on the server for use in multi-turn + # conversations. + int expires_at; + # Base64 encoded audio bytes generated by the model, in the format + # specified in the request. + string data; + # Transcript of the audio generated by the model. + string transcript; +}; + +# Static predicted output content, such as the content of a text file that is +# being regenerated. +public type PredictionContent record { + # The type of the predicted content you want to provide. This type is + # currently always `content`. + "content" 'type; + # The content that should be matched when generating a model response. + # If generated tokens would match this content, the entire model response + # can be returned much more quickly. + string|ChatCompletionRequestMessageContentPartText[] content; +}; + +# Options for streaming response. Only set this when you set `stream: true`. +public type ChatCompletionStreamOptions record { + # If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value. + boolean include_usage?; +}; + +public type ChatCompletionTokenLogprob record { + # The token. + string token; + # The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. + decimal logprob; + # A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. + int[]? bytes; + # List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. + ChatCompletionTokenLogprob_top_logprobs[] top_logprobs; +}; + +public type ChatCompletionRequestMessage ChatCompletionRequestSystemMessage|ChatCompletionRequestUserMessage|ChatCompletionRequestAssistantMessage|ChatCompletionRequestToolMessage|ChatCompletionRequestFunctionMessage; + +public type ChatCompletionRequestUserMessageContentPart ChatCompletionRequestMessageContentPartText|ChatCompletionRequestMessageContentPartImage|ChatCompletionRequestMessageContentPartAudio; + +# The function that the model called. +public type ChatCompletionMessageToolCall_function record { + # The name of the function to call. + string name; + # The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + string arguments; +}; + +public type ChatCompletionRequestSystemMessageContentPart ChatCompletionRequestMessageContentPartText; + +public type AssistantsNamedToolChoice_function record { + # The name of the function to call. + string name; +}; + +public type ChatCompletionRequestAssistantMessage record { + # The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. + string|ChatCompletionRequestAssistantMessageContentPart[]? content?; + # The refusal message by the assistant. + string? refusal?; + # The role of the messages author, in this case `assistant`. + "assistant" role; + # An optional name for the participant. Provides the model information to differentiate between participants of the same role. + string name?; + ChatCompletionRequestAssistantMessage_audio? audio?; + ChatCompletionMessageToolCalls tool_calls?; + ChatCompletionRequestAssistantMessage_function_call? function_call?; +}; + +# Controls which (if any) tool is called by the model. +# `none` means the model will not call any tool and instead generates a message. +# `auto` means the model can pick between generating a message or calling one or more tools. +# `required` means the model must call one or more tools. +# Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. +# +# `none` is the default when no tools are present. `auto` is the default if tools are present. +public type ChatCompletionToolChoiceOption "none"|"auto"|"required"|ChatCompletionNamedToolChoice; + # Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. # # # Deprecated @deprecated -public type ChatCompletionRequestAssistantMessage_function_call record { +public type ChatCompletionResponseMessage_function_call record { # The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. string arguments; # The name of the function to call. string name; }; -# Specifies a tool the model should use. Use to force the model to call a specific function. -public type ChatCompletionNamedToolChoice record { +public type ChatCompletionRequestToolMessageContentPart ChatCompletionRequestMessageContentPartText; + +# Provides a set of configurations for controlling the behaviours when communicating with a remote HTTP endpoint. +@display {label: "Connection Config"} +public type ConnectionConfig record {| + # Configurations related to client authentication + http:BearerTokenConfig auth; + # The HTTP version understood by the client + http:HttpVersion httpVersion = http:HTTP_2_0; + # Configurations related to HTTP/1.x protocol + ClientHttp1Settings http1Settings?; + # Configurations related to HTTP/2 protocol + http:ClientHttp2Settings http2Settings?; + # The maximum time to wait (in seconds) for a response before closing the connection + decimal timeout = 60; + # The choice of setting `forwarded`/`x-forwarded` header + string forwarded = "disable"; + # Configurations associated with request pooling + http:PoolConfiguration poolConfig?; + # HTTP caching related configurations + http:CacheConfig cache?; + # Specifies the way of handling compression (`accept-encoding`) header + http:Compression compression = http:COMPRESSION_AUTO; + # Configurations associated with the behaviour of the Circuit Breaker + http:CircuitBreakerConfig circuitBreaker?; + # Configurations associated with retrying + http:RetryConfig retryConfig?; + # Configurations associated with inbound response size limits + http:ResponseLimitConfigs responseLimits?; + # SSL/TLS-related options + http:ClientSecureSocket secureSocket?; + # Proxy server related options + http:ProxyConfig proxy?; + # Enables the inbound payload validation functionality which provided by the constraint package. Enabled by default + boolean validation = true; +|}; + +# Breakdown of tokens used in a completion. +public type CompletionUsage_completion_tokens_details record { + # When using Predicted Outputs, the number of tokens in the + # prediction that appeared in the completion. + int accepted_prediction_tokens?; + # Audio input tokens generated by the model. + int audio_tokens?; + # Tokens generated by the model for reasoning. + int reasoning_tokens?; + # When using Predicted Outputs, the number of tokens in the + # prediction that did not appear in the completion. However, like + # reasoning tokens, these tokens are still counted in the total + # completion tokens for purposes of billing, output, and context window + # limits. + int rejected_prediction_tokens?; +}; + +# The schema for the response format, described as a JSON Schema object. +public type ResponseFormatJsonSchemaSchema record { +}; + +public type ChatCompletionRequestUserMessage record { + # The contents of the user message. + string|ChatCompletionRequestUserMessageContentPart[] content; + # The role of the messages author, in this case `user`. + "user" role; + # An optional name for the participant. Provides the model information to differentiate between participants of the same role. + string name?; +}; + +# The tool calls generated by the model, such as function calls. +public type ChatCompletionMessageToolCalls ChatCompletionMessageToolCall[]; + +# Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. +public type ChatCompletionFunctionCallOption record { + # The name of the function to call. + string name; +}; + +@deprecated +public type ChatCompletionFunctions record { + # A description of what the function does, used by the model to choose when and how to call the function. + string description?; + # The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. + string name; + FunctionParameters parameters?; +}; + +# Learn about [audio inputs](/docs/guides/audio). +# + input_audio - The type of the content part. Always `input_audio`. +public type ChatCompletionRequestMessageContentPartAudio record { + # The type of the content part. Always `input_audio`. + "input_audio" 'type; + ChatCompletionRequestMessageContentPartAudio_input_audio input_audio; +}; + +public type ChatCompletionTool record { # The type of the tool. Currently, only `function` is supported. "function" 'type; - ChatCompletionNamedToolChoice_function 'function; + FunctionObject 'function; }; -# Options for streaming response. Only set this when you set `stream: true`. -public type ChatCompletionStreamOptions record { - # If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value. - boolean include_usage?; +public type ChatCompletionRequestSystemMessage record { + # The contents of the system message. + string|ChatCompletionRequestSystemMessageContentPart[] content; + # The role of the messages author, in this case `system`. + "system" role; + # An optional name for the participant. Provides the model information to differentiate between participants of the same role. + string name?; }; -public type ChatCompletionTokenLogprob record { +public type ChatCompletionRequestMessageContentPartImage_image_url record { + # Either a URL of the image or the base64 encoded image data. + string url; + # Specifies the detail level of the image. Learn more in the [Vision guide](/docs/guides/vision#low-or-high-fidelity-image-understanding). + "auto"|"low"|"high" detail = "auto"; +}; + +# Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. +public type ParallelToolCalls boolean; + +public type ChatCompletionTokenLogprob_top_logprobs record { # The token. string token; # The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. decimal logprob; # A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. int[]? bytes; - # List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. - ChatCompletionTokenLogprob_top_logprobs[] top_logprobs; }; +public type ResponseFormatJsonSchema_json_schema record { + # A description of what the response format is for, used by the model to determine how to respond in the format. + string description?; + # The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. + string name; + ResponseFormatJsonSchemaSchema schema?; + # Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`. To learn more, read the [Structured Outputs guide](/docs/guides/structured-outputs). + boolean? strict = false; +}; + +# Learn about [image inputs](/docs/guides/vision). +# + image_url - The type of the content part. Always `image_url`. +public type ChatCompletionRequestMessageContentPartImage record { + # The type of the content part. + "image_url" 'type; + ChatCompletionRequestMessageContentPartImage_image_url image_url; +}; + +# Learn about [text inputs](/docs/guides/text-generation). +public type ChatCompletionRequestMessageContentPartText record { + # The type of the content part. + "text" 'type; + # The text content. + string text; +}; + +# The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. +# +# Omitting `parameters` defines a function with an empty parameter list. +public type FunctionParameters record { +}; + +# Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. +# +# # Deprecated +@deprecated +public type ChatCompletionRequestAssistantMessage_function_call record { + # The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + string arguments; + # The name of the function to call. + string name; +}; + +# Specifies a tool the model should use. Use to force the model to call a specific function. +# + function - The type of the tool. Always `function`. +public type ChatCompletionNamedToolChoice record { + # The type of the tool. Currently, only `function` is supported. + "function" 'type; + AssistantsNamedToolChoice_function 'function; +}; + +# Output types that you would like the model to generate for this request. +# Most models are capable of generating text, which is the default: +# +# `["text"]` +# +# The `gpt-4o-audio-preview` model can also be used to [generate audio](/docs/guides/audio). To +# request that this model generate both text and audio responses, you can +# use: +# +# `["text", "audio"]` +public type ChatCompletionModalities ("text"|"audio")[]?; + public type CreateChatCompletionResponse_choices record { # The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, # `length` if the maximum number of tokens specified in the request was reached, @@ -67,35 +320,48 @@ public type CreateChatCompletionResponse_choices record { CreateChatCompletionResponse_logprobs? logprobs; }; -public type ChatCompletionRequestMessage ChatCompletionRequestSystemMessage|ChatCompletionRequestUserMessage|ChatCompletionRequestAssistantMessage|ChatCompletionRequestToolMessage|ChatCompletionRequestFunctionMessage; - public type FunctionObject record { # A description of what the function does, used by the model to choose when and how to call the function. string description?; # The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. string name; FunctionParameters parameters?; + # Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](docs/guides/function-calling). + boolean? strict = false; }; -public type ChatCompletionRequestMessageContentPart ChatCompletionRequestMessageContentPartText|ChatCompletionRequestMessageContentPartImage; +public type ResponseFormatJsonSchema record { + # The type of response format being defined: `json_schema` + "json_schema" 'type; + ResponseFormatJsonSchema_json_schema json_schema; +}; -# The function that the model called. -public type ChatCompletionMessageToolCall_function record { - # The name of the function to call. - string name; - # The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - string arguments; +# Breakdown of tokens used in the prompt. +public type CompletionUsage_prompt_tokens_details record { + # Audio input tokens present in the prompt. + int audio_tokens?; + # Cached tokens present in the prompt. + int cached_tokens?; }; public type CreateChatCompletionRequest record { - # A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). + # A list of messages comprising the conversation so far. Depending on the + # [model](/docs/models) you use, different message types (modalities) are + # supported, like [text](/docs/guides/text-generation), + # [images](/docs/guides/vision), and [audio](/docs/guides/audio). @constraint:Array {minLength: 1} ChatCompletionRequestMessage[] messages; - # ID of the model to use. See the [model endpoint compatibility](/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. - string|"gpt-4o"|"gpt-4o-2024-05-13"|"gpt-4o-mini"|"gpt-4o-mini-2024-07-18"|"gpt-4-turbo"|"gpt-4-turbo-2024-04-09"|"gpt-4-0125-preview"|"gpt-4-turbo-preview"|"gpt-4-1106-preview"|"gpt-4-vision-preview"|"gpt-4"|"gpt-4-0314"|"gpt-4-0613"|"gpt-4-32k"|"gpt-4-32k-0314"|"gpt-4-32k-0613"|"gpt-3.5-turbo"|"gpt-3.5-turbo-16k"|"gpt-3.5-turbo-0301"|"gpt-3.5-turbo-0613"|"gpt-3.5-turbo-1106"|"gpt-3.5-turbo-0125"|"gpt-3.5-turbo-16k-0613" model; + # ID of the model to use. See the [model endpoint compatibility](/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. + string|"o1-preview"|"o1-preview-2024-09-12"|"o1-mini"|"o1-mini-2024-09-12"|"gpt-4o"|"gpt-4o-2024-11-20"|"gpt-4o-2024-08-06"|"gpt-4o-2024-05-13"|"gpt-4o-realtime-preview"|"gpt-4o-realtime-preview-2024-10-01"|"gpt-4o-audio-preview"|"gpt-4o-audio-preview-2024-10-01"|"chatgpt-4o-latest"|"gpt-4o-mini"|"gpt-4o-mini-2024-07-18"|"gpt-4-turbo"|"gpt-4-turbo-2024-04-09"|"gpt-4-0125-preview"|"gpt-4-turbo-preview"|"gpt-4-1106-preview"|"gpt-4-vision-preview"|"gpt-4"|"gpt-4-0314"|"gpt-4-0613"|"gpt-4-32k"|"gpt-4-32k-0314"|"gpt-4-32k-0613"|"gpt-3.5-turbo"|"gpt-3.5-turbo-16k"|"gpt-3.5-turbo-0301"|"gpt-3.5-turbo-0613"|"gpt-3.5-turbo-1106"|"gpt-3.5-turbo-0125"|"gpt-3.5-turbo-16k-0613" model; + # Whether or not to store the output of this chat completion request + # for use in our [model distillation](/docs/guides/distillation) or [evals](/docs/guides/evals) products. + boolean? store = false; + # Developer-defined tags and values used for filtering completions + # in the [dashboard](https://platform.openai.com/chat-completions). + record {|string...;|}? metadata?; # Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. # - # [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) + # [See more information about frequency and presence penalties.](/docs/guides/text-generation) decimal? frequency_penalty = 0; # Modify the likelihood of specified tokens appearing in the completion. # @@ -105,28 +371,48 @@ public type CreateChatCompletionRequest record { boolean? logprobs = false; # An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. int? top_logprobs?; - # The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. + # The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API. + # + # This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with [o1 series models](/docs/guides/reasoning). # - # The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. + # # Deprecated + @deprecated int? max_tokens?; + # An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). + int? max_completion_tokens?; # How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. int? n = 1; + ChatCompletionModalities? modalities?; + # Configuration for a [Predicted Output](/docs/guides/predicted-outputs), + # which can greatly improve response times when large parts of the model + # response are known ahead of time. This is most common when you are + # regenerating a file with only minor changes to most of the content. + PredictionContent? prediction?; + CreateChatCompletionRequest_audio? audio?; # Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. # - # [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) + # [See more information about frequency and presence penalties.](/docs/guides/text-generation) decimal? presence_penalty = 0; - CreateChatCompletionRequest_response_format response_format?; + # An object specifying the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4o mini](/docs/models#gpt-4o-mini), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. + # + # Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](/docs/guides/structured-outputs). + # + # Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the message the model generates is valid JSON. + # + # **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. + ResponseFormatText|ResponseFormatJsonObject|ResponseFormatJsonSchema response_format?; # This feature is in Beta. # If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. # Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. int? seed?; # Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - # - If set to 'auto', the system will utilize scale tier credits until they are exhausted. + # - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. + # - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. # - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. # - When not set, the default behavior is 'auto'. # # When this parameter is set, the response body will include the `service_tier` utilized. - "auto"|"default"? service_tier?; + "auto"|"default"? service_tier = "auto"; # Up to 4 sequences where the API will stop generating further tokens. string|string[]? stop?; # If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). @@ -144,7 +430,7 @@ public type CreateChatCompletionRequest record { ChatCompletionTool[] tools?; ChatCompletionToolChoiceOption tool_choice?; ParallelToolCalls parallel_tool_calls?; - # A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids). + # A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). string user?; # Deprecated in favor of `tool_choice`. # @@ -172,40 +458,23 @@ public type CreateChatCompletionRequest record { public type CreateChatCompletionResponse_logprobs record { # A list of message content tokens with log probability information. ChatCompletionTokenLogprob[]? content; + # A list of message refusal tokens with log probability information. + ChatCompletionTokenLogprob[]? refusal; }; -public type ChatCompletionRequestAssistantMessage record { - # The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. - string? content?; - # The role of the messages author, in this case `assistant`. - "assistant" role; - # An optional name for the participant. Provides the model information to differentiate between participants of the same role. - string name?; - ChatCompletionMessageToolCalls tool_calls?; - ChatCompletionRequestAssistantMessage_function_call? function_call?; -}; - -# Controls which (if any) tool is called by the model. -# `none` means the model will not call any tool and instead generates a message. -# `auto` means the model can pick between generating a message or calling one or more tools. -# `required` means the model must call one or more tools. -# Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. -# -# `none` is the default when no tools are present. `auto` is the default if tools are present. -public type ChatCompletionToolChoiceOption "none"|"auto"|"required"|ChatCompletionNamedToolChoice; - -# Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. -# -# # Deprecated -@deprecated -public type ChatCompletionResponseMessage_function_call record { - # The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - string arguments; - # The name of the function to call. - string name; +# Parameters for audio output. Required when audio output is requested with +# `modalities: ["audio"]`. [Learn more](/docs/guides/audio). +public type CreateChatCompletionRequest_audio record { + # The voice the model uses to respond. Supported voices are `ash`, `ballad`, `coral`, `sage`, and `verse` (also supported but not recommended are `alloy`, `echo`, and `shimmer`; these voices are less expressive). + "alloy"|"ash"|"ballad"|"coral"|"echo"|"sage"|"shimmer"|"verse" voice; + # Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, + # `opus`, or `pcm16`. + "wav"|"mp3"|"flac"|"opus"|"pcm16" format; }; # Usage statistics for the completion request. +# + completion_tokens_details - Breakdown of tokens used in the completion. +# + prompt_tokens_details - Breakdown of tokens used in the prompt. public type CompletionUsage record { # Number of tokens in the generated completion. int completion_tokens; @@ -213,61 +482,24 @@ public type CompletionUsage record { int prompt_tokens; # Total number of tokens used in the request (prompt + completion). int total_tokens; + CompletionUsage_completion_tokens_details completion_tokens_details?; + CompletionUsage_prompt_tokens_details prompt_tokens_details?; }; -# Provides a set of configurations for controlling the behaviours when communicating with a remote HTTP endpoint. -@display {label: "Connection Config"} -public type ConnectionConfig record {| - # Configurations related to client authentication - http:BearerTokenConfig auth; - # The HTTP version understood by the client - http:HttpVersion httpVersion = http:HTTP_2_0; - # Configurations related to HTTP/1.x protocol - ClientHttp1Settings http1Settings?; - # Configurations related to HTTP/2 protocol - http:ClientHttp2Settings http2Settings?; - # The maximum time to wait (in seconds) for a response before closing the connection - decimal timeout = 60; - # The choice of setting `forwarded`/`x-forwarded` header - string forwarded = "disable"; - # Configurations associated with request pooling - http:PoolConfiguration poolConfig?; - # HTTP caching related configurations - http:CacheConfig cache?; - # Specifies the way of handling compression (`accept-encoding`) header - http:Compression compression = http:COMPRESSION_AUTO; - # Configurations associated with the behaviour of the Circuit Breaker - http:CircuitBreakerConfig circuitBreaker?; - # Configurations associated with retrying - http:RetryConfig retryConfig?; - # Configurations associated with inbound response size limits - http:ResponseLimitConfigs responseLimits?; - # SSL/TLS-related options - http:ClientSecureSocket secureSocket?; - # Proxy server related options - http:ProxyConfig proxy?; - # Enables the inbound payload validation functionality which provided by the constraint package. Enabled by default - boolean validation = true; -|}; - -public type ChatCompletionNamedToolChoice_function record { - # The name of the function to call. - string name; +public type ChatCompletionRequestMessageContentPartAudio_input_audio record { + # Base64 encoded audio data. + string data; + # The format of the encoded audio data. Currently supports "wav" and "mp3". + "wav"|"mp3" format; }; -public type ChatCompletionRequestUserMessage record { - # The contents of the user message. - string|ChatCompletionRequestMessageContentPart[] content; - # The role of the messages author, in this case `user`. - "user" role; - # An optional name for the participant. Provides the model information to differentiate between participants of the same role. - string name?; +public type ResponseFormatText record { + # The type of response format being defined: `text` + "text" 'type; }; -# The tool calls generated by the model, such as function calls. -public type ChatCompletionMessageToolCalls ChatCompletionMessageToolCall[]; - # Represents a chat completion response returned by model, based on the provided input. +# + usage - Usage statistics for the completion request. public type CreateChatCompletionResponse record { # A unique identifier for the chat completion. string id; @@ -298,30 +530,15 @@ public type ChatCompletionRequestFunctionMessage record { string name; }; -# Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. -public type ChatCompletionFunctionCallOption record { - # The name of the function to call. - string name; -}; - public type ChatCompletionRequestToolMessage record { # The role of the messages author, in this case `tool`. "tool" role; # The contents of the tool message. - string content; + string|ChatCompletionRequestToolMessageContentPart[] content; # Tool call that this message is responding to. string tool_call_id; }; -@deprecated -public type ChatCompletionFunctions record { - # A description of what the function does, used by the model to choose when and how to call the function. - string description?; - # The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. - string name; - FunctionParameters parameters?; -}; - # Proxy server configurations to be used with the HTTP client endpoint. public type ProxyConfig record {| # Host name of the proxy server @@ -335,28 +552,6 @@ public type ProxyConfig record {| string password = ""; |}; -public type ChatCompletionTool record { - # The type of the tool. Currently, only `function` is supported. - "function" 'type; - FunctionObject 'function; -}; - -public type ChatCompletionRequestSystemMessage record { - # The contents of the system message. - string content; - # The role of the messages author, in this case `system`. - "system" role; - # An optional name for the participant. Provides the model information to differentiate between participants of the same role. - string name?; -}; - -public type ChatCompletionRequestMessageContentPartImage_image_url record { - # Either a URL of the image or the base64 encoded image data. - string url; - # Specifies the detail level of the image. Learn more in the [Vision guide](/docs/guides/vision/low-or-high-fidelity-image-understanding). - "auto"|"low"|"high" detail = "auto"; -}; - public type ChatCompletionMessageToolCall record { # The ID of the tool call. string id; @@ -365,36 +560,27 @@ public type ChatCompletionMessageToolCall record { ChatCompletionMessageToolCall_function 'function; }; -# An object specifying the format that the model must output. Compatible with [GPT-4 Turbo](/docs/models/gpt-4-and-gpt-4-turbo) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. -# -# Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. -# -# **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. -public type CreateChatCompletionRequest_response_format record { - # Must be one of `text` or `json_object`. - "text"|"json_object" 'type = "text"; -}; +public type ChatCompletionRequestAssistantMessageContentPart ChatCompletionRequestMessageContentPartText|ChatCompletionRequestMessageContentPartRefusal; -# Whether to enable [parallel function calling](/docs/guides/function-calling/parallel-function-calling) during tool use. -public type ParallelToolCalls boolean; +public type ResponseFormatJsonObject record { + # The type of response format being defined: `json_object` + "json_object" 'type; +}; # A chat completion message generated by the model. +# + tool_calls - The tool calls generated by the model, such as function calls. +# + audio - If the audio output modality is requested, this object contains data about the audio response from the model. +# + function_call - Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. public type ChatCompletionResponseMessage record { # The contents of the message. string? content; + # The refusal message generated by the model. + string? refusal; ChatCompletionMessageToolCalls tool_calls?; # The role of the author of this message. "assistant" role; ChatCompletionResponseMessage_function_call function_call?; -}; - -public type ChatCompletionTokenLogprob_top_logprobs record { - # The token. - string token; - # The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. - decimal logprob; - # A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. - int[]? bytes; + ChatCompletionResponseMessage_audio? audio?; }; # Provides settings related to HTTP/1.x protocol. @@ -407,21 +593,16 @@ public type ClientHttp1Settings record {| ProxyConfig proxy?; |}; -public type ChatCompletionRequestMessageContentPartImage record { +public type ChatCompletionRequestMessageContentPartRefusal record { # The type of the content part. - "image_url" 'type; - ChatCompletionRequestMessageContentPartImage_image_url image_url; + "refusal" 'type; + # The refusal message generated by the model. + string refusal; }; -public type ChatCompletionRequestMessageContentPartText record { - # The type of the content part. - "text" 'type; - # The text content. - string text; -}; - -# The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. -# -# Omitting `parameters` defines a function with an empty parameter list. -public type FunctionParameters record { +# Data about a previous audio response from the model. +# [Learn more](/docs/guides/audio). +public type ChatCompletionRequestAssistantMessage_audio record { + # Unique identifier for a previous audio response from the model. + string id; }; diff --git a/docs/spec/openapi.yaml b/docs/spec/openapi.yaml index 1e0945a..100dde7 100644 --- a/docs/spec/openapi.yaml +++ b/docs/spec/openapi.yaml @@ -1,14280 +1,24941 @@ openapi: 3.0.0 info: - title: OpenAI API - description: The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details. - version: "2.1.0" - termsOfService: https://openai.com/policies/terms-of-use - contact: - name: OpenAI Support - url: https://help.openai.com/ - license: - name: MIT - url: https://github.com/openai/openai-openapi/blob/master/LICENSE + title: OpenAI API + description: The OpenAI REST API. Please see + https://platform.openai.com/docs/api-reference for more details. + version: 2.3.0 + termsOfService: https://openai.com/policies/terms-of-use + contact: + name: OpenAI Support + url: https://help.openai.com/ + license: + name: MIT + url: https://github.com/openai/openai-openapi/blob/master/LICENSE servers: - - url: https://api.openai.com/v1 + - url: https://api.openai.com/v1 tags: - - name: Assistants - description: Build Assistants that can call models and use tools. - - name: Audio - description: Turn audio into text or text into audio. - - name: Chat - description: Given a list of messages comprising a conversation, the model will return a response. - - name: Completions - description: Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position. - - name: Embeddings - description: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. - - name: Fine-tuning - description: Manage fine-tuning jobs to tailor a model to your specific training data. - - name: Batch - description: Create large batches of API requests to run asynchronously. - - name: Files - description: Files are used to upload documents that can be used with features like Assistants and Fine-tuning. - - name: Uploads - description: Use Uploads to upload large files in multiple parts. - - name: Images - description: Given a prompt and/or an input image, the model will generate a new image. - - name: Models - description: List and describe the various models available in the API. - - name: Moderations - description: Given a input text, outputs if the model classifies it as potentially harmful. + - name: Assistants + description: Build Assistants that can call models and use tools. + - name: Audio + description: Turn audio into text or text into audio. + - name: Chat + description: Given a list of messages comprising a conversation, the model will + return a response. + - name: Completions + description: Given a prompt, the model will return one or more predicted + completions, and can also return the probabilities of alternative tokens + at each position. + - name: Embeddings + description: Get a vector representation of a given input that can be easily + consumed by machine learning models and algorithms. + - name: Fine-tuning + description: Manage fine-tuning jobs to tailor a model to your specific training data. + - name: Batch + description: Create large batches of API requests to run asynchronously. + - name: Files + description: Files are used to upload documents that can be used with features + like Assistants and Fine-tuning. + - name: Uploads + description: Use Uploads to upload large files in multiple parts. + - name: Images + description: Given a prompt and/or an input image, the model will generate a new image. + - name: Models + description: List and describe the various models available in the API. + - name: Moderations + description: Given text and/or image inputs, classifies if those inputs are + potentially harmful. + - name: Audit Logs + description: List user actions and configuration changes within this organization. paths: - # Note: When adding an endpoint, make sure you also add it in the `groups` section, in the end of this file, - # under the appropriate group - /chat/completions: - post: - operationId: createChatCompletion - tags: - - Chat - summary: Creates a model response for the given chat conversation. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateChatCompletionRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/CreateChatCompletionResponse" - - x-oaiMeta: - name: Create chat completion - group: chat - returns: | - Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed. - path: create - examples: - - title: Default - request: - curl: | - curl https://api.openai.com/v1/chat/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "VAR_model_id", - "messages": [ - { - "role": "system", - "content": "You are a helpful assistant." - }, - { - "role": "user", - "content": "Hello!" - } - ] - }' - python: | - from openai import OpenAI - client = OpenAI() - - completion = client.chat.completions.create( - model="VAR_model_id", - messages=[ - {"role": "system", "content": "You are a helpful assistant."}, - {"role": "user", "content": "Hello!"} - ] - ) - - print(completion.choices[0].message) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const completion = await openai.chat.completions.create({ - messages: [{ role: "system", content: "You are a helpful assistant." }], - model: "VAR_model_id", - }); - - console.log(completion.choices[0]); - } + /assistants: + get: + operationId: listAssistants + tags: + - Assistants + summary: Returns a list of assistants. + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListAssistantsResponse" + x-oaiMeta: + name: List assistants + group: assistants + beta: true + returns: A list of [assistant](/docs/api-reference/assistants/object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/assistants?order=desc&limit=20" \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + my_assistants = client.beta.assistants.list( + order="desc", + limit="20", + ) + print(my_assistants.data) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const myAssistants = await openai.beta.assistants.list({ + order: "desc", + limit: "20", + }); + + console.log(myAssistants.data); + } + + main(); + response: > + { + "object": "list", + "data": [ + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698982736, + "name": "Coding Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc456", + "object": "assistant", + "created_at": 1698982718, + "name": "My Assistant", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc789", + "object": "assistant", + "created_at": 1698982643, + "name": null, + "description": null, + "model": "gpt-4o", + "instructions": null, + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + ], + "first_id": "asst_abc123", + "last_id": "asst_abc789", + "has_more": false + } + post: + operationId: createAssistant + tags: + - Assistants + summary: Create an assistant with a model and instructions. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateAssistantRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/AssistantObject" + x-oaiMeta: + name: Create assistant + group: assistants + beta: true + returns: An [assistant](/docs/api-reference/assistants/object) object. + examples: + - title: Code Interpreter + request: + curl: > + curl "https://api.openai.com/v1/assistants" \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + "name": "Math Tutor", + "tools": [{"type": "code_interpreter"}], + "model": "gpt-4o" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + my_assistant = client.beta.assistants.create( + instructions="You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + name="Math Tutor", + tools=[{"type": "code_interpreter"}], + model="gpt-4o", + ) + + print(my_assistant) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const myAssistant = await openai.beta.assistants.create({ + instructions: + "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + name: "Math Tutor", + tools: [{ type: "code_interpreter" }], + model: "gpt-4o", + }); + + console.log(myAssistant); + } + + + main(); + response: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698984975, + "name": "Math Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + - title: Files + request: + curl: > + curl https://api.openai.com/v1/assistants \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", + "tools": [{"type": "file_search"}], + "tool_resources": {"file_search": {"vector_store_ids": ["vs_123"]}}, + "model": "gpt-4o" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + my_assistant = client.beta.assistants.create( + instructions="You are an HR bot, and you have access to files to answer employee questions about company policies.", + name="HR Helper", + tools=[{"type": "file_search"}], + tool_resources={"file_search": {"vector_store_ids": ["vs_123"]}}, + model="gpt-4o" + ) + + print(my_assistant) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const myAssistant = await openai.beta.assistants.create({ + instructions: + "You are an HR bot, and you have access to files to answer employee questions about company policies.", + name: "HR Helper", + tools: [{ type: "file_search" }], + tool_resources: { + file_search: { + vector_store_ids: ["vs_123"] + } + }, + model: "gpt-4o" + }); + + console.log(myAssistant); + } + + + main(); + response: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1699009403, + "name": "HR Helper", + "description": null, + "model": "gpt-4o", + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", + "tools": [ + { + "type": "file_search" + } + ], + "tool_resources": { + "file_search": { + "vector_store_ids": ["vs_123"] + } + }, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + /assistants/{assistant_id}: + get: + operationId: getAssistant + tags: + - Assistants + summary: Retrieves an assistant. + parameters: + - in: path + name: assistant_id + required: true + schema: + type: string + description: The ID of the assistant to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/AssistantObject" + x-oaiMeta: + name: Retrieve assistant + group: assistants + beta: true + returns: The [assistant](/docs/api-reference/assistants/object) object matching + the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/assistants/asst_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + my_assistant = client.beta.assistants.retrieve("asst_abc123") + print(my_assistant) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const myAssistant = await openai.beta.assistants.retrieve( + "asst_abc123" + ); + + console.log(myAssistant); + } + + main(); + response: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1699009709, + "name": "HR Helper", + "description": null, + "model": "gpt-4o", + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", + "tools": [ + { + "type": "file_search" + } + ], + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + post: + operationId: modifyAssistant + tags: + - Assistants + summary: Modifies an assistant. + parameters: + - in: path + name: assistant_id + required: true + schema: + type: string + description: The ID of the assistant to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyAssistantRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/AssistantObject" + x-oaiMeta: + name: Modify assistant + group: assistants + beta: true + returns: The modified [assistant](/docs/api-reference/assistants/object) object. + examples: + request: + curl: > + curl https://api.openai.com/v1/assistants/asst_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + "tools": [{"type": "file_search"}], + "model": "gpt-4o" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + my_updated_assistant = client.beta.assistants.update( + "asst_abc123", + instructions="You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + name="HR Helper", + tools=[{"type": "file_search"}], + model="gpt-4o" + ) + + + print(my_updated_assistant) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const myUpdatedAssistant = await openai.beta.assistants.update( + "asst_abc123", + { + instructions: + "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + name: "HR Helper", + tools: [{ type: "file_search" }], + model: "gpt-4o" + } + ); + + console.log(myUpdatedAssistant); + } + + + main(); + response: > + { + "id": "asst_123", + "object": "assistant", + "created_at": 1699009709, + "name": "HR Helper", + "description": null, + "model": "gpt-4o", + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + "tools": [ + { + "type": "file_search" + } + ], + "tool_resources": { + "file_search": { + "vector_store_ids": [] + } + }, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + delete: + operationId: deleteAssistant + tags: + - Assistants + summary: Delete an assistant. + parameters: + - in: path + name: assistant_id + required: true + schema: + type: string + description: The ID of the assistant to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteAssistantResponse" + x-oaiMeta: + name: Delete assistant + group: assistants + beta: true + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/assistants/asst_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + response = client.beta.assistants.delete("asst_abc123") + print(response) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const response = await openai.beta.assistants.del("asst_abc123"); + + console.log(response); + } + + main(); + response: | + { + "id": "asst_abc123", + "object": "assistant.deleted", + "deleted": true + } + /audio/speech: + post: + operationId: createSpeech + tags: + - Audio + summary: Generates audio from the input text. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateSpeechRequest" + responses: + "200": + description: OK + headers: + Transfer-Encoding: + schema: + type: string + description: chunked + content: + application/octet-stream: + schema: + type: string + format: binary + x-oaiMeta: + name: Create speech + group: audio + returns: The audio file content. + examples: + request: + curl: | + curl https://api.openai.com/v1/audio/speech \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "tts-1", + "input": "The quick brown fox jumped over the lazy dog.", + "voice": "alloy" + }' \ + --output speech.mp3 + python: | + from pathlib import Path + import openai + + speech_file_path = Path(__file__).parent / "speech.mp3" + response = openai.audio.speech.create( + model="tts-1", + voice="alloy", + input="The quick brown fox jumped over the lazy dog." + ) + response.stream_to_file(speech_file_path) + node: > + import fs from "fs"; + + import path from "path"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const speechFile = path.resolve("./speech.mp3"); + + + async function main() { + const mp3 = await openai.audio.speech.create({ + model: "tts-1", + voice: "alloy", + input: "Today is a wonderful day to build something people love!", + }); + console.log(speechFile); + const buffer = Buffer.from(await mp3.arrayBuffer()); + await fs.promises.writeFile(speechFile, buffer); + } + + main(); + /audio/transcriptions: + post: + operationId: createTranscription + tags: + - Audio + summary: Transcribes audio into the input language. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateTranscriptionRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + oneOf: + - $ref: "#/components/schemas/CreateTranscriptionResponseJson" + - $ref: "#/components/schemas/CreateTranscriptionResponseVerboseJson" + x-oaiMeta: + name: Create transcription + group: audio + returns: The [transcription object](/docs/api-reference/audio/json-object) or a + [verbose transcription + object](/docs/api-reference/audio/verbose-json-object). + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F model="whisper-1" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + model="whisper-1", + file=audio_file + ) + node: > + import fs from "fs"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + }); + + console.log(transcription.text); + } + + main(); + response: > + { + "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that." + } + - title: Word timestamps + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F "timestamp_granularities[]=word" \ + -F model="whisper-1" \ + -F response_format="verbose_json" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + file=audio_file, + model="whisper-1", + response_format="verbose_json", + timestamp_granularities=["word"] + ) + + print(transcript.words) + node: > + import fs from "fs"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + response_format: "verbose_json", + timestamp_granularities: ["word"] + }); + + console.log(transcription.text); + } + + main(); + response: > + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "words": [ + { + "word": "The", + "start": 0.0, + "end": 0.23999999463558197 + }, + ... + { + "word": "volleyball", + "start": 7.400000095367432, + "end": 7.900000095367432 + } + ] + } + - title: Segment timestamps + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F "timestamp_granularities[]=segment" \ + -F model="whisper-1" \ + -F response_format="verbose_json" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + file=audio_file, + model="whisper-1", + response_format="verbose_json", + timestamp_granularities=["segment"] + ) + + print(transcript.words) + node: > + import fs from "fs"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + response_format: "verbose_json", + timestamp_granularities: ["segment"] + }); + + console.log(transcription.text); + } + + main(); + response: > + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "segments": [ + { + "id": 0, + "seek": 0, + "start": 0.0, + "end": 3.319999933242798, + "text": " The beach was a popular spot on a hot summer day.", + "tokens": [ + 50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530 + ], + "temperature": 0.0, + "avg_logprob": -0.2860786020755768, + "compression_ratio": 1.2363636493682861, + "no_speech_prob": 0.00985979475080967 + }, + ... + ] + } + /audio/translations: + post: + operationId: createTranslation + tags: + - Audio + summary: Translates audio into English. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateTranslationRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + oneOf: + - $ref: "#/components/schemas/CreateTranslationResponseJson" + - $ref: "#/components/schemas/CreateTranslationResponseVerboseJson" + x-oaiMeta: + name: Create translation + group: audio + returns: The translated text. + examples: + request: + curl: | + curl https://api.openai.com/v1/audio/translations \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/german.m4a" \ + -F model="whisper-1" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.translations.create( + model="whisper-1", + file=audio_file + ) + node: | + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const translation = await openai.audio.translations.create({ + file: fs.createReadStream("speech.mp3"), + model: "whisper-1", + }); + + console.log(translation.text); + } + main(); + response: > + { + "text": "Hello, my name is Wolfgang and I come from Germany. Where are you heading today?" + } + /batches: + post: + summary: Creates and executes a batch from an uploaded file of requests + operationId: createBatch + tags: + - Batch + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - input_file_id + - endpoint + - completion_window + properties: + input_file_id: + type: string + description: > + The ID of an uploaded file that contains requests for the + new batch. + + + See [upload file](/docs/api-reference/files/create) for how + to upload a file. + - main(); - response: &chat_completion_example | + Your input file must be formatted as a [JSONL + file](/docs/api-reference/batch/request-input), and must be + uploaded with the purpose `batch`. The file can contain up + to 50,000 requests, and can be up to 200 MB in size. + endpoint: + type: string + enum: + - /v1/chat/completions + - /v1/embeddings + - /v1/completions + description: The endpoint to be used for all requests in the batch. Currently + `/v1/chat/completions`, `/v1/embeddings`, and + `/v1/completions` are supported. Note that `/v1/embeddings` + batches are also restricted to a maximum of 50,000 embedding + inputs across all requests in the batch. + completion_window: + type: string + enum: + - 24h + description: The time frame within which the batch should be processed. + Currently only `24h` is supported. + metadata: + type: object + additionalProperties: + type: string + description: Optional custom metadata for the batch. + nullable: true + responses: + "200": + description: Batch created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Create batch + group: batch + returns: The created [Batch](/docs/api-reference/batch/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "input_file_id": "file-abc123", + "endpoint": "/v1/chat/completions", + "completion_window": "24h" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.create( + input_file_id="file-abc123", + endpoint="/v1/chat/completions", + completion_window="24h" + ) + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.create({ + input_file_id: "file-abc123", + endpoint: "/v1/chat/completions", + completion_window: "24h" + }); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "validating", + "output_file_id": null, + "error_file_id": null, + "created_at": 1711471533, + "in_progress_at": null, + "expires_at": null, + "finalizing_at": null, + "completed_at": null, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 0, + "completed": 0, + "failed": 0 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + get: + operationId: listBatches + tags: + - Batch + summary: List your organization's batches. + parameters: + - in: query + name: after + required: false + schema: + type: string + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + responses: + "200": + description: Batch listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListBatchesResponse" + x-oaiMeta: + name: List batch + group: batch + returns: A list of paginated [Batch](/docs/api-reference/batch/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches?limit=2 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.list() + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.batches.list(); + + for await (const batch of list) { + console.log(batch); + } + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly job", + } + }, + { ... }, + ], + "first_id": "batch_abc123", + "last_id": "batch_abc456", + "has_more": true + } + /batches/{batch_id}: + get: + operationId: retrieveBatch + tags: + - Batch + summary: Retrieves a batch. + parameters: + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the batch to retrieve. + responses: + "200": + description: Batch retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Retrieve batch + group: batch + returns: The [Batch](/docs/api-reference/batch/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches/batch_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.retrieve("batch_abc123") + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.retrieve("batch_abc123"); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + /batches/{batch_id}/cancel: + post: + operationId: cancelBatch + tags: + - Batch + summary: Cancels an in-progress batch. The batch will be in status `cancelling` + for up to 10 minutes, before changing to `cancelled`, where it will have + partial results (if any) available in the output file. + parameters: + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the batch to cancel. + responses: + "200": + description: Batch is cancelling. Returns the cancelling batch's details. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Cancel batch + group: batch + returns: The [Batch](/docs/api-reference/batch/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches/batch_abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -X POST + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.cancel("batch_abc123") + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.cancel("batch_abc123"); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "cancelling", + "output_file_id": null, + "error_file_id": null, + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": null, + "completed_at": null, + "failed_at": null, + "expired_at": null, + "cancelling_at": 1711475133, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 23, + "failed": 1 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + /chat/completions: + post: + operationId: createChatCompletion + tags: + - Chat + summary: > + Creates a model response for the given chat conversation. Learn more in + the + + [text generation](/docs/guides/text-generation), + [vision](/docs/guides/vision), + + and [audio](/docs/guides/audio) guides. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateChatCompletionRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateChatCompletionResponse" + x-oaiMeta: + name: Create chat completion + group: chat + returns: > + Returns a [chat completion](/docs/api-reference/chat/object) object, + or a streamed sequence of [chat completion + chunk](/docs/api-reference/chat/streaming) objects if the request is + streamed. + path: create + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_chat_model_id", + "messages": [ + { + "role": "system", + "content": "You are a helpful assistant." + }, + { + "role": "user", + "content": "Hello!" + } + ] + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=[ + {"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": "Hello!"} + ] + ) + + + print(completion.choices[0].message) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const completion = await openai.chat.completions.create({ + messages: [{ role: "system", content: "You are a helpful assistant." }], + model: "VAR_chat_model_id", + }); + + console.log(completion.choices[0]); + } + + + main(); + response: | + { + "id": "chatcmpl-123", + "object": "chat.completion", + "created": 1677652288, + "model": "gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices": [{ + "index": 0, + "message": { + "role": "assistant", + "content": "\n\nHello there, how may I assist you today?", + }, + "logprobs": null, + "finish_reason": "stop" + }], + "usage": { + "prompt_tokens": 9, + "completion_tokens": 12, + "total_tokens": 21, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } + } + - title: Image input + request: + curl: > + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": [ { - "id": "chatcmpl-123", - "object": "chat.completion", - "created": 1677652288, - "model": "gpt-4o-mini", - "system_fingerprint": "fp_44709d6fcb", - "choices": [{ - "index": 0, - "message": { - "role": "assistant", - "content": "\n\nHello there, how may I assist you today?", - }, - "logprobs": null, - "finish_reason": "stop" - }], - "usage": { - "prompt_tokens": 9, - "completion_tokens": 12, - "total_tokens": 21 - } - } - - title: Image input - request: - curl: | - curl https://api.openai.com/v1/chat/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "gpt-4-turbo", - "messages": [ - { - "role": "user", - "content": [ - { - "type": "text", - "text": "What'\''s in this image?" - }, - { - "type": "image_url", - "image_url": { - "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" - } - } - ] - } - ], - "max_tokens": 300 - }' - python: | - from openai import OpenAI - - client = OpenAI() - - response = client.chat.completions.create( - model="gpt-4-turbo", - messages=[ - { - "role": "user", - "content": [ - {"type": "text", "text": "What's in this image?"}, - { - "type": "image_url", - "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", - }, - ], - } - ], - max_tokens=300, - ) - - print(response.choices[0]) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const response = await openai.chat.completions.create({ - model: "gpt-4-turbo", - messages: [ - { - role: "user", - content: [ - { type: "text", text: "What's in this image?" }, - { - type: "image_url", - image_url: - "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", - }, - ], - }, - ], - }); - console.log(response.choices[0]); - } - main(); - response: &chat_completion_image_example | + "type": "text", + "text": "What'\''s in this image?" + }, { - "id": "chatcmpl-123", - "object": "chat.completion", - "created": 1677652288, - "model": "gpt-4o-mini", - "system_fingerprint": "fp_44709d6fcb", - "choices": [{ - "index": 0, - "message": { - "role": "assistant", - "content": "\n\nThis image shows a wooden boardwalk extending through a lush green marshland.", - }, - "logprobs": null, - "finish_reason": "stop" - }], - "usage": { - "prompt_tokens": 9, - "completion_tokens": 12, - "total_tokens": 21 + "type": "image_url", + "image_url": { + "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" } } - - title: Streaming - request: - curl: | - curl https://api.openai.com/v1/chat/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "VAR_model_id", - "messages": [ - { - "role": "system", - "content": "You are a helpful assistant." - }, - { - "role": "user", - "content": "Hello!" - } - ], - "stream": true - }' - python: | - from openai import OpenAI - client = OpenAI() - - completion = client.chat.completions.create( - model="VAR_model_id", - messages=[ - {"role": "system", "content": "You are a helpful assistant."}, - {"role": "user", "content": "Hello!"} - ], - stream=True - ) - - for chunk in completion: - print(chunk.choices[0].delta) - - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const completion = await openai.chat.completions.create({ - model: "VAR_model_id", - messages: [ - {"role": "system", "content": "You are a helpful assistant."}, - {"role": "user", "content": "Hello!"} - ], - stream: true, - }); - - for await (const chunk of completion) { - console.log(chunk.choices[0].delta.content); - } - } + ] + } + ], + "max_tokens": 300 + }' + python: > + from openai import OpenAI - main(); - response: &chat_completion_chunk_example | - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} - - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} - - .... - - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} - - title: Functions - request: - curl: | - curl https://api.openai.com/v1/chat/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "gpt-4-turbo", - "messages": [ - { - "role": "user", - "content": "What'\''s the weather like in Boston today?" - } - ], - "tools": [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA" - }, - "unit": { - "type": "string", - "enum": ["celsius", "fahrenheit"] - } - }, - "required": ["location"] - } - } - } - ], - "tool_choice": "auto" - }' - python: | - from openai import OpenAI - client = OpenAI() - - tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, - }, - "required": ["location"], - }, - } - } - ] - messages = [{"role": "user", "content": "What's the weather like in Boston today?"}] - completion = client.chat.completions.create( - model="VAR_model_id", - messages=messages, - tools=tools, - tool_choice="auto" - ) - - print(completion) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]; - const tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, - }, - "required": ["location"], - }, - } - } - ]; - const response = await openai.chat.completions.create({ - model: "gpt-4-turbo", - messages: messages, - tools: tools, - tool_choice: "auto", - }); + client = OpenAI() - console.log(response); - } - main(); - response: &chat_completion_function_example | - { - "id": "chatcmpl-abc123", - "object": "chat.completion", - "created": 1699896916, - "model": "gpt-4o-mini", - "choices": [ - { - "index": 0, - "message": { - "role": "assistant", - "content": null, - "tool_calls": [ - { - "id": "call_abc123", - "type": "function", - "function": { - "name": "get_current_weather", - "arguments": "{\n\"location\": \"Boston, MA\"\n}" - } + response = client.chat.completions.create( + model="gpt-4o", + messages=[ + { + "role": "user", + "content": [ + {"type": "text", "text": "What's in this image?"}, + { + "type": "image_url", + "image_url": { + "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", } - ] }, - "logprobs": null, - "finish_reason": "tool_calls" - } ], - "usage": { - "prompt_tokens": 82, - "completion_tokens": 17, - "total_tokens": 99 - } - } - - title: Logprobs - request: - curl: | - curl https://api.openai.com/v1/chat/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "VAR_model_id", - "messages": [ - { - "role": "user", - "content": "Hello!" - } - ], - "logprobs": true, - "top_logprobs": 2 - }' - python: | - from openai import OpenAI - client = OpenAI() - - completion = client.chat.completions.create( - model="VAR_model_id", - messages=[ - {"role": "user", "content": "Hello!"} - ], - logprobs=True, - top_logprobs=2 - ) - - print(completion.choices[0].message) - print(completion.choices[0].logprobs) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const completion = await openai.chat.completions.create({ - messages: [{ role: "user", content: "Hello!" }], - model: "VAR_model_id", - logprobs: true, - top_logprobs: 2, - }); - - console.log(completion.choices[0]); - } + } + ], + max_tokens=300, + ) + + + print(response.choices[0]) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + - main(); - response: | + async function main() { + const response = await openai.chat.completions.create({ + model: "gpt-4o", + messages: [ + { + role: "user", + content: [ + { type: "text", text: "What's in this image?" }, { - "id": "chatcmpl-123", - "object": "chat.completion", - "created": 1702685778, - "model": "gpt-4o-mini", - "choices": [ - { - "index": 0, - "message": { - "role": "assistant", - "content": "Hello! How can I assist you today?" - }, - "logprobs": { - "content": [ - { - "token": "Hello", - "logprob": -0.31725305, - "bytes": [72, 101, 108, 108, 111], - "top_logprobs": [ - { - "token": "Hello", - "logprob": -0.31725305, - "bytes": [72, 101, 108, 108, 111] - }, - { - "token": "Hi", - "logprob": -1.3190403, - "bytes": [72, 105] - } - ] - }, - { - "token": "!", - "logprob": -0.02380986, - "bytes": [ - 33 - ], - "top_logprobs": [ - { - "token": "!", - "logprob": -0.02380986, - "bytes": [33] - }, - { - "token": " there", - "logprob": -3.787621, - "bytes": [32, 116, 104, 101, 114, 101] - } - ] - }, - { - "token": " How", - "logprob": -0.000054669687, - "bytes": [32, 72, 111, 119], - "top_logprobs": [ - { - "token": " How", - "logprob": -0.000054669687, - "bytes": [32, 72, 111, 119] - }, - { - "token": "<|end|>", - "logprob": -10.953937, - "bytes": null - } - ] - }, - { - "token": " can", - "logprob": -0.015801601, - "bytes": [32, 99, 97, 110], - "top_logprobs": [ - { - "token": " can", - "logprob": -0.015801601, - "bytes": [32, 99, 97, 110] - }, - { - "token": " may", - "logprob": -4.161023, - "bytes": [32, 109, 97, 121] - } - ] - }, - { - "token": " I", - "logprob": -3.7697225e-6, - "bytes": [ - 32, - 73 - ], - "top_logprobs": [ - { - "token": " I", - "logprob": -3.7697225e-6, - "bytes": [32, 73] - }, - { - "token": " assist", - "logprob": -13.596657, - "bytes": [32, 97, 115, 115, 105, 115, 116] - } - ] - }, - { - "token": " assist", - "logprob": -0.04571125, - "bytes": [32, 97, 115, 115, 105, 115, 116], - "top_logprobs": [ - { - "token": " assist", - "logprob": -0.04571125, - "bytes": [32, 97, 115, 115, 105, 115, 116] - }, - { - "token": " help", - "logprob": -3.1089056, - "bytes": [32, 104, 101, 108, 112] - } - ] - }, - { - "token": " you", - "logprob": -5.4385737e-6, - "bytes": [32, 121, 111, 117], - "top_logprobs": [ - { - "token": " you", - "logprob": -5.4385737e-6, - "bytes": [32, 121, 111, 117] - }, - { - "token": " today", - "logprob": -12.807695, - "bytes": [32, 116, 111, 100, 97, 121] - } - ] - }, - { - "token": " today", - "logprob": -0.0040071653, - "bytes": [32, 116, 111, 100, 97, 121], - "top_logprobs": [ - { - "token": " today", - "logprob": -0.0040071653, - "bytes": [32, 116, 111, 100, 97, 121] - }, - { - "token": "?", - "logprob": -5.5247097, - "bytes": [63] - } - ] - }, - { - "token": "?", - "logprob": -0.0008108172, - "bytes": [63], - "top_logprobs": [ - { - "token": "?", - "logprob": -0.0008108172, - "bytes": [63] - }, - { - "token": "?\n", - "logprob": -7.184561, - "bytes": [63, 10] - } - ] - } - ] - }, - "finish_reason": "stop" - } - ], - "usage": { - "prompt_tokens": 9, - "completion_tokens": 9, - "total_tokens": 18 + type: "image_url", + image_url: { + "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", }, - "system_fingerprint": null } + ], + }, + ], + }); + console.log(response.choices[0]); + } + + main(); + response: > + { + "id": "chatcmpl-123", + "object": "chat.completion", + "created": 1677652288, + "model": "gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices": [{ + "index": 0, + "message": { + "role": "assistant", + "content": "\n\nThis image shows a wooden boardwalk extending through a lush green marshland.", + }, + "logprobs": null, + "finish_reason": "stop" + }], + "usage": { + "prompt_tokens": 9, + "completion_tokens": 12, + "total_tokens": 21, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_chat_model_id", + "messages": [ + { + "role": "system", + "content": "You are a helpful assistant." + }, + { + "role": "user", + "content": "Hello!" + } + ], + "stream": true + }' + python: > + from openai import OpenAI - /completions: - post: - operationId: createCompletion - tags: - - Completions - summary: Creates a completion for the provided prompt and parameters. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateCompletionRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/CreateCompletionResponse" - x-oaiMeta: - name: Create completion - group: completions - returns: | - Returns a [completion](/docs/api-reference/completions/object) object, or a sequence of completion objects if the request is streamed. - legacy: true - examples: - - title: No streaming - request: - curl: | - curl https://api.openai.com/v1/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "VAR_model_id", - "prompt": "Say this is a test", - "max_tokens": 7, - "temperature": 0 - }' - python: | - from openai import OpenAI - client = OpenAI() - - client.completions.create( - model="VAR_model_id", - prompt="Say this is a test", - max_tokens=7, - temperature=0 - ) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const completion = await openai.completions.create({ - model: "VAR_model_id", - prompt: "Say this is a test.", - max_tokens: 7, - temperature: 0, - }); - - console.log(completion); - } - main(); - response: | - { - "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", - "object": "text_completion", - "created": 1589478378, - "model": "VAR_model_id", - "system_fingerprint": "fp_44709d6fcb", - "choices": [ - { - "text": "\n\nThis is indeed a test", - "index": 0, - "logprobs": null, - "finish_reason": "length" - } - ], - "usage": { - "prompt_tokens": 5, - "completion_tokens": 7, - "total_tokens": 12 - } - } - - title: Streaming - request: - curl: | - curl https://api.openai.com/v1/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "VAR_model_id", - "prompt": "Say this is a test", - "max_tokens": 7, - "temperature": 0, - "stream": true - }' - python: | - from openai import OpenAI - client = OpenAI() - - for chunk in client.completions.create( - model="VAR_model_id", - prompt="Say this is a test", - max_tokens=7, - temperature=0, - stream=True - ): - print(chunk.choices[0].text) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const stream = await openai.completions.create({ - model: "VAR_model_id", - prompt: "Say this is a test.", - stream: true, - }); - - for await (const chunk of stream) { - console.log(chunk.choices[0].text) - } - } - main(); - response: | - { - "id": "cmpl-7iA7iJjj8V2zOkCGvWF2hAkDWBQZe", - "object": "text_completion", - "created": 1690759702, - "choices": [ - { - "text": "This", - "index": 0, - "logprobs": null, - "finish_reason": null - } - ], - "model": "gpt-3.5-turbo-instruct" - "system_fingerprint": "fp_44709d6fcb", - } + client = OpenAI() - /images/generations: - post: - operationId: createImage - tags: - - Images - summary: Creates an image given a prompt. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateImageRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ImagesResponse" - x-oaiMeta: - name: Create image - group: images - returns: Returns a list of [image](/docs/api-reference/images/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/images/generations \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "model": "dall-e-3", - "prompt": "A cute baby sea otter", - "n": 1, - "size": "1024x1024" - }' - python: | - from openai import OpenAI - client = OpenAI() - - client.images.generate( - model="dall-e-3", - prompt="A cute baby sea otter", - n=1, - size="1024x1024" - ) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const image = await openai.images.generate({ model: "dall-e-3", prompt: "A cute baby sea otter" }); - - console.log(image.data); + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=[ + {"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": "Hello!"} + ], + stream=True + ) + + + for chunk in completion: + print(chunk.choices[0].delta) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const completion = await openai.chat.completions.create({ + model: "VAR_chat_model_id", + messages: [ + {"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": "Hello!"} + ], + stream: true, + }); + + for await (const chunk of completion) { + console.log(chunk.choices[0].delta.content); + } + } + + + main(); + response: > + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} + + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} + + + .... + + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} + - title: Functions + request: + curl: > + curl https://api.openai.com/v1/chat/completions \ + + -H "Content-Type: application/json" \ + + -H "Authorization: Bearer $OPENAI_API_KEY" \ + + -d '{ + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What'\''s the weather like in Boston today?" + } + ], + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] } - main(); - response: | + }, + "required": ["location"] + } + } + } + ], + "tool_choice": "auto" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ] + + messages = [{"role": "user", "content": "What's the weather like + in Boston today?"}] + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=messages, + tools=tools, + tool_choice="auto" + ) + + + print(completion) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]; + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; + + const response = await openai.chat.completions.create({ + model: "gpt-4o", + messages: messages, + tools: tools, + tool_choice: "auto", + }); + + console.log(response); + } + + + main(); + response: | + { + "id": "chatcmpl-abc123", + "object": "chat.completion", + "created": 1699896916, + "model": "gpt-4o-mini", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": null, + "tool_calls": [ + { + "id": "call_abc123", + "type": "function", + "function": { + "name": "get_current_weather", + "arguments": "{\n\"location\": \"Boston, MA\"\n}" + } + } + ] + }, + "logprobs": null, + "finish_reason": "tool_calls" + } + ], + "usage": { + "prompt_tokens": 82, + "completion_tokens": 17, + "total_tokens": 99, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } + } + - title: Logprobs + request: + curl: | + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_chat_model_id", + "messages": [ + { + "role": "user", + "content": "Hello!" + } + ], + "logprobs": true, + "top_logprobs": 2 + }' + python: | + from openai import OpenAI + client = OpenAI() + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=[ + {"role": "user", "content": "Hello!"} + ], + logprobs=True, + top_logprobs=2 + ) + + print(completion.choices[0].message) + print(completion.choices[0].logprobs) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const completion = await openai.chat.completions.create({ + messages: [{ role: "user", content: "Hello!" }], + model: "VAR_chat_model_id", + logprobs: true, + top_logprobs: 2, + }); + + console.log(completion.choices[0]); + } + + main(); + response: | + { + "id": "chatcmpl-123", + "object": "chat.completion", + "created": 1702685778, + "model": "gpt-4o-mini", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "Hello! How can I assist you today?" + }, + "logprobs": { + "content": [ { - "created": 1589478378, - "data": [ + "token": "Hello", + "logprob": -0.31725305, + "bytes": [72, 101, 108, 108, 111], + "top_logprobs": [ { - "url": "https://..." + "token": "Hello", + "logprob": -0.31725305, + "bytes": [72, 101, 108, 108, 111] }, { - "url": "https://..." + "token": "Hi", + "logprob": -1.3190403, + "bytes": [72, 105] } ] - } - /images/edits: - post: - operationId: createImageEdit - tags: - - Images - summary: Creates an edited or extended image given an original image and a prompt. - requestBody: - required: true - content: - multipart/form-data: - schema: - $ref: "#/components/schemas/CreateImageEditRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ImagesResponse" - x-oaiMeta: - name: Create image edit - group: images - returns: Returns a list of [image](/docs/api-reference/images/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/images/edits \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -F image="@otter.png" \ - -F mask="@mask.png" \ - -F prompt="A cute baby sea otter wearing a beret" \ - -F n=2 \ - -F size="1024x1024" - python: | - from openai import OpenAI - client = OpenAI() - - client.images.edit( - image=open("otter.png", "rb"), - mask=open("mask.png", "rb"), - prompt="A cute baby sea otter wearing a beret", - n=2, - size="1024x1024" - ) - node.js: |- - import fs from "fs"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const image = await openai.images.edit({ - image: fs.createReadStream("otter.png"), - mask: fs.createReadStream("mask.png"), - prompt: "A cute baby sea otter wearing a beret", - }); - - console.log(image.data); - } - main(); - response: | + }, { - "created": 1589478378, - "data": [ + "token": "!", + "logprob": -0.02380986, + "bytes": [ + 33 + ], + "top_logprobs": [ { - "url": "https://..." + "token": "!", + "logprob": -0.02380986, + "bytes": [33] }, { - "url": "https://..." + "token": " there", + "logprob": -3.787621, + "bytes": [32, 116, 104, 101, 114, 101] } ] - } - /images/variations: - post: - operationId: createImageVariation - tags: - - Images - summary: Creates a variation of a given image. - requestBody: - required: true - content: - multipart/form-data: - schema: - $ref: "#/components/schemas/CreateImageVariationRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ImagesResponse" - x-oaiMeta: - name: Create image variation - group: images - returns: Returns a list of [image](/docs/api-reference/images/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/images/variations \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -F image="@otter.png" \ - -F n=2 \ - -F size="1024x1024" - python: | - from openai import OpenAI - client = OpenAI() - - response = client.images.create_variation( - image=open("image_edit_original.png", "rb"), - n=2, - size="1024x1024" - ) - node.js: |- - import fs from "fs"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const image = await openai.images.createVariation({ - image: fs.createReadStream("otter.png"), - }); - - console.log(image.data); - } - main(); - response: | + }, { - "created": 1589478378, - "data": [ + "token": " How", + "logprob": -0.000054669687, + "bytes": [32, 72, 111, 119], + "top_logprobs": [ { - "url": "https://..." + "token": " How", + "logprob": -0.000054669687, + "bytes": [32, 72, 111, 119] }, { - "url": "https://..." + "token": "<|end|>", + "logprob": -10.953937, + "bytes": null } ] - } - - /embeddings: - post: - operationId: createEmbedding - tags: - - Embeddings - summary: Creates an embedding vector representing the input text. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateEmbeddingRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/CreateEmbeddingResponse" - x-oaiMeta: - name: Create embeddings - group: embeddings - returns: A list of [embedding](/docs/api-reference/embeddings/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/embeddings \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -d '{ - "input": "The food was delicious and the waiter...", - "model": "text-embedding-ada-002", - "encoding_format": "float" - }' - python: | - from openai import OpenAI - client = OpenAI() - - client.embeddings.create( - model="text-embedding-ada-002", - input="The food was delicious and the waiter...", - encoding_format="float" - ) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const embedding = await openai.embeddings.create({ - model: "text-embedding-ada-002", - input: "The quick brown fox jumped over the lazy dog", - encoding_format: "float", - }); - - console.log(embedding); - } - - main(); - response: | + }, { - "object": "list", - "data": [ + "token": " can", + "logprob": -0.015801601, + "bytes": [32, 99, 97, 110], + "top_logprobs": [ { - "object": "embedding", - "embedding": [ - 0.0023064255, - -0.009327292, - .... (1536 floats total for ada-002) - -0.0028842222, - ], - "index": 0 + "token": " can", + "logprob": -0.015801601, + "bytes": [32, 99, 97, 110] + }, + { + "token": " may", + "logprob": -4.161023, + "bytes": [32, 109, 97, 121] } + ] + }, + { + "token": " I", + "logprob": -3.7697225e-6, + "bytes": [ + 32, + 73 ], - "model": "text-embedding-ada-002", - "usage": { - "prompt_tokens": 8, - "total_tokens": 8 - } - } - - /audio/speech: - post: - operationId: createSpeech - tags: - - Audio - summary: Generates audio from the input text. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateSpeechRequest" - responses: - "200": - description: OK - headers: - Transfer-Encoding: - schema: - type: string - description: chunked - content: - application/octet-stream: - schema: - type: string - format: binary - x-oaiMeta: - name: Create speech - group: audio - returns: The audio file content. - examples: - request: - curl: | - curl https://api.openai.com/v1/audio/speech \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -d '{ - "model": "tts-1", - "input": "The quick brown fox jumped over the lazy dog.", - "voice": "alloy" - }' \ - --output speech.mp3 - python: | - from pathlib import Path - import openai - - speech_file_path = Path(__file__).parent / "speech.mp3" - response = openai.audio.speech.create( - model="tts-1", - voice="alloy", - input="The quick brown fox jumped over the lazy dog." - ) - response.stream_to_file(speech_file_path) - node: | - import fs from "fs"; - import path from "path"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - const speechFile = path.resolve("./speech.mp3"); - - async function main() { - const mp3 = await openai.audio.speech.create({ - model: "tts-1", - voice: "alloy", - input: "Today is a wonderful day to build something people love!", - }); - console.log(speechFile); - const buffer = Buffer.from(await mp3.arrayBuffer()); - await fs.promises.writeFile(speechFile, buffer); - } - main(); - /audio/transcriptions: - post: - operationId: createTranscription - tags: - - Audio - summary: Transcribes audio into the input language. - requestBody: - required: true - content: - multipart/form-data: - schema: - $ref: "#/components/schemas/CreateTranscriptionRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - oneOf: - - $ref: "#/components/schemas/CreateTranscriptionResponseJson" - - $ref: "#/components/schemas/CreateTranscriptionResponseVerboseJson" - x-oaiMeta: - name: Create transcription - group: audio - returns: The [transcription object](/docs/api-reference/audio/json-object) or a [verbose transcription object](/docs/api-reference/audio/verbose-json-object). - examples: - - title: Default - request: - curl: | - curl https://api.openai.com/v1/audio/transcriptions \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: multipart/form-data" \ - -F file="@/path/to/file/audio.mp3" \ - -F model="whisper-1" - python: | - from openai import OpenAI - client = OpenAI() - - audio_file = open("speech.mp3", "rb") - transcript = client.audio.transcriptions.create( - model="whisper-1", - file=audio_file - ) - node: | - import fs from "fs"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const transcription = await openai.audio.transcriptions.create({ - file: fs.createReadStream("audio.mp3"), - model: "whisper-1", - }); - - console.log(transcription.text); - } - main(); - response: &basic_transcription_response_example | - { - "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that." - } - - title: Word timestamps - request: - curl: | - curl https://api.openai.com/v1/audio/transcriptions \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: multipart/form-data" \ - -F file="@/path/to/file/audio.mp3" \ - -F "timestamp_granularities[]=word" \ - -F model="whisper-1" \ - -F response_format="verbose_json" - python: | - from openai import OpenAI - client = OpenAI() - - audio_file = open("speech.mp3", "rb") - transcript = client.audio.transcriptions.create( - file=audio_file, - model="whisper-1", - response_format="verbose_json", - timestamp_granularities=["word"] - ) - - print(transcript.words) - node: | - import fs from "fs"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const transcription = await openai.audio.transcriptions.create({ - file: fs.createReadStream("audio.mp3"), - model: "whisper-1", - response_format: "verbose_json", - timestamp_granularities: ["word"] - }); - - console.log(transcription.text); - } - main(); - response: | - { - "task": "transcribe", - "language": "english", - "duration": 8.470000267028809, - "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", - "words": [ - { - "word": "The", - "start": 0.0, - "end": 0.23999999463558197 - }, - ... - { - "word": "volleyball", - "start": 7.400000095367432, - "end": 7.900000095367432 - } - ] - } - - title: Segment timestamps - request: - curl: | - curl https://api.openai.com/v1/audio/transcriptions \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: multipart/form-data" \ - -F file="@/path/to/file/audio.mp3" \ - -F "timestamp_granularities[]=segment" \ - -F model="whisper-1" \ - -F response_format="verbose_json" - python: | - from openai import OpenAI - client = OpenAI() - - audio_file = open("speech.mp3", "rb") - transcript = client.audio.transcriptions.create( - file=audio_file, - model="whisper-1", - response_format="verbose_json", - timestamp_granularities=["segment"] - ) - - print(transcript.words) - node: | - import fs from "fs"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const transcription = await openai.audio.transcriptions.create({ - file: fs.createReadStream("audio.mp3"), - model: "whisper-1", - response_format: "verbose_json", - timestamp_granularities: ["segment"] - }); - - console.log(transcription.text); - } - main(); - response: &verbose_transcription_response_example | - { - "task": "transcribe", - "language": "english", - "duration": 8.470000267028809, - "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", - "segments": [ - { - "id": 0, - "seek": 0, - "start": 0.0, - "end": 3.319999933242798, - "text": " The beach was a popular spot on a hot summer day.", - "tokens": [ - 50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530 - ], - "temperature": 0.0, - "avg_logprob": -0.2860786020755768, - "compression_ratio": 1.2363636493682861, - "no_speech_prob": 0.00985979475080967 - }, - ... - ] - } - /audio/translations: - post: - operationId: createTranslation - tags: - - Audio - summary: Translates audio into English. - requestBody: - required: true - content: - multipart/form-data: - schema: - $ref: "#/components/schemas/CreateTranslationRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - oneOf: - - $ref: "#/components/schemas/CreateTranslationResponseJson" - - $ref: "#/components/schemas/CreateTranslationResponseVerboseJson" - x-oaiMeta: - name: Create translation - group: audio - returns: The translated text. - examples: - request: - curl: | - curl https://api.openai.com/v1/audio/translations \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: multipart/form-data" \ - -F file="@/path/to/file/german.m4a" \ - -F model="whisper-1" - python: | - from openai import OpenAI - client = OpenAI() - - audio_file = open("speech.mp3", "rb") - transcript = client.audio.translations.create( - model="whisper-1", - file=audio_file - ) - node: | - import fs from "fs"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const translation = await openai.audio.translations.create({ - file: fs.createReadStream("speech.mp3"), - model: "whisper-1", - }); - - console.log(translation.text); + "top_logprobs": [ + { + "token": " I", + "logprob": -3.7697225e-6, + "bytes": [32, 73] + }, + { + "token": " assist", + "logprob": -13.596657, + "bytes": [32, 97, 115, 115, 105, 115, 116] } - main(); - response: | + ] + }, { - "text": "Hello, my name is Wolfgang and I come from Germany. Where are you heading today?" - } - - /files: - get: - operationId: listFiles - tags: - - Files - summary: Returns a list of files that belong to the user's organization. - parameters: - - in: query - name: purpose - required: false - schema: - type: string - description: Only return files with the given purpose. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListFilesResponse" - x-oaiMeta: - name: List files - group: files - returns: A list of [File](/docs/api-reference/files/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/files \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.files.list() - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const list = await openai.files.list(); - - for await (const file of list) { - console.log(file); - } + "token": " assist", + "logprob": -0.04571125, + "bytes": [32, 97, 115, 115, 105, 115, 116], + "top_logprobs": [ + { + "token": " assist", + "logprob": -0.04571125, + "bytes": [32, 97, 115, 115, 105, 115, 116] + }, + { + "token": " help", + "logprob": -3.1089056, + "bytes": [32, 104, 101, 108, 112] } - - main(); - response: | + ] + }, { - "data": [ + "token": " you", + "logprob": -5.4385737e-6, + "bytes": [32, 121, 111, 117], + "top_logprobs": [ { - "id": "file-abc123", - "object": "file", - "bytes": 175, - "created_at": 1613677385, - "filename": "salesOverview.pdf", - "purpose": "assistants", + "token": " you", + "logprob": -5.4385737e-6, + "bytes": [32, 121, 111, 117] }, { - "id": "file-abc123", - "object": "file", - "bytes": 140, - "created_at": 1613779121, - "filename": "puppy.jsonl", - "purpose": "fine-tune", + "token": " today", + "logprob": -12.807695, + "bytes": [32, 116, 111, 100, 97, 121] } - ], - "object": "list" - } - post: - operationId: createFile - tags: - - Files - summary: | - Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and the size of all files uploaded by one organization can be up to 100 GB. - - The Assistants API supports files up to 2 million tokens and of specific file types. See the [Assistants Tools guide](/docs/assistants/tools) for details. - - The Fine-tuning API only supports `.jsonl` files. The input also has certain required formats for fine-tuning [chat](/docs/api-reference/fine-tuning/chat-input) or [completions](/docs/api-reference/fine-tuning/completions-input) models. - - The Batch API only supports `.jsonl` files up to 100 MB in size. The input also has a specific required [format](/docs/api-reference/batch/request-input). - - Please [contact us](https://help.openai.com/) if you need to increase these storage limits. - requestBody: - required: true - content: - multipart/form-data: - schema: - $ref: "#/components/schemas/CreateFileRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/OpenAIFile" - x-oaiMeta: - name: Upload file - group: files - returns: The uploaded [File](/docs/api-reference/files/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/files \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -F purpose="fine-tune" \ - -F file="@mydata.jsonl" - python: | - from openai import OpenAI - client = OpenAI() - - client.files.create( - file=open("mydata.jsonl", "rb"), - purpose="fine-tune" - ) - node.js: |- - import fs from "fs"; - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const file = await openai.files.create({ - file: fs.createReadStream("mydata.jsonl"), - purpose: "fine-tune", - }); - - console.log(file); + ] + }, + { + "token": " today", + "logprob": -0.0040071653, + "bytes": [32, 116, 111, 100, 97, 121], + "top_logprobs": [ + { + "token": " today", + "logprob": -0.0040071653, + "bytes": [32, 116, 111, 100, 97, 121] + }, + { + "token": "?", + "logprob": -5.5247097, + "bytes": [63] } - - main(); - response: | + ] + }, { - "id": "file-abc123", - "object": "file", - "bytes": 120000, - "created_at": 1677610602, - "filename": "mydata.jsonl", - "purpose": "fine-tune", - } - /files/{file_id}: - delete: - operationId: deleteFile - tags: - - Files - summary: Delete a file. - parameters: - - in: path - name: file_id - required: true - schema: - type: string - description: The ID of the file to use for this request. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/DeleteFileResponse" - x-oaiMeta: - name: Delete file - group: files - returns: Deletion status. - examples: - request: - curl: | - curl https://api.openai.com/v1/files/file-abc123 \ - -X DELETE \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.files.delete("file-abc123") - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const file = await openai.files.del("file-abc123"); - - console.log(file); + "token": "?", + "logprob": -0.0008108172, + "bytes": [63], + "top_logprobs": [ + { + "token": "?", + "logprob": -0.0008108172, + "bytes": [63] + }, + { + "token": "?\n", + "logprob": -7.184561, + "bytes": [63, 10] } - - main(); - response: | - { - "id": "file-abc123", - "object": "file", - "deleted": true + ] } - get: - operationId: retrieveFile - tags: - - Files - summary: Returns information about a specific file. - parameters: - - in: path - name: file_id - required: true - schema: - type: string - description: The ID of the file to use for this request. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/OpenAIFile" - x-oaiMeta: - name: Retrieve file - group: files - returns: The [File](/docs/api-reference/files/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/files/file-abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.files.retrieve("file-abc123") - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const file = await openai.files.retrieve("file-abc123"); - - console.log(file); - } - - main(); - response: | - { - "id": "file-abc123", - "object": "file", - "bytes": 120000, - "created_at": 1677610602, - "filename": "mydata.jsonl", - "purpose": "fine-tune", + ] + }, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 9, + "completion_tokens": 9, + "total_tokens": 18, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + }, + "system_fingerprint": null + } + /completions: + post: + operationId: createCompletion + tags: + - Completions + summary: Creates a completion for the provided prompt and parameters. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateCompletionRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateCompletionResponse" + x-oaiMeta: + name: Create completion + group: completions + returns: > + Returns a [completion](/docs/api-reference/completions/object) object, + or a sequence of completion objects if the request is streamed. + legacy: true + examples: + - title: No streaming + request: + curl: | + curl https://api.openai.com/v1/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_completion_model_id", + "prompt": "Say this is a test", + "max_tokens": 7, + "temperature": 0 + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.completions.create( + model="VAR_completion_model_id", + prompt="Say this is a test", + max_tokens=7, + temperature=0 + ) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const completion = await openai.completions.create({ + model: "VAR_completion_model_id", + prompt: "Say this is a test.", + max_tokens: 7, + temperature: 0, + }); + + console.log(completion); + } + main(); + response: | + { + "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", + "object": "text_completion", + "created": 1589478378, + "model": "VAR_completion_model_id", + "system_fingerprint": "fp_44709d6fcb", + "choices": [ + { + "text": "\n\nThis is indeed a test", + "index": 0, + "logprobs": null, + "finish_reason": "length" + } + ], + "usage": { + "prompt_tokens": 5, + "completion_tokens": 7, + "total_tokens": 12 + } + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_completion_model_id", + "prompt": "Say this is a test", + "max_tokens": 7, + "temperature": 0, + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + for chunk in client.completions.create( + model="VAR_completion_model_id", + prompt="Say this is a test", + max_tokens=7, + temperature=0, + stream=True + ): + print(chunk.choices[0].text) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const stream = await openai.completions.create({ + model: "VAR_completion_model_id", + prompt: "Say this is a test.", + stream: true, + }); + + for await (const chunk of stream) { + console.log(chunk.choices[0].text) + } + } + main(); + response: | + { + "id": "cmpl-7iA7iJjj8V2zOkCGvWF2hAkDWBQZe", + "object": "text_completion", + "created": 1690759702, + "choices": [ + { + "text": "This", + "index": 0, + "logprobs": null, + "finish_reason": null + } + ], + "model": "gpt-3.5-turbo-instruct" + "system_fingerprint": "fp_44709d6fcb", + } + /embeddings: + post: + operationId: createEmbedding + tags: + - Embeddings + summary: Creates an embedding vector representing the input text. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateEmbeddingRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateEmbeddingResponse" + x-oaiMeta: + name: Create embeddings + group: embeddings + returns: A list of [embedding](/docs/api-reference/embeddings/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/embeddings \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "input": "The food was delicious and the waiter...", + "model": "text-embedding-ada-002", + "encoding_format": "float" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.embeddings.create( + model="text-embedding-ada-002", + input="The food was delicious and the waiter...", + encoding_format="float" + ) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const embedding = await openai.embeddings.create({ + model: "text-embedding-ada-002", + input: "The quick brown fox jumped over the lazy dog", + encoding_format: "float", + }); + + console.log(embedding); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "object": "embedding", + "embedding": [ + 0.0023064255, + -0.009327292, + .... (1536 floats total for ada-002) + -0.0028842222, + ], + "index": 0 + } + ], + "model": "text-embedding-ada-002", + "usage": { + "prompt_tokens": 8, + "total_tokens": 8 + } + } + /files: + get: + operationId: listFiles + tags: + - Files + summary: Returns a list of files. + parameters: + - in: query + name: purpose + required: false + schema: + type: string + description: Only return files with the given purpose. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 10,000, and the default is 10,000. + required: false + schema: + type: integer + default: 10000 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFilesResponse" + x-oaiMeta: + name: List files + group: files + returns: A list of [File](/docs/api-reference/files/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.list() + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.files.list(); + + for await (const file of list) { + console.log(file); + } + } + + main(); + response: | + { + "data": [ + { + "id": "file-abc123", + "object": "file", + "bytes": 175, + "created_at": 1613677385, + "filename": "salesOverview.pdf", + "purpose": "assistants", + }, + { + "id": "file-abc123", + "object": "file", + "bytes": 140, + "created_at": 1613779121, + "filename": "puppy.jsonl", + "purpose": "fine-tune", + } + ], + "object": "list" + } + post: + operationId: createFile + tags: + - Files + summary: > + Upload a file that can be used across various endpoints. Individual + files can be up to 512 MB, and the size of all files uploaded by one + organization can be up to 100 GB. + + + The Assistants API supports files up to 2 million tokens and of specific + file types. See the [Assistants Tools guide](/docs/assistants/tools) for + details. + + + The Fine-tuning API only supports `.jsonl` files. The input also has + certain required formats for fine-tuning + [chat](/docs/api-reference/fine-tuning/chat-input) or + [completions](/docs/api-reference/fine-tuning/completions-input) models. + + + The Batch API only supports `.jsonl` files up to 200 MB in size. The + input also has a specific required + [format](/docs/api-reference/batch/request-input). + + + Please [contact us](https://help.openai.com/) if you need to increase + these storage limits. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateFileRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/OpenAIFile" + x-oaiMeta: + name: Upload file + group: files + returns: The uploaded [File](/docs/api-reference/files/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -F purpose="fine-tune" \ + -F file="@mydata.jsonl" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.create( + file=open("mydata.jsonl", "rb"), + purpose="fine-tune" + ) + node.js: |- + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.create({ + file: fs.createReadStream("mydata.jsonl"), + purpose: "fine-tune", + }); + + console.log(file); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "file", + "bytes": 120000, + "created_at": 1677610602, + "filename": "mydata.jsonl", + "purpose": "fine-tune", + } + /files/{file_id}: + delete: + operationId: deleteFile + tags: + - Files + summary: Delete a file. + parameters: + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to use for this request. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteFileResponse" + x-oaiMeta: + name: Delete file + group: files + returns: Deletion status. + examples: + request: + curl: | + curl https://api.openai.com/v1/files/file-abc123 \ + -X DELETE \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.delete("file-abc123") + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.del("file-abc123"); + + console.log(file); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "file", + "deleted": true + } + get: + operationId: retrieveFile + tags: + - Files + summary: Returns information about a specific file. + parameters: + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to use for this request. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/OpenAIFile" + x-oaiMeta: + name: Retrieve file + group: files + returns: The [File](/docs/api-reference/files/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/files/file-abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.retrieve("file-abc123") + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.retrieve("file-abc123"); + + console.log(file); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "file", + "bytes": 120000, + "created_at": 1677610602, + "filename": "mydata.jsonl", + "purpose": "fine-tune", + } + /files/{file_id}/content: + get: + operationId: downloadFile + tags: + - Files + summary: Returns the contents of the specified file. + parameters: + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to use for this request. + responses: + "200": + description: OK + content: + application/json: + schema: + type: string + x-oaiMeta: + name: Retrieve file content + group: files + returns: The file content. + examples: + request: + curl: | + curl https://api.openai.com/v1/files/file-abc123/content \ + -H "Authorization: Bearer $OPENAI_API_KEY" > file.jsonl + python: | + from openai import OpenAI + client = OpenAI() + + content = client.files.content("file-abc123") + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.content("file-abc123"); + + console.log(file); + } + + main(); + /fine_tuning/jobs: + post: + operationId: createFineTuningJob + tags: + - Fine-tuning + summary: > + Creates a fine-tuning job which begins the process of creating a new + model from a given dataset. + + + Response includes details of the enqueued job including job status and + the name of the fine-tuned models once complete. + + + [Learn more about fine-tuning](/docs/guides/fine-tuning) + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateFineTuningJobRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Create fine-tuning job + group: fine-tuning + returns: A [fine-tuning.job](/docs/api-reference/fine-tuning/object) object. + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-BK7bzQj3FfZFXr7DbL6xJwfo", + "model": "gpt-4o-mini" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.create( + training_file="file-abc123", + model="gpt-4o-mini" + ) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const fineTune = await openai.fineTuning.jobs.create({ + training_file: "file-abc123" + }); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": null, + "training_file": "file-abc123", + } + - title: Epochs + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "model": "gpt-4o-mini", + "hyperparameters": { + "n_epochs": 2 + } + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.create( + training_file="file-abc123", + model="gpt-4o-mini", + hyperparameters={ + "n_epochs":2 + } + ) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const fineTune = await openai.fineTuning.jobs.create({ + training_file: "file-abc123", + model: "gpt-4o-mini", + hyperparameters: { n_epochs: 2 } + }); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": null, + "training_file": "file-abc123", + "hyperparameters": {"n_epochs": 2}, + } + - title: Validation file + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "validation_file": "file-abc123", + "model": "gpt-4o-mini" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.create( + training_file="file-abc123", + validation_file="file-def456", + model="gpt-4o-mini" + ) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const fineTune = await openai.fineTuning.jobs.create({ + training_file: "file-abc123", + validation_file: "file-abc123" + }); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": "file-abc123", + "training_file": "file-abc123", + } + - title: W&B Integration + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "validation_file": "file-abc123", + "model": "gpt-4o-mini", + "integrations": [ + { + "type": "wandb", + "wandb": { + "project": "my-wandb-project", + "name": "ft-run-display-name" + "tags": [ + "first-experiment", "v2" + ] } - /files/{file_id}/content: - get: - operationId: downloadFile - tags: - - Files - summary: Returns the contents of the specified file. - parameters: - - in: path - name: file_id - required: true - schema: - type: string - description: The ID of the file to use for this request. - responses: - "200": - description: OK - content: - application/json: - schema: - type: string - x-oaiMeta: - name: Retrieve file content - group: files - returns: The file content. - examples: - request: - curl: | - curl https://api.openai.com/v1/files/file-abc123/content \ - -H "Authorization: Bearer $OPENAI_API_KEY" > file.jsonl - python: | - from openai import OpenAI - client = OpenAI() - - content = client.files.content("file-abc123") - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const file = await openai.files.content("file-abc123"); - - console.log(file); - } - - main(); - /uploads: - post: - operationId: createUpload - tags: - - Uploads - summary: | - Creates an intermediate [Upload](/docs/api-reference/uploads/object) object that you can add [Parts](/docs/api-reference/uploads/part-object) to. Currently, an Upload can accept at most 8 GB in total and expires after an hour after you create it. - - Once you complete the Upload, we will create a [File](/docs/api-reference/files/object) object that contains all the parts you uploaded. This File is usable in the rest of our platform as a regular File object. - - For certain `purpose`s, the correct `mime_type` must be specified. Please refer to documentation for the supported MIME types for your use case: - - [Assistants](/docs/assistants/tools/file-search/supported-files) - - For guidance on the proper filename extensions for each purpose, please follow the documentation on [creating a File](/docs/api-reference/files/create). - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateUploadRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/Upload" - x-oaiMeta: - name: Create upload - group: uploads - returns: The [Upload](/docs/api-reference/uploads/object) object with status `pending`. - examples: - request: - curl: | - curl https://api.openai.com/v1/uploads \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "purpose": "fine-tune", - "filename": "training_examples.jsonl", - "bytes": 2147483648, - "mime_type": "text/jsonl" - }' - response: | - { - "id": "upload_abc123", - "object": "upload", - "bytes": 2147483648, - "created_at": 1719184911, - "filename": "training_examples.jsonl", - "purpose": "fine-tune", - "status": "pending", - "expires_at": 1719127296 + } + ] + }' + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": "file-abc123", + "training_file": "file-abc123", + "integrations": [ + { + "type": "wandb", + "wandb": { + "project": "my-wandb-project", + "entity": None, + "run_id": "ftjob-abc123" + } + } + ] + } + get: + operationId: listPaginatedFineTuningJobs + tags: + - Fine-tuning + summary: | + List your organization's fine-tuning jobs + parameters: + - name: after + in: query + description: Identifier for the last job from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of fine-tuning jobs to retrieve. + required: false + schema: + type: integer + default: 20 + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListPaginatedFineTuningJobsResponse" + x-oaiMeta: + name: List fine-tuning jobs + group: fine-tuning + returns: A list of paginated [fine-tuning + job](/docs/api-reference/fine-tuning/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs?limit=2 \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.list() + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.fineTuning.jobs.list(); + + for await (const fineTune of list) { + console.log(fineTune); + } + } + + main(); + response: > + { + "object": "list", + "data": [ + { + "object": "fine_tuning.job.event", + "id": "ft-event-TjX0lMfOniCZX64t9PUQT5hn", + "created_at": 1689813489, + "level": "warn", + "message": "Fine tuning process stopping due to job cancellation", + "data": null, + "type": "message" + }, + { ... }, + { ... } + ], "has_more": true + } + /fine_tuning/jobs/{fine_tuning_job_id}: + get: + operationId: retrieveFineTuningJob + tags: + - Fine-tuning + summary: | + Get info about a fine-tuning job. + + [Learn more about fine-tuning](/docs/guides/fine-tuning) + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Retrieve fine-tuning job + group: fine-tuning + returns: The [fine-tuning](/docs/api-reference/fine-tuning/object) object with + the given ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/fine_tuning/jobs/ft-AF1WoRqd3aJAHsqc9NY7iL8F + \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.retrieve("ftjob-abc123") + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const fineTune = await openai.fineTuning.jobs.retrieve("ftjob-abc123"); + + console.log(fineTune); + } + + + main(); + response: > + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "davinci-002", + "created_at": 1692661014, + "finished_at": 1692661190, + "fine_tuned_model": "ft:davinci-002:my-org:custom_suffix:7q8mpxmy", + "organization_id": "org-123", + "result_files": [ + "file-abc123" + ], + "status": "succeeded", + "validation_file": null, + "training_file": "file-abc123", + "hyperparameters": { + "n_epochs": 4, + "batch_size": 1, + "learning_rate_multiplier": 1.0 + }, + "trained_tokens": 5768, + "integrations": [], + "seed": 0, + "estimated_finish": 0 + } + /fine_tuning/jobs/{fine_tuning_job_id}/cancel: + post: + operationId: cancelFineTuningJob + tags: + - Fine-tuning + summary: | + Immediately cancel a fine-tune job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Cancel fine-tuning + group: fine-tuning + returns: The cancelled [fine-tuning](/docs/api-reference/fine-tuning/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.cancel("ftjob-abc123") + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const fineTune = await openai.fineTuning.jobs.cancel("ftjob-abc123"); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "hyperparameters": { + "n_epochs": "auto" + }, + "status": "cancelled", + "validation_file": "file-abc123", + "training_file": "file-abc123" + } + /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints: + get: + operationId: listFineTuningJobCheckpoints + tags: + - Fine-tuning + summary: | + List checkpoints for a fine-tuning job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to get checkpoints for. + - name: after + in: query + description: Identifier for the last checkpoint ID from the previous pagination + request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of checkpoints to retrieve. + required: false + schema: + type: integer + default: 10 + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFineTuningJobCheckpointsResponse" + x-oaiMeta: + name: List fine-tuning checkpoints + group: fine-tuning + returns: A list of fine-tuning [checkpoint + objects](/docs/api-reference/fine-tuning/checkpoint-object) for a + fine-tuning job. + examples: + request: + curl: > + curl + https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/checkpoints + \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: > + { + "object": "list" + "data": [ + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", + "created_at": 1721764867, + "fine_tuned_model_checkpoint": "ft:gpt-4o-mini-2024-07-18:my-org:custom-suffix:96olL566:ckpt-step-2000", + "metrics": { + "full_valid_loss": 0.134, + "full_valid_mean_token_accuracy": 0.874 + }, + "fine_tuning_job_id": "ftjob-abc123", + "step_number": 2000, + }, + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", + "created_at": 1721764800, + "fine_tuned_model_checkpoint": "ft:gpt-4o-mini-2024-07-18:my-org:custom-suffix:7q8mpxmy:ckpt-step-1000", + "metrics": { + "full_valid_loss": 0.167, + "full_valid_mean_token_accuracy": 0.781 + }, + "fine_tuning_job_id": "ftjob-abc123", + "step_number": 1000, + }, + ], + "first_id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", + "last_id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", + "has_more": true + } + /fine_tuning/jobs/{fine_tuning_job_id}/events: + get: + operationId: listFineTuningEvents + tags: + - Fine-tuning + summary: | + Get status updates for a fine-tuning job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to get events for. + - name: after + in: query + description: Identifier for the last event from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of events to retrieve. + required: false + schema: + type: integer + default: 20 + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFineTuningJobEventsResponse" + x-oaiMeta: + name: List fine-tuning events + group: fine-tuning + returns: A list of fine-tuning event objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/events \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.list_events( + fine_tuning_job_id="ftjob-abc123", + limit=2 + ) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const list = await openai.fineTuning.list_events(id="ftjob-abc123", limit=2); + + for await (const fineTune of list) { + console.log(fineTune); + } + } + + + main(); + response: > + { + "object": "list", + "data": [ + { + "object": "fine_tuning.job.event", + "id": "ft-event-ddTJfwuMVpfLXseO0Am0Gqjm", + "created_at": 1721764800, + "level": "info", + "message": "Fine tuning job successfully completed", + "data": null, + "type": "message" + }, + { + "object": "fine_tuning.job.event", + "id": "ft-event-tyiGuB72evQncpH87xe505Sv", + "created_at": 1721764800, + "level": "info", + "message": "New fine-tuned model created: ft:gpt-4o-mini:openai::7p4lURel", + "data": null, + "type": "message" + } + ], + "has_more": true + } + /images/edits: + post: + operationId: createImageEdit + tags: + - Images + summary: Creates an edited or extended image given an original image and a prompt. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateImageEditRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ImagesResponse" + x-oaiMeta: + name: Create image edit + group: images + returns: Returns a list of [image](/docs/api-reference/images/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/images/edits \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -F image="@otter.png" \ + -F mask="@mask.png" \ + -F prompt="A cute baby sea otter wearing a beret" \ + -F n=2 \ + -F size="1024x1024" + python: | + from openai import OpenAI + client = OpenAI() + + client.images.edit( + image=open("otter.png", "rb"), + mask=open("mask.png", "rb"), + prompt="A cute baby sea otter wearing a beret", + n=2, + size="1024x1024" + ) + node.js: |- + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const image = await openai.images.edit({ + image: fs.createReadStream("otter.png"), + mask: fs.createReadStream("mask.png"), + prompt: "A cute baby sea otter wearing a beret", + }); + + console.log(image.data); + } + main(); + response: | + { + "created": 1589478378, + "data": [ + { + "url": "https://..." + }, + { + "url": "https://..." + } + ] + } + /images/generations: + post: + operationId: createImage + tags: + - Images + summary: Creates an image given a prompt. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateImageRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ImagesResponse" + x-oaiMeta: + name: Create image + group: images + returns: Returns a list of [image](/docs/api-reference/images/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/images/generations \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "dall-e-3", + "prompt": "A cute baby sea otter", + "n": 1, + "size": "1024x1024" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.images.generate( + model="dall-e-3", + prompt="A cute baby sea otter", + n=1, + size="1024x1024" + ) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const image = await openai.images.generate({ model: "dall-e-3", prompt: "A cute baby sea otter" }); + + console.log(image.data); + } + + main(); + response: | + { + "created": 1589478378, + "data": [ + { + "url": "https://..." + }, + { + "url": "https://..." + } + ] + } + /images/variations: + post: + operationId: createImageVariation + tags: + - Images + summary: Creates a variation of a given image. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateImageVariationRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ImagesResponse" + x-oaiMeta: + name: Create image variation + group: images + returns: Returns a list of [image](/docs/api-reference/images/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/images/variations \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -F image="@otter.png" \ + -F n=2 \ + -F size="1024x1024" + python: | + from openai import OpenAI + client = OpenAI() + + response = client.images.create_variation( + image=open("image_edit_original.png", "rb"), + n=2, + size="1024x1024" + ) + node.js: |- + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const image = await openai.images.createVariation({ + image: fs.createReadStream("otter.png"), + }); + + console.log(image.data); + } + main(); + response: | + { + "created": 1589478378, + "data": [ + { + "url": "https://..." + }, + { + "url": "https://..." + } + ] + } + /models: + get: + operationId: listModels + tags: + - Models + summary: Lists the currently available models, and provides basic information + about each one such as the owner and availability. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListModelsResponse" + x-oaiMeta: + name: List models + group: models + returns: A list of [model](/docs/api-reference/models/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/models \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.models.list() + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.models.list(); + + for await (const model of list) { + console.log(model); + } + } + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "model-id-0", + "object": "model", + "created": 1686935002, + "owned_by": "organization-owner" + }, + { + "id": "model-id-1", + "object": "model", + "created": 1686935002, + "owned_by": "organization-owner", + }, + { + "id": "model-id-2", + "object": "model", + "created": 1686935002, + "owned_by": "openai" + }, + ], + "object": "list" + } + /models/{model}: + get: + operationId: retrieveModel + tags: + - Models + summary: Retrieves a model instance, providing basic information about the model + such as the owner and permissioning. + parameters: + - in: path + name: model + required: true + schema: + type: string + example: gpt-4o-mini + description: The ID of the model to use for this request + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Model" + x-oaiMeta: + name: Retrieve model + group: models + returns: The [model](/docs/api-reference/models/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/models/VAR_chat_model_id \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.models.retrieve("VAR_chat_model_id") + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const model = await openai.models.retrieve("VAR_chat_model_id"); + + console.log(model); + } + + main(); + response: | + { + "id": "VAR_chat_model_id", + "object": "model", + "created": 1686935002, + "owned_by": "openai" + } + delete: + operationId: deleteModel + tags: + - Models + summary: Delete a fine-tuned model. You must have the Owner role in your + organization to delete a model. + parameters: + - in: path + name: model + required: true + schema: + type: string + example: ft:gpt-4o-mini:acemeco:suffix:abc123 + description: The model to delete + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteModelResponse" + x-oaiMeta: + name: Delete a fine-tuned model + group: models + returns: Deletion status. + examples: + request: + curl: > + curl + https://api.openai.com/v1/models/ft:gpt-4o-mini:acemeco:suffix:abc123 + \ + -X DELETE \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.models.delete("ft:gpt-4o-mini:acemeco:suffix:abc123") + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const model = await openai.models.del("ft:gpt-4o-mini:acemeco:suffix:abc123"); + + console.log(model); + } + + main(); + response: | + { + "id": "ft:gpt-4o-mini:acemeco:suffix:abc123", + "object": "model", + "deleted": true + } + /moderations: + post: + operationId: createModeration + tags: + - Moderations + summary: | + Classifies if text and/or image inputs are potentially harmful. Learn + more in the [moderation guide](/docs/guides/moderation). + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateModerationRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateModerationResponse" + x-oaiMeta: + name: Create moderation + group: moderations + returns: A [moderation](/docs/api-reference/moderations/object) object. + examples: + - title: Single string + request: + curl: | + curl https://api.openai.com/v1/moderations \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "input": "I want to kill them." + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + moderation = client.moderations.create(input="I want to kill + them.") + + print(moderation) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const moderation = await openai.moderations.create({ input: "I want to kill them." }); + + console.log(moderation); + } + + main(); + response: | + { + "id": "modr-AB8CjOTu2jiq12hp1AQPfeqFWaORR", + "model": "text-moderation-007", + "results": [ + { + "flagged": true, + "categories": { + "sexual": false, + "hate": false, + "harassment": true, + "self-harm": false, + "sexual/minors": false, + "hate/threatening": false, + "violence/graphic": false, + "self-harm/intent": false, + "self-harm/instructions": false, + "harassment/threatening": true, + "violence": true + }, + "category_scores": { + "sexual": 0.000011726012417057063, + "hate": 0.22706663608551025, + "harassment": 0.5215635299682617, + "self-harm": 2.227119921371923e-6, + "sexual/minors": 7.107352217872176e-8, + "hate/threatening": 0.023547329008579254, + "violence/graphic": 0.00003391829886822961, + "self-harm/intent": 1.646940972932498e-6, + "self-harm/instructions": 1.1198755256458526e-9, + "harassment/threatening": 0.5694745779037476, + "violence": 0.9971134662628174 + } + } + ] + } + - title: Image and text + request: + curl: > + curl https://api.openai.com/v1/moderations \ + -X POST \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "omni-moderation-latest", + "input": [ + { "type": "text", "text": "...text to classify goes here..." }, + { + "type": "image_url", + "image_url": { + "url": "https://example.com/image.png" } + } + ] + }' + python: > + from openai import OpenAI - /uploads/{upload_id}/parts: - post: - operationId: addUploadPart - tags: - - Uploads - summary: | - Adds a [Part](/docs/api-reference/uploads/part-object) to an [Upload](/docs/api-reference/uploads/object) object. A Part represents a chunk of bytes from the file you are trying to upload. - - Each Part can be at most 64 MB, and you can add Parts until you hit the Upload maximum of 8 GB. - - It is possible to add multiple Parts in parallel. You can decide the intended order of the Parts when you [complete the Upload](/docs/api-reference/uploads/complete). - parameters: - - in: path - name: upload_id - required: true - schema: - type: string - example: upload_abc123 - description: | - The ID of the Upload. - requestBody: - required: true - content: - multipart/form-data: - schema: - $ref: "#/components/schemas/AddUploadPartRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/UploadPart" - x-oaiMeta: - name: Add upload part - group: uploads - returns: The upload [Part](/docs/api-reference/uploads/part-object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/uploads/upload_abc123/parts - -F data="aHR0cHM6Ly9hcGkub3BlbmFpLmNvbS92MS91cGxvYWRz..." - response: | - { - "id": "part_def456", - "object": "upload.part", - "created_at": 1719185911, - "upload_id": "upload_abc123" - } + client = OpenAI() - /uploads/{upload_id}/complete: - post: - operationId: completeUpload - tags: - - Uploads - summary: | - Completes the [Upload](/docs/api-reference/uploads/object). - - Within the returned Upload object, there is a nested [File](/docs/api-reference/files/object) object that is ready to use in the rest of the platform. - - You can specify the order of the Parts by passing in an ordered list of the Part IDs. - - The number of bytes uploaded upon completion must match the number of bytes initially specified when creating the Upload object. No Parts may be added after an Upload is completed. - parameters: - - in: path - name: upload_id - required: true - schema: - type: string - example: upload_abc123 - description: | - The ID of the Upload. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CompleteUploadRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/Upload" - x-oaiMeta: - name: Complete upload - group: uploads - returns: The [Upload](/docs/api-reference/uploads/object) object with status `completed` with an additional `file` property containing the created usable File object. - examples: - request: - curl: | - curl https://api.openai.com/v1/uploads/upload_abc123/complete - -d '{ - "part_ids": ["part_def456", "part_ghi789"] - }' - response: | - { - "id": "upload_abc123", - "object": "upload", - "bytes": 2147483648, - "created_at": 1719184911, - "filename": "training_examples.jsonl", - "purpose": "fine-tune", - "status": "completed", - "expires_at": 1719127296, - "file": { - "id": "file-xyz321", - "object": "file", - "bytes": 2147483648, - "created_at": 1719186911, - "filename": "training_examples.jsonl", - "purpose": "fine-tune", - } - } - /uploads/{upload_id}/cancel: - post: - operationId: cancelUpload - tags: - - Uploads - summary: | - Cancels the Upload. No Parts may be added after an Upload is cancelled. - parameters: - - in: path - name: upload_id - required: true - schema: - type: string - example: upload_abc123 - description: | - The ID of the Upload. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/Upload" - x-oaiMeta: - name: Cancel upload - group: uploads - returns: The [Upload](/docs/api-reference/uploads/object) object with status `cancelled`. - examples: - request: - curl: | - curl https://api.openai.com/v1/uploads/upload_abc123/cancel - response: | + response = client.moderations.create( + model="omni-moderation-latest", + input=[ + {"type": "text", "text": "...text to classify goes here..."}, { - "id": "upload_abc123", - "object": "upload", - "bytes": 2147483648, - "created_at": 1719184911, - "filename": "training_examples.jsonl", - "purpose": "fine-tune", - "status": "cancelled", - "expires_at": 1719127296 - } - - /fine_tuning/jobs: - post: - operationId: createFineTuningJob - tags: - - Fine-tuning - summary: | - Creates a fine-tuning job which begins the process of creating a new model from a given dataset. - - Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete. - - [Learn more about fine-tuning](/docs/guides/fine-tuning) - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateFineTuningJobRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/FineTuningJob" - x-oaiMeta: - name: Create fine-tuning job - group: fine-tuning - returns: A [fine-tuning.job](/docs/api-reference/fine-tuning/object) object. - examples: - - title: Default - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "training_file": "file-BK7bzQj3FfZFXr7DbL6xJwfo", - "model": "gpt-3.5-turbo" - }' - python: | - from openai import OpenAI - client = OpenAI() - - client.fine_tuning.jobs.create( - training_file="file-abc123", - model="gpt-3.5-turbo" - ) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const fineTune = await openai.fineTuning.jobs.create({ - training_file: "file-abc123" - }); - - console.log(fineTune); - } - - main(); - response: | - { - "object": "fine_tuning.job", - "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0125", - "created_at": 1614807352, - "fine_tuned_model": null, - "organization_id": "org-123", - "result_files": [], - "status": "queued", - "validation_file": null, - "training_file": "file-abc123", - } - - title: Epochs - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "training_file": "file-abc123", - "model": "gpt-3.5-turbo", - "hyperparameters": { - "n_epochs": 2 - } - }' - python: | - from openai import OpenAI - client = OpenAI() - - client.fine_tuning.jobs.create( - training_file="file-abc123", - model="gpt-3.5-turbo", - hyperparameters={ - "n_epochs":2 - } - ) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const fineTune = await openai.fineTuning.jobs.create({ - training_file: "file-abc123", - model: "gpt-3.5-turbo", - hyperparameters: { n_epochs: 2 } - }); - - console.log(fineTune); - } - - main(); - response: | - { - "object": "fine_tuning.job", - "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0125", - "created_at": 1614807352, - "fine_tuned_model": null, - "organization_id": "org-123", - "result_files": [], - "status": "queued", - "validation_file": null, - "training_file": "file-abc123", - "hyperparameters": {"n_epochs": 2}, - } - - title: Validation file - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "training_file": "file-abc123", - "validation_file": "file-abc123", - "model": "gpt-3.5-turbo" - }' - python: | - from openai import OpenAI - client = OpenAI() - - client.fine_tuning.jobs.create( - training_file="file-abc123", - validation_file="file-def456", - model="gpt-3.5-turbo" - ) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const fineTune = await openai.fineTuning.jobs.create({ - training_file: "file-abc123", - validation_file: "file-abc123" - }); - - console.log(fineTune); - } - - main(); - response: | - { - "object": "fine_tuning.job", - "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0125", - "created_at": 1614807352, - "fine_tuned_model": null, - "organization_id": "org-123", - "result_files": [], - "status": "queued", - "validation_file": "file-abc123", - "training_file": "file-abc123", - } - - title: W&B Integration - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "training_file": "file-abc123", - "validation_file": "file-abc123", - "model": "gpt-3.5-turbo", - "integrations": [ - { - "type": "wandb", - "wandb": { - "project": "my-wandb-project", - "name": "ft-run-display-name" - "tags": [ - "first-experiment", "v2" - ] - } - } - ] - }' - response: | - { - "object": "fine_tuning.job", - "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0125", - "created_at": 1614807352, - "fine_tuned_model": null, - "organization_id": "org-123", - "result_files": [], - "status": "queued", - "validation_file": "file-abc123", - "training_file": "file-abc123", - "integrations": [ - { - "type": "wandb", - "wandb": { - "project": "my-wandb-project", - "entity": None, - "run_id": "ftjob-abc123" - } - } - ] - } - get: - operationId: listPaginatedFineTuningJobs - tags: - - Fine-tuning - summary: | - List your organization's fine-tuning jobs - parameters: - - name: after - in: query - description: Identifier for the last job from the previous pagination request. - required: false - schema: - type: string - - name: limit - in: query - description: Number of fine-tuning jobs to retrieve. - required: false - schema: - type: integer - default: 20 - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListPaginatedFineTuningJobsResponse" - x-oaiMeta: - name: List fine-tuning jobs - group: fine-tuning - returns: A list of paginated [fine-tuning job](/docs/api-reference/fine-tuning/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs?limit=2 \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.fine_tuning.jobs.list() - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const list = await openai.fineTuning.jobs.list(); - - for await (const fineTune of list) { - console.log(fineTune); - } + "type": "image_url", + "image_url": { + "url": "https://example.com/image.png", + # can also use base64 encoded image URLs + # "url": "data:image/jpeg;base64,abcdefg..." } + }, + ], + ) - main(); - response: | - { - "object": "list", - "data": [ - { - "object": "fine_tuning.job.event", - "id": "ft-event-TjX0lMfOniCZX64t9PUQT5hn", - "created_at": 1689813489, - "level": "warn", - "message": "Fine tuning process stopping due to job cancellation", - "data": null, - "type": "message" - }, - { ... }, - { ... } - ], "has_more": true - } - /fine_tuning/jobs/{fine_tuning_job_id}: - get: - operationId: retrieveFineTuningJob - tags: - - Fine-tuning - summary: | - Get info about a fine-tuning job. - - [Learn more about fine-tuning](/docs/guides/fine-tuning) - parameters: - - in: path - name: fine_tuning_job_id - required: true - schema: - type: string - example: ft-AF1WoRqd3aJAHsqc9NY7iL8F - description: | - The ID of the fine-tuning job. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/FineTuningJob" - x-oaiMeta: - name: Retrieve fine-tuning job - group: fine-tuning - returns: The [fine-tuning](/docs/api-reference/fine-tuning/object) object with the given ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs/ft-AF1WoRqd3aJAHsqc9NY7iL8F \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.fine_tuning.jobs.retrieve("ftjob-abc123") - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const fineTune = await openai.fineTuning.jobs.retrieve("ftjob-abc123"); - - console.log(fineTune); - } - main(); - response: &fine_tuning_example | - { - "object": "fine_tuning.job", - "id": "ftjob-abc123", - "model": "davinci-002", - "created_at": 1692661014, - "finished_at": 1692661190, - "fine_tuned_model": "ft:davinci-002:my-org:custom_suffix:7q8mpxmy", - "organization_id": "org-123", - "result_files": [ - "file-abc123" - ], - "status": "succeeded", - "validation_file": null, - "training_file": "file-abc123", - "hyperparameters": { - "n_epochs": 4, - "batch_size": 1, - "learning_rate_multiplier": 1.0 - }, - "trained_tokens": 5768, - "integrations": [], - "seed": 0, - "estimated_finish": 0 - } - /fine_tuning/jobs/{fine_tuning_job_id}/events: - get: - operationId: listFineTuningEvents - tags: - - Fine-tuning - summary: | - Get status updates for a fine-tuning job. - parameters: - - in: path - name: fine_tuning_job_id - required: true - schema: - type: string - example: ft-AF1WoRqd3aJAHsqc9NY7iL8F - description: | - The ID of the fine-tuning job to get events for. - - name: after - in: query - description: Identifier for the last event from the previous pagination request. - required: false - schema: - type: string - - name: limit - in: query - description: Number of events to retrieve. - required: false - schema: - type: integer - default: 20 - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListFineTuningJobEventsResponse" - x-oaiMeta: - name: List fine-tuning events - group: fine-tuning - returns: A list of fine-tuning event objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/events \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.fine_tuning.jobs.list_events( - fine_tuning_job_id="ftjob-abc123", - limit=2 - ) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const list = await openai.fineTuning.list_events(id="ftjob-abc123", limit=2); - - for await (const fineTune of list) { - console.log(fineTune); - } - } + print(response) + node.js: > + import OpenAI from "openai"; - main(); - response: | - { - "object": "list", - "data": [ - { - "object": "fine_tuning.job.event", - "id": "ft-event-ddTJfwuMVpfLXseO0Am0Gqjm", - "created_at": 1692407401, - "level": "info", - "message": "Fine tuning job successfully completed", - "data": null, - "type": "message" - }, - { - "object": "fine_tuning.job.event", - "id": "ft-event-tyiGuB72evQncpH87xe505Sv", - "created_at": 1692407400, - "level": "info", - "message": "New fine-tuned model created: ft:gpt-3.5-turbo:openai::7p4lURel", - "data": null, - "type": "message" - } - ], - "has_more": true - } - /fine_tuning/jobs/{fine_tuning_job_id}/cancel: - post: - operationId: cancelFineTuningJob - tags: - - Fine-tuning - summary: | - Immediately cancel a fine-tune job. - parameters: - - in: path - name: fine_tuning_job_id - required: true - schema: - type: string - example: ft-AF1WoRqd3aJAHsqc9NY7iL8F - description: | - The ID of the fine-tuning job to cancel. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/FineTuningJob" - x-oaiMeta: - name: Cancel fine-tuning - group: fine-tuning - returns: The cancelled [fine-tuning](/docs/api-reference/fine-tuning/object) object. - examples: - request: - curl: | - curl -X POST https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/cancel \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.fine_tuning.jobs.cancel("ftjob-abc123") - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const fineTune = await openai.fineTuning.jobs.cancel("ftjob-abc123"); - - console.log(fineTune); - } - main(); - response: | - { - "object": "fine_tuning.job", - "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0125", - "created_at": 1689376978, - "fine_tuned_model": null, - "organization_id": "org-123", - "result_files": [], - "hyperparameters": { - "n_epochs": "auto" - }, - "status": "cancelled", - "validation_file": "file-abc123", - "training_file": "file-abc123" - } - /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints: - get: - operationId: listFineTuningJobCheckpoints - tags: - - Fine-tuning - summary: | - List checkpoints for a fine-tuning job. - parameters: - - in: path - name: fine_tuning_job_id - required: true - schema: - type: string - example: ft-AF1WoRqd3aJAHsqc9NY7iL8F - description: | - The ID of the fine-tuning job to get checkpoints for. - - name: after - in: query - description: Identifier for the last checkpoint ID from the previous pagination request. - required: false - schema: - type: string - - name: limit - in: query - description: Number of checkpoints to retrieve. - required: false - schema: - type: integer - default: 10 - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListFineTuningJobCheckpointsResponse" - x-oaiMeta: - name: List fine-tuning checkpoints - group: fine-tuning - returns: A list of fine-tuning [checkpoint objects](/docs/api-reference/fine-tuning/checkpoint-object) for a fine-tuning job. - examples: - request: - curl: | - curl https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/checkpoints \ - -H "Authorization: Bearer $OPENAI_API_KEY" - response: | - { - "object": "list" - "data": [ - { - "object": "fine_tuning.job.checkpoint", - "id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", - "created_at": 1519129973, - "fine_tuned_model_checkpoint": "ft:gpt-3.5-turbo-0125:my-org:custom-suffix:96olL566:ckpt-step-2000", - "metrics": { - "full_valid_loss": 0.134, - "full_valid_mean_token_accuracy": 0.874 - }, - "fine_tuning_job_id": "ftjob-abc123", - "step_number": 2000, - }, - { - "object": "fine_tuning.job.checkpoint", - "id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", - "created_at": 1519129833, - "fine_tuned_model_checkpoint": "ft:gpt-3.5-turbo-0125:my-org:custom-suffix:7q8mpxmy:ckpt-step-1000", - "metrics": { - "full_valid_loss": 0.167, - "full_valid_mean_token_accuracy": 0.781 - }, - "fine_tuning_job_id": "ftjob-abc123", - "step_number": 1000, - }, - ], - "first_id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", - "last_id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", - "has_more": true - } + const openai = new OpenAI(); - /models: - get: - operationId: listModels - tags: - - Models - summary: Lists the currently available models, and provides basic information about each one such as the owner and availability. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListModelsResponse" - x-oaiMeta: - name: List models - group: models - returns: A list of [model](/docs/api-reference/models/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/models \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.models.list() - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const list = await openai.models.list(); - - for await (const model of list) { - console.log(model); - } - } - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "model-id-0", - "object": "model", - "created": 1686935002, - "owned_by": "organization-owner" - }, - { - "id": "model-id-1", - "object": "model", - "created": 1686935002, - "owned_by": "organization-owner", - }, - { - "id": "model-id-2", - "object": "model", - "created": 1686935002, - "owned_by": "openai" - }, - ], - "object": "list" - } - /models/{model}: - get: - operationId: retrieveModel - tags: - - Models - summary: Retrieves a model instance, providing basic information about the model such as the owner and permissioning. - parameters: - - in: path - name: model - required: true - schema: - type: string - # ideally this will be an actual ID, so this will always work from browser - example: gpt-3.5-turbo - description: The ID of the model to use for this request - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/Model" - x-oaiMeta: - name: Retrieve model - group: models - returns: The [model](/docs/api-reference/models/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/models/VAR_model_id \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.models.retrieve("VAR_model_id") - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const model = await openai.models.retrieve("VAR_model_id"); - - console.log(model); - } - main(); - response: &retrieve_model_response | + const moderation = await openai.moderations.create({ + model: "omni-moderation-latest", + input: [ + { type: "text", text: "...text to classify goes here..." }, { - "id": "VAR_model_id", - "object": "model", - "created": 1686935002, - "owned_by": "openai" - } - delete: - operationId: deleteModel - tags: - - Models - summary: Delete a fine-tuned model. You must have the Owner role in your organization to delete a model. - parameters: - - in: path - name: model - required: true - schema: - type: string - example: ft:gpt-3.5-turbo:acemeco:suffix:abc123 - description: The model to delete - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/DeleteModelResponse" - x-oaiMeta: - name: Delete a fine-tuned model - group: models - returns: Deletion status. - examples: - request: - curl: | - curl https://api.openai.com/v1/models/ft:gpt-3.5-turbo:acemeco:suffix:abc123 \ - -X DELETE \ - -H "Authorization: Bearer $OPENAI_API_KEY" - python: | - from openai import OpenAI - client = OpenAI() - - client.models.delete("ft:gpt-3.5-turbo:acemeco:suffix:abc123") - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const model = await openai.models.del("ft:gpt-3.5-turbo:acemeco:suffix:abc123"); - - console.log(model); + type: "image_url", + image_url: { + url: "https://example.com/image.png" + // can also use base64 encoded image URLs + // url: "data:image/jpeg;base64,abcdefg..." } - main(); - response: | - { - "id": "ft:gpt-3.5-turbo:acemeco:suffix:abc123", - "object": "model", - "deleted": true } + ], + }); - /moderations: - post: - operationId: createModeration - tags: - - Moderations - summary: Classifies if text is potentially harmful. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateModerationRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/CreateModerationResponse" - x-oaiMeta: - name: Create moderation - group: moderations - returns: A [moderation](/docs/api-reference/moderations/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/moderations \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -d '{ - "input": "I want to kill them." - }' - python: | - from openai import OpenAI - client = OpenAI() - - moderation = client.moderations.create(input="I want to kill them.") - print(moderation) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const moderation = await openai.moderations.create({ input: "I want to kill them." }); - - console.log(moderation); + + console.log(moderation); + response: | + { + "id": "modr-0d9740456c391e43c445bf0f010940c7", + "model": "omni-moderation-latest", + "results": [ + { + "flagged": true, + "categories": { + "harassment": true, + "harassment/threatening": true, + "sexual": false, + "hate": false, + "hate/threatening": false, + "illicit": false, + "illicit/violent": false, + "self-harm/intent": false, + "self-harm/instructions": false, + "self-harm": false, + "sexual/minors": false, + "violence": true, + "violence/graphic": true + }, + "category_scores": { + "harassment": 0.8189693396524255, + "harassment/threatening": 0.804985420696006, + "sexual": 1.573112165348997e-6, + "hate": 0.007562942636942845, + "hate/threatening": 0.004208854591835476, + "illicit": 0.030535955153511665, + "illicit/violent": 0.008925306722380033, + "self-harm/intent": 0.00023023930975076432, + "self-harm/instructions": 0.0002293869201073356, + "self-harm": 0.012598046106750154, + "sexual/minors": 2.212566909570261e-8, + "violence": 0.9999992735124786, + "violence/graphic": 0.843064871157054 + }, + "category_applied_input_types": { + "harassment": [ + "text" + ], + "harassment/threatening": [ + "text" + ], + "sexual": [ + "text", + "image" + ], + "hate": [ + "text" + ], + "hate/threatening": [ + "text" + ], + "illicit": [ + "text" + ], + "illicit/violent": [ + "text" + ], + "self-harm/intent": [ + "text", + "image" + ], + "self-harm/instructions": [ + "text", + "image" + ], + "self-harm": [ + "text", + "image" + ], + "sexual/minors": [ + "text" + ], + "violence": [ + "text", + "image" + ], + "violence/graphic": [ + "text", + "image" + ] + } + } + ] + } + /organization/audit_logs: + get: + summary: List user actions and configuration changes within this organization. + operationId: list-audit-logs + tags: + - Audit Logs + parameters: + - name: effective_at + in: query + description: Return only events whose `effective_at` (Unix seconds) is in this + range. + required: false + schema: + type: object + properties: + gt: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is greater + than this value. + gte: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is greater + than or equal to this value. + lt: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is less than + this value. + lte: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is less than + or equal to this value. + - name: project_ids[] + in: query + description: Return only events for these projects. + required: false + schema: + type: array + items: + type: string + - name: event_types[] + in: query + description: Return only events with a `type` in one of these values. For + example, `project.created`. For all options, see the documentation + for the [audit log object](/docs/api-reference/audit-logs/object). + required: false + schema: + type: array + items: + $ref: "#/components/schemas/AuditLogEventType" + - name: actor_ids[] + in: query + description: Return only events performed by these actors. Can be a user ID, a + service account ID, or an api key tracking ID. + required: false + schema: + type: array + items: + type: string + - name: actor_emails[] + in: query + description: Return only events performed by users with these emails. + required: false + schema: + type: array + items: + type: string + - name: resource_ids[] + in: query + description: Return only events performed on these targets. For example, a + project ID updated. + required: false + schema: + type: array + items: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: Audit logs listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListAuditLogsResponse" + x-oaiMeta: + name: List audit logs + group: audit-logs + returns: A list of paginated [Audit Log](/docs/api-reference/audit-logs/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/audit_logs \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "list", + "data": [ + { + "id": "audit_log-xxx_yyyymmdd", + "type": "project.archived", + "effective_at": 1722461446, + "actor": { + "type": "api_key", + "api_key": { + "type": "user", + "user": { + "id": "user-xxx", + "email": "user@example.com" + } } - main(); - response: &moderation_example | - { - "id": "modr-XXXXX", - "model": "text-moderation-005", - "results": [ - { - "flagged": true, - "categories": { - "sexual": false, - "hate": false, - "harassment": false, - "self-harm": false, - "sexual/minors": false, - "hate/threatening": false, - "violence/graphic": false, - "self-harm/intent": false, - "self-harm/instructions": false, - "harassment/threatening": true, - "violence": true, - }, - "category_scores": { - "sexual": 1.2282071e-06, - "hate": 0.010696256, - "harassment": 0.29842457, - "self-harm": 1.5236925e-08, - "sexual/minors": 5.7246268e-08, - "hate/threatening": 0.0060676364, - "violence/graphic": 4.435014e-06, - "self-harm/intent": 8.098441e-10, - "self-harm/instructions": 2.8498655e-11, - "harassment/threatening": 0.63055265, - "violence": 0.99011886, - } + }, + "project.archived": { + "id": "proj_abc" + }, + }, + { + "id": "audit_log-yyy__20240101", + "type": "api_key.updated", + "effective_at": 1720804190, + "actor": { + "type": "session", + "session": { + "user": { + "id": "user-xxx", + "email": "user@example.com" + }, + "ip_address": "127.0.0.1", + "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36" } - ] - } - - /assistants: - get: - operationId: listAssistants - tags: - - Assistants - summary: Returns a list of assistants. - parameters: - - name: limit - in: query - description: &pagination_limit_param_description | - A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: &pagination_order_param_description | - Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order. - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: &pagination_after_param_description | - A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list. - schema: - type: string - - name: before - in: query - description: &pagination_before_param_description | - A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list. - schema: - type: string - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListAssistantsResponse" - x-oaiMeta: - name: List assistants - group: assistants - beta: true - returns: A list of [assistant](/docs/api-reference/assistants/object) objects. - examples: - request: - curl: | - curl "https://api.openai.com/v1/assistants?order=desc&limit=20" \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - my_assistants = client.beta.assistants.list( - order="desc", - limit="20", - ) - print(my_assistants.data) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const myAssistants = await openai.beta.assistants.list({ - order: "desc", - limit: "20", - }); - - console.log(myAssistants.data); + }, + "api_key.updated": { + "id": "key_xxxx", + "data": { + "scopes": ["resource_2.operation_2"] } - - main(); - response: &list_assistants_example | - { - "object": "list", - "data": [ - { - "id": "asst_abc123", - "object": "assistant", - "created_at": 1698982736, - "name": "Coding Tutor", - "description": null, - "model": "gpt-4-turbo", - "instructions": "You are a helpful assistant designed to make me better at coding!", - "tools": [], - "tool_resources": {}, - "metadata": {}, - "top_p": 1.0, - "temperature": 1.0, - "response_format": "auto" - }, - { - "id": "asst_abc456", - "object": "assistant", - "created_at": 1698982718, - "name": "My Assistant", - "description": null, - "model": "gpt-4-turbo", - "instructions": "You are a helpful assistant designed to make me better at coding!", - "tools": [], - "tool_resources": {}, - "metadata": {}, - "top_p": 1.0, - "temperature": 1.0, - "response_format": "auto" - }, + }, + } + ], + "first_id": "audit_log-xxx__20240101", + "last_id": "audit_log_yyy__20240101", + "has_more": true + } + /organization/costs: + get: + summary: Get costs details for the organization. + operationId: usage-costs + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently only `1d` is + supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1d + default: 1d + - name: project_ids + in: query + description: Return only costs for these projects. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the costs by the specified fields. Support fields include + `project_id`, `line_item` and any combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - line_item + - name: limit + in: query + description: > + A limit on the number of buckets to be returned. Limit can range + between 1 and 180, and the default is 7. + required: false + schema: + type: integer + default: 7 + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Costs data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Costs + group: usage-costs + returns: A list of paginated, time bucketed + [Costs](/docs/api-reference/usage/costs_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/costs?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: | + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ { - "id": "asst_abc789", - "object": "assistant", - "created_at": 1698982643, - "name": null, - "description": null, - "model": "gpt-4-turbo", - "instructions": null, - "tools": [], - "tool_resources": {}, - "metadata": {}, - "top_p": 1.0, - "temperature": 1.0, - "response_format": "auto" + "object": "organization.costs.result", + "amount": { + "value": 0.06, + "currency": "usd" + }, + "line_item": null, + "project_id": null } - ], - "first_id": "asst_abc123", - "last_id": "asst_abc789", - "has_more": false - } - post: - operationId: createAssistant - tags: - - Assistants - summary: Create an assistant with a model and instructions. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateAssistantRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/AssistantObject" - x-oaiMeta: - name: Create assistant - group: assistants - beta: true - returns: An [assistant](/docs/api-reference/assistants/object) object. - examples: - - title: Code Interpreter - request: - curl: | - curl "https://api.openai.com/v1/assistants" \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", - "name": "Math Tutor", - "tools": [{"type": "code_interpreter"}], - "model": "gpt-4-turbo" - }' - - python: | - from openai import OpenAI - client = OpenAI() - - my_assistant = client.beta.assistants.create( - instructions="You are a personal math tutor. When asked a question, write and run Python code to answer the question.", - name="Math Tutor", - tools=[{"type": "code_interpreter"}], - model="gpt-4-turbo", - ) - print(my_assistant) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const myAssistant = await openai.beta.assistants.create({ - instructions: - "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", - name: "Math Tutor", - tools: [{ type: "code_interpreter" }], - model: "gpt-4-turbo", - }); - - console.log(myAssistant); - } - - main(); - response: &create_assistants_example | - { - "id": "asst_abc123", - "object": "assistant", - "created_at": 1698984975, - "name": "Math Tutor", - "description": null, - "model": "gpt-4-turbo", - "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", - "tools": [ - { - "type": "code_interpreter" + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/invites: + get: + summary: Returns a list of invites in the organization. + operationId: list-invites + tags: + - Invites + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Invites listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/InviteListResponse" + x-oaiMeta: + name: List invites + group: administration + returns: A list of [Invite](/docs/api-reference/invite/object) objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/invites?after=invite-abc&limit=20 + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "list", + "data": [ + { + "object": "organization.invite", + "id": "invite-abc", + "email": "user@example.com", + "role": "owner", + "status": "accepted", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": 1711471533 + } + ], + "first_id": "invite-abc", + "last_id": "invite-abc", + "has_more": false + } + post: + summary: Create an invite for a user to the organization. The invite must be + accepted by the user before they have access to the organization. + operationId: inviteUser + tags: + - Invites + requestBody: + description: The invite request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/InviteRequest" + responses: + "200": + description: User invited successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Invite" + x-oaiMeta: + name: Create invite + group: administration + returns: The created [Invite](/docs/api-reference/invite/object) object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/organization/invites \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "email": "user@example.com", + "role": "owner" + }' + response: + content: | + { + "object": "organization.invite", + "id": "invite-abc", + "email": "user@example.com", + "role": "owner", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": null + } + /organization/invites/{invite_id}: + get: + summary: Retrieves an invite. + operationId: retrieve-invite + tags: + - Invites + parameters: + - in: path + name: invite_id + required: true + schema: + type: string + description: The ID of the invite to retrieve. + responses: + "200": + description: Invite retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Invite" + x-oaiMeta: + name: Retrieve invite + group: administration + returns: The [Invite](/docs/api-reference/invite/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/invites/invite-abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.invite", + "id": "invite-abc", + "email": "user@example.com", + "role": "owner", + "status": "accepted", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": 1711471533 + } + delete: + summary: Delete an invite. If the invite has already been accepted, it cannot be + deleted. + operationId: delete-invite + tags: + - Invites + parameters: + - in: path + name: invite_id + required: true + schema: + type: string + description: The ID of the invite to delete. + responses: + "200": + description: Invite deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/InviteDeleteResponse" + x-oaiMeta: + name: Delete invite + group: administration + returns: Confirmation that the invite has been deleted + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/invites/invite-abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.invite.deleted", + "id": "invite-abc", + "deleted": true + } + /organization/projects: + get: + summary: Returns a list of projects. + operationId: list-projects + tags: + - Projects + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + - name: include_archived + in: query + schema: + type: boolean + default: false + description: If `true` returns all projects including those that have been + `archived`. Archived projects are not included by default. + responses: + "200": + description: Projects listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectListResponse" + x-oaiMeta: + name: List projects + group: administration + returns: A list of [Project](/docs/api-reference/projects/object) objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects?after=proj_abc&limit=20&include_archived=false + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "list", + "data": [ + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project example", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + ], + "first_id": "proj-abc", + "last_id": "proj-xyz", + "has_more": false + } + post: + summary: Create a new project in the organization. Projects can be created and + archived, but cannot be deleted. + operationId: create-project + tags: + - Projects + requestBody: + description: The project create request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectCreateRequest" + responses: + "200": + description: Project created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + x-oaiMeta: + name: Create project + group: administration + returns: The created [Project](/docs/api-reference/projects/object) object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/organization/projects \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "Project ABC" + }' + response: + content: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project ABC", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + /organization/projects/{project_id}: + get: + summary: Retrieves a project. + operationId: retrieve-project + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + responses: + "200": + description: Project retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + x-oaiMeta: + name: Retrieve project + group: administration + description: Retrieve a project. + returns: The [Project](/docs/api-reference/projects/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project example", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + post: + summary: Modifies a project in the organization. + operationId: modify-project + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + requestBody: + description: The project update request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUpdateRequest" + responses: + "200": + description: Project updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + "400": + description: Error response when updating the default project. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Modify project + group: administration + returns: The updated [Project](/docs/api-reference/projects/object) object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "Project DEF" + }' + /organization/projects/{project_id}/api_keys: + get: + summary: Returns a list of API keys in the project. + operationId: list-project-api-keys + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project API keys listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectApiKeyListResponse" + x-oaiMeta: + name: List project API keys + group: administration + returns: A list of [ProjectApiKey](/docs/api-reference/project-api-keys/object) + objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects/proj_abc/api_keys?after=key_abc&limit=20 + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "list", + "data": [ + { + "object": "organization.project.api_key", + "redacted_value": "sk-abc...def", + "name": "My API Key", + "created_at": 1711471533, + "id": "key_abc", + "owner": { + "type": "user", + "user": { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 } - ], - "metadata": {}, - "top_p": 1.0, - "temperature": 1.0, - "response_format": "auto" } - - title: Files - request: - curl: | - curl https://api.openai.com/v1/assistants \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", - "tools": [{"type": "file_search"}], - "tool_resources": {"file_search": {"vector_store_ids": ["vs_123"]}}, - "model": "gpt-4-turbo" - }' - python: | - from openai import OpenAI - client = OpenAI() - - my_assistant = client.beta.assistants.create( - instructions="You are an HR bot, and you have access to files to answer employee questions about company policies.", - name="HR Helper", - tools=[{"type": "file_search"}], - tool_resources={"file_search": {"vector_store_ids": ["vs_123"]}}, - model="gpt-4-turbo" - ) - print(my_assistant) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const myAssistant = await openai.beta.assistants.create({ - instructions: - "You are an HR bot, and you have access to files to answer employee questions about company policies.", - name: "HR Helper", - tools: [{ type: "file_search" }], - tool_resources: { - file_search: { - vector_store_ids: ["vs_123"] - } - }, - model: "gpt-4-turbo" - }); - - console.log(myAssistant); - } - - main(); - response: | - { - "id": "asst_abc123", - "object": "assistant", - "created_at": 1699009403, - "name": "HR Helper", - "description": null, - "model": "gpt-4-turbo", - "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", - "tools": [ - { - "type": "file_search" - } - ], - "tool_resources": { - "file_search": { - "vector_store_ids": ["vs_123"] - } - }, - "metadata": {}, - "top_p": 1.0, - "temperature": 1.0, - "response_format": "auto" - } - - /assistants/{assistant_id}: - get: - operationId: getAssistant - tags: - - Assistants - summary: Retrieves an assistant. - parameters: - - in: path - name: assistant_id - required: true - schema: - type: string - description: The ID of the assistant to retrieve. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/AssistantObject" - x-oaiMeta: - name: Retrieve assistant - group: assistants - beta: true - returns: The [assistant](/docs/api-reference/assistants/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/assistants/asst_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - my_assistant = client.beta.assistants.retrieve("asst_abc123") - print(my_assistant) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const myAssistant = await openai.beta.assistants.retrieve( - "asst_abc123" - ); - - console.log(myAssistant); + } + ], + "first_id": "key_abc", + "last_id": "key_xyz", + "has_more": false + } + error_response: + content: | + { + "code": 400, + "message": "Project {name} is archived" + } + /organization/projects/{project_id}/api_keys/{key_id}: + get: + summary: Retrieves an API key in the project. + operationId: retrieve-project-api-key + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: key_id + in: path + description: The ID of the API key. + required: true + schema: + type: string + responses: + "200": + description: Project API key retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectApiKey" + x-oaiMeta: + name: Retrieve project API key + group: administration + returns: The [ProjectApiKey](/docs/api-reference/project-api-keys/object) object + matching the specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects/proj_abc/api_keys/key_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.project.api_key", + "redacted_value": "sk-abc...def", + "name": "My API Key", + "created_at": 1711471533, + "id": "key_abc", + "owner": { + "type": "user", + "user": { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + } + } + delete: + summary: Deletes an API key from the project. + operationId: delete-project-api-key + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: key_id + in: path + description: The ID of the API key. + required: true + schema: + type: string + responses: + "200": + description: Project API key deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectApiKeyDeleteResponse" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Delete project API key + group: administration + returns: Confirmation of the key's deletion or an error if the key belonged to a + service account + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/projects/proj_abc/api_keys/key_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.project.api_key.deleted", + "id": "key_abc", + "deleted": true + } + error_response: + content: > + { + "code": 400, + "message": "API keys cannot be deleted for service accounts, please delete the service account" + } + /organization/projects/{project_id}/archive: + post: + summary: Archives a project in the organization. Archived projects cannot be + used or updated. + operationId: archive-project + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + responses: + "200": + description: Project archived successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + x-oaiMeta: + name: Archive project + group: administration + returns: The archived [Project](/docs/api-reference/projects/object) object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc/archive \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project DEF", + "created_at": 1711471533, + "archived_at": 1711471533, + "status": "archived" + } + /organization/projects/{project_id}/rate_limits: + get: + summary: Returns the rate limits per model for a project. + operationId: list-project-rate-limits + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: | + A limit on the number of objects to be returned. The default is 100. + required: false + schema: + type: integer + default: 100 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, beginning with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project rate limits listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectRateLimitListResponse" + x-oaiMeta: + name: List project rate limits + group: administration + returns: A list of + [ProjectRateLimit](/docs/api-reference/project-rate-limits/object) + objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects/proj_abc/rate_limits?after=rl_xxx&limit=20 + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "project.rate_limit", + "id": "rl-ada", + "model": "ada", + "max_requests_per_1_minute": 600, + "max_tokens_per_1_minute": 150000, + "max_images_per_1_minute": 10 + } + ], + "first_id": "rl-ada", + "last_id": "rl-ada", + "has_more": false + } + error_response: | + { + "code": 404, + "message": "The project {project_id} was not found" + } + /organization/projects/{project_id}/rate_limits/{rate_limit_id}: + post: + summary: Updates a project rate limit. + operationId: update-project-rate-limits + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: rate_limit_id + in: path + description: The ID of the rate limit. + required: true + schema: + type: string + requestBody: + description: The project rate limit update request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectRateLimitUpdateRequest" + responses: + "200": + description: Project rate limit updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectRateLimit" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Modify project rate limit + group: administration + returns: The updated + [ProjectRateLimit](/docs/api-reference/project-rate-limits/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc/rate_limits/rl_xxx + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "max_requests_per_1_minute": 500 + }' + response: | + { + "object": "project.rate_limit", + "id": "rl-ada", + "model": "ada", + "max_requests_per_1_minute": 600, + "max_tokens_per_1_minute": 150000, + "max_images_per_1_minute": 10 + } + error_response: | + { + "code": 404, + "message": "The project {project_id} was not found" + } + /organization/projects/{project_id}/service_accounts: + get: + summary: Returns a list of service accounts in the project. + operationId: list-project-service-accounts + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project service accounts listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountListResponse" + "400": + description: Error response when project is archived. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: List project service accounts + group: administration + returns: A list of + [ProjectServiceAccount](/docs/api-reference/project-service-accounts/object) + objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects/proj_abc/service_accounts?after=custom_id&limit=20 + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "list", + "data": [ + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Service Account", + "role": "owner", + "created_at": 1711471533 + } + ], + "first_id": "svc_acct_abc", + "last_id": "svc_acct_xyz", + "has_more": false + } + post: + summary: Creates a new service account in the project. This also returns an + unredacted API key for the service account. + operationId: create-project-service-account + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + requestBody: + description: The project service account create request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountCreateRequest" + responses: + "200": + description: Project service account created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountCreateResponse" + "400": + description: Error response when project is archived. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Create project service account + group: administration + returns: The created + [ProjectServiceAccount](/docs/api-reference/project-service-accounts/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc/service_accounts + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "Production App" + }' + response: + content: | + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Production App", + "role": "member", + "created_at": 1711471533, + "api_key": { + "object": "organization.project.service_account.api_key", + "value": "sk-abcdefghijklmnop123", + "name": "Secret Key", + "created_at": 1711471533, + "id": "key_abc" + } + } + /organization/projects/{project_id}/service_accounts/{service_account_id}: + get: + summary: Retrieves a service account in the project. + operationId: retrieve-project-service-account + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: service_account_id + in: path + description: The ID of the service account. + required: true + schema: + type: string + responses: + "200": + description: Project service account retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccount" + x-oaiMeta: + name: Retrieve project service account + group: administration + returns: The + [ProjectServiceAccount](/docs/api-reference/project-service-accounts/object) + object matching the specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Service Account", + "role": "owner", + "created_at": 1711471533 + } + delete: + summary: Deletes a service account from the project. + operationId: delete-project-service-account + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: service_account_id + in: path + description: The ID of the service account. + required: true + schema: + type: string + responses: + "200": + description: Project service account deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountDeleteResponse" + x-oaiMeta: + name: Delete project service account + group: administration + returns: Confirmation of service account being deleted, or an error in case of + an archived project, which has no service accounts + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.project.service_account.deleted", + "id": "svc_acct_abc", + "deleted": true + } + /organization/projects/{project_id}/users: + get: + summary: Returns a list of users in the project. + operationId: list-project-users + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project users listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserListResponse" + "400": + description: Error response when project is archived. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: List project users + group: administration + returns: A list of [ProjectUser](/docs/api-reference/project-users/object) + objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects/proj_abc/users?after=user_abc&limit=20 + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "list", + "data": [ + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + ], + "first_id": "user-abc", + "last_id": "user-xyz", + "has_more": false + } + error_response: + content: | + { + "code": 400, + "message": "Project {name} is archived" + } + post: + summary: Adds a user to the project. Users must already be members of the + organization to be added to a project. + operationId: create-project-user + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + tags: + - Projects + requestBody: + description: The project user create request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserCreateRequest" + responses: + "200": + description: User added to project successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUser" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Create project user + group: administration + returns: The created [ProjectUser](/docs/api-reference/project-users/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc/users \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "user_id": "user_abc", + "role": "member" + }' + response: + content: | + { + "object": "organization.project.user", + "id": "user_abc", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + error_response: + content: | + { + "code": 400, + "message": "Project {name} is archived" + } + /organization/projects/{project_id}/users/{user_id}: + get: + summary: Retrieves a user in the project. + operationId: retrieve-project-user + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: Project user retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUser" + x-oaiMeta: + name: Retrieve project user + group: administration + returns: The [ProjectUser](/docs/api-reference/project-users/object) object + matching the specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + post: + summary: Modifies a user's role in the project. + operationId: modify-project-user + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + requestBody: + description: The project user update request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserUpdateRequest" + responses: + "200": + description: Project user's role updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUser" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Modify project user + group: administration + returns: The updated [ProjectUser](/docs/api-reference/project-users/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "role": "owner" + }' + response: + content: | + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + delete: + summary: Deletes a user from the project. + operationId: delete-project-user + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: Project user deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserDeleteResponse" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Delete project user + group: administration + returns: Confirmation that project has been deleted or an error in case of an + archived project, which has no users + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.project.user.deleted", + "id": "user_abc", + "deleted": true + } + /organization/usage/audio_speeches: + get: + summary: Get audio speeches usage details for the organization. + operationId: usage-audio-speeches + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Audio speeches + group: usage-audio-speeches + returns: A list of paginated, time bucketed [Audio speeches + usage](/docs/api-reference/usage/audio_speeches_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/audio_speeches?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.audio_speeches.result", + "characters": 45, + "num_model_requests": 1, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null } - - main(); - response: | - { - "id": "asst_abc123", - "object": "assistant", - "created_at": 1699009709, - "name": "HR Helper", - "description": null, - "model": "gpt-4-turbo", - "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", - "tools": [ + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/audio_transcriptions: + get: + summary: Get audio transcriptions usage details for the organization. + operationId: usage-audio-transcriptions + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Audio transcriptions + group: usage-audio-transcriptions + returns: A list of paginated, time bucketed [Audio transcriptions + usage](/docs/api-reference/usage/audio_transcriptions_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/audio_transcriptions?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ { - "type": "file_search" + "object": "organization.usage.audio_transcriptions.result", + "seconds": 20, + "num_model_requests": 1, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null } - ], - "metadata": {}, - "top_p": 1.0, - "temperature": 1.0, - "response_format": "auto" - } - post: - operationId: modifyAssistant - tags: - - Assistants - summary: Modifies an assistant. - parameters: - - in: path - name: assistant_id - required: true - schema: - type: string - description: The ID of the assistant to modify. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/ModifyAssistantRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/AssistantObject" - x-oaiMeta: - name: Modify assistant - group: assistants - beta: true - returns: The modified [assistant](/docs/api-reference/assistants/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/assistants/asst_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", - "tools": [{"type": "file_search"}], - "model": "gpt-4-turbo" - }' - python: | - from openai import OpenAI - client = OpenAI() - - my_updated_assistant = client.beta.assistants.update( - "asst_abc123", - instructions="You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", - name="HR Helper", - tools=[{"type": "file_search"}], - model="gpt-4-turbo" - ) - - print(my_updated_assistant) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const myUpdatedAssistant = await openai.beta.assistants.update( - "asst_abc123", - { - instructions: - "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", - name: "HR Helper", - tools: [{ type: "file_search" }], - model: "gpt-4-turbo" - } - ); - - console.log(myUpdatedAssistant); + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/code_interpreter_sessions: + get: + summary: Get code interpreter sessions usage details for the organization. + operationId: usage-code-interpreter-sessions + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Code interpreter sessions + group: usage-code-interpreter-sessions + returns: A list of paginated, time bucketed [Code interpreter sessions + usage](/docs/api-reference/usage/code_interpreter_sessions_object) + objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/code_interpreter_sessions?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.code_interpreter_sessions.result", + "sessions": 1, + "project_id": null } - - main(); - response: | - { - "id": "asst_123", - "object": "assistant", - "created_at": 1699009709, - "name": "HR Helper", - "description": null, - "model": "gpt-4-turbo", - "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", - "tools": [ + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/completions: + get: + summary: Get completions usage details for the organization. + operationId: usage-completions + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: batch + in: query + description: > + If `true`, return batch jobs only. If `false`, return non-batch jobs + only. By default, return both. + required: false + schema: + type: boolean + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model`, `batch` or + any combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - batch + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Completions + group: usage-completions + returns: A list of paginated, time bucketed [Completions + usage](/docs/api-reference/usage/completions_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/completions?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ { - "type": "file_search" + "object": "organization.usage.completions.result", + "input_tokens": 1000, + "output_tokens": 500, + "input_cached_tokens": 800, + "num_model_requests": 5, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null, + "batch": null } - ], - "tool_resources": { - "file_search": { - "vector_store_ids": [] + ] + } + ], + "has_more": true, + "next_page": "AAAAAGdGxdEiJdKOAAAAAGcqsYA=" + } + /organization/usage/embeddings: + get: + summary: Get embeddings usage details for the organization. + operationId: usage-embeddings + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Embeddings + group: usage-embeddings + returns: A list of paginated, time bucketed [Embeddings + usage](/docs/api-reference/usage/embeddings_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/embeddings?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.embeddings.result", + "input_tokens": 16, + "num_model_requests": 2, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null } - }, - "metadata": {}, - "top_p": 1.0, - "temperature": 1.0, - "response_format": "auto" - } - delete: - operationId: deleteAssistant - tags: - - Assistants - summary: Delete an assistant. - parameters: - - in: path - name: assistant_id - required: true - schema: - type: string - description: The ID of the assistant to delete. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/DeleteAssistantResponse" - x-oaiMeta: - name: Delete assistant - group: assistants - beta: true - returns: Deletion status - examples: - request: - curl: | - curl https://api.openai.com/v1/assistants/asst_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -X DELETE - python: | - from openai import OpenAI - client = OpenAI() - - response = client.beta.assistants.delete("asst_abc123") - print(response) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const response = await openai.beta.assistants.del("asst_abc123"); - - console.log(response); + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/images: + get: + summary: Get images usage details for the organization. + operationId: usage-images + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: sources + in: query + description: Return only usages for these sources. Possible values are + `image.generation`, `image.edit`, `image.variation` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - image.generation + - image.edit + - image.variation + - name: sizes + in: query + description: Return only usages for these image sizes. Possible values are + `256x256`, `512x512`, `1024x1024`, `1792x1792`, `1024x1792` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - 256x256 + - 512x512 + - 1024x1024 + - 1792x1792 + - 1024x1792 + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model`, `size`, + `source` or any combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - size + - source + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Images + group: usage-images + returns: A list of paginated, time bucketed [Images + usage](/docs/api-reference/usage/images_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/images?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: | + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.images.result", + "images": 2, + "num_model_requests": 2, + "size": null, + "source": null, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null } - main(); - response: | - { - "id": "asst_abc123", - "object": "assistant.deleted", - "deleted": true - } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/moderations: + get: + summary: Get moderations usage details for the organization. + operationId: usage-moderations + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Moderations + group: usage-moderations + returns: A list of paginated, time bucketed [Moderations + usage](/docs/api-reference/usage/moderations_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/moderations?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.moderations.result", + "input_tokens": 16, + "num_model_requests": 2, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/vector_stores: + get: + summary: Get vector stores usage details for the organization. + operationId: usage-vector-stores + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Vector stores + group: usage-vector-stores + returns: A list of paginated, time bucketed [Vector stores + usage](/docs/api-reference/usage/vector_stores_object) objects. + examples: + request: + curl: > + curl + "https://api.openai.com/v1/organization/usage/vector_stores?start_time=1730419200&limit=1" + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.vector_stores.result", + "usage_bytes": 1024, + "project_id": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/users: + get: + summary: Lists all of the users in the organization. + operationId: list-users + tags: + - Users + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Users listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UserListResponse" + x-oaiMeta: + name: List users + group: administration + returns: A list of [User](/docs/api-reference/users/object) objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/users?after=user_abc&limit=20 + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "list", + "data": [ + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + ], + "first_id": "user-abc", + "last_id": "user-xyz", + "has_more": false + } + /organization/users/{user_id}: + get: + summary: Retrieves a user by their identifier. + operationId: retrieve-user + tags: + - Users + parameters: + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: User retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/User" + x-oaiMeta: + name: Retrieve user + group: administration + returns: The [User](/docs/api-reference/users/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/users/user_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + post: + summary: Modifies a user's role in the organization. + operationId: modify-user + tags: + - Users + parameters: + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + requestBody: + description: The new user role to modify. This must be one of `owner` or `member`. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/UserRoleUpdateRequest" + responses: + "200": + description: User role updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/User" + x-oaiMeta: + name: Modify user + group: administration + returns: The updated [User](/docs/api-reference/users/object) object. + examples: + request: + curl: > + curl -X POST https://api.openai.com/v1/organization/users/user_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "role": "owner" + }' + response: + content: | + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + delete: + summary: Deletes a user from the organization. + operationId: delete-user + tags: + - Users + parameters: + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: User deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UserDeleteResponse" + x-oaiMeta: + name: Delete user + group: administration + returns: Confirmation of the deleted user + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/users/user_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: + content: | + { + "object": "organization.user.deleted", + "id": "user_abc", + "deleted": true + } + /threads: + post: + operationId: createThread + tags: + - Assistants + summary: Create a thread. + requestBody: + content: + application/json: + schema: + $ref: "#/components/schemas/CreateThreadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ThreadObject" + x-oaiMeta: + name: Create thread + group: threads + beta: true + returns: A [thread](/docs/api-reference/threads) object. + examples: + - title: Empty + request: + curl: | + curl https://api.openai.com/v1/threads \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '' + python: | + from openai import OpenAI + client = OpenAI() + + empty_thread = client.beta.threads.create() + print(empty_thread) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const emptyThread = await openai.beta.threads.create(); + + console.log(emptyThread); + } + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699012949, + "metadata": {}, + "tool_resources": {} + } + - title: Messages + request: + curl: | + curl https://api.openai.com/v1/threads \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "messages": [{ + "role": "user", + "content": "Hello, what is AI?" + }, { + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }] + }' + python: | + from openai import OpenAI + client = OpenAI() + + message_thread = client.beta.threads.create( + messages=[ + { + "role": "user", + "content": "Hello, what is AI?" + }, + { + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }, + ] + ) - /threads: - post: - operationId: createThread - tags: - - Assistants - summary: Create a thread. - requestBody: - content: - application/json: - schema: - $ref: "#/components/schemas/CreateThreadRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ThreadObject" - x-oaiMeta: - name: Create thread - group: threads - beta: true - returns: A [thread](/docs/api-reference/threads) object. - examples: - - title: Empty - request: - curl: | - curl https://api.openai.com/v1/threads \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '' - python: | - from openai import OpenAI - client = OpenAI() - - empty_thread = client.beta.threads.create() - print(empty_thread) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const emptyThread = await openai.beta.threads.create(); - - console.log(emptyThread); - } + print(message_thread) + node.js: >- + import OpenAI from "openai"; - main(); - response: | - { - "id": "thread_abc123", - "object": "thread", - "created_at": 1699012949, - "metadata": {}, - "tool_resources": {} - } - - title: Messages - request: - curl: | - curl https://api.openai.com/v1/threads \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "messages": [{ - "role": "user", - "content": "Hello, what is AI?" - }, { - "role": "user", - "content": "How does AI work? Explain it in simple terms." - }] - }' - python: | - from openai import OpenAI - client = OpenAI() - - message_thread = client.beta.threads.create( - messages=[ - { - "role": "user", - "content": "Hello, what is AI?" - }, - { - "role": "user", - "content": "How does AI work? Explain it in simple terms." - }, - ] - ) - - print(message_thread) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const messageThread = await openai.beta.threads.create({ - messages: [ - { - role: "user", - content: "Hello, what is AI?" - }, - { - role: "user", - content: "How does AI work? Explain it in simple terms.", - }, - ], - }); - - console.log(messageThread); - } - main(); - response: | - { - "id": "thread_abc123", - "object": "thread", - "created_at": 1699014083, - "metadata": {}, - "tool_resources": {} - } + const openai = new OpenAI(); - /threads/{thread_id}: - get: - operationId: getThread - tags: - - Assistants - summary: Retrieves a thread. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to retrieve. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ThreadObject" - x-oaiMeta: - name: Retrieve thread - group: threads - beta: true - returns: The [thread](/docs/api-reference/threads/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - my_thread = client.beta.threads.retrieve("thread_abc123") - print(my_thread) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const myThread = await openai.beta.threads.retrieve( - "thread_abc123" - ); - - console.log(myThread); - } - main(); - response: | - { - "id": "thread_abc123", - "object": "thread", - "created_at": 1699014083, - "metadata": {}, - "tool_resources": { - "code_interpreter": { - "file_ids": [] - } - } - } - post: - operationId: modifyThread - tags: - - Assistants - summary: Modifies a thread. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to modify. Only the `metadata` can be modified. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/ModifyThreadRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ThreadObject" - x-oaiMeta: - name: Modify thread - group: threads - beta: true - returns: The modified [thread](/docs/api-reference/threads/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "metadata": { - "modified": "true", - "user": "abc123" - } - }' - python: | - from openai import OpenAI - client = OpenAI() - - my_updated_thread = client.beta.threads.update( - "thread_abc123", - metadata={ - "modified": "true", - "user": "abc123" - } - ) - print(my_updated_thread) - node.js: |- - import OpenAI from "openai"; + async function main() { + const messageThread = await openai.beta.threads.create({ + messages: [ + { + role: "user", + content: "Hello, what is AI?" + }, + { + role: "user", + content: "How does AI work? Explain it in simple terms.", + }, + ], + }); + + console.log(messageThread); + } + + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "metadata": {}, + "tool_resources": {} + } + /threads/runs: + post: + operationId: createThreadAndRun + tags: + - Assistants + summary: Create a thread and run it in one request. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateThreadAndRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Create thread and run + group: threads + beta: true + returns: A [run](/docs/api-reference/runs/object) object. + examples: + - title: Default + request: + curl: > + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "thread": { + "messages": [ + {"role": "user", "content": "Explain deep learning to a 5 year old."} + ] + } + }' + python: > + from openai import OpenAI - const openai = new OpenAI(); + client = OpenAI() - async function main() { - const updatedThread = await openai.beta.threads.update( - "thread_abc123", - { - metadata: { modified: "true", user: "abc123" }, - } - ); - console.log(updatedThread); - } + run = client.beta.threads.create_and_run( + assistant_id="asst_abc123", + thread={ + "messages": [ + {"role": "user", "content": "Explain deep learning to a 5 year old."} + ] + } + ) - main(); - response: | - { - "id": "thread_abc123", - "object": "thread", - "created_at": 1699014083, - "metadata": { - "modified": "true", - "user": "abc123" - }, - "tool_resources": {} - } - delete: - operationId: deleteThread - tags: - - Assistants - summary: Delete a thread. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to delete. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/DeleteThreadResponse" - x-oaiMeta: - name: Delete thread - group: threads - beta: true - returns: Deletion status - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -X DELETE - python: | - from openai import OpenAI - client = OpenAI() - - response = client.beta.threads.delete("thread_abc123") - print(response) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const response = await openai.beta.threads.del("thread_abc123"); - - console.log(response); - } - main(); - response: | - { - "id": "thread_abc123", - "object": "thread.deleted", - "deleted": true - } - /threads/{thread_id}/messages: - get: - operationId: listMessages - tags: - - Assistants - summary: Returns a list of messages for a given thread. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the [thread](/docs/api-reference/threads) the messages belong to. - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string - - name: run_id - in: query - description: | - Filter messages by the run ID that generated them. - schema: - type: string - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListMessagesResponse" - x-oaiMeta: - name: List messages - group: threads - beta: true - returns: A list of [message](/docs/api-reference/messages) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/messages \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - thread_messages = client.beta.threads.messages.list("thread_abc123") - print(thread_messages.data) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const threadMessages = await openai.beta.threads.messages.list( - "thread_abc123" - ); - - console.log(threadMessages.data); - } + print(run) + node.js: > + import OpenAI from "openai"; - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "msg_abc123", - "object": "thread.message", - "created_at": 1699016383, - "assistant_id": null, - "thread_id": "thread_abc123", - "run_id": null, - "role": "user", - "content": [ - { - "type": "text", - "text": { - "value": "How does AI work? Explain it in simple terms.", - "annotations": [] - } - } - ], - "attachments": [], - "metadata": {} - }, - { - "id": "msg_abc456", - "object": "thread.message", - "created_at": 1699016383, - "assistant_id": null, - "thread_id": "thread_abc123", - "run_id": null, - "role": "user", - "content": [ - { - "type": "text", - "text": { - "value": "Hello, what is AI?", - "annotations": [] - } - } - ], - "attachments": [], - "metadata": {} - } - ], - "first_id": "msg_abc123", - "last_id": "msg_abc456", - "has_more": false - } - post: - operationId: createMessage - tags: - - Assistants - summary: Create a message. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the [thread](/docs/api-reference/threads) to create a message for. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateMessageRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/MessageObject" - x-oaiMeta: - name: Create message - group: threads - beta: true - returns: A [message](/docs/api-reference/messages/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/messages \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "role": "user", - "content": "How does AI work? Explain it in simple terms." - }' - python: | - from openai import OpenAI - client = OpenAI() - - thread_message = client.beta.threads.messages.create( - "thread_abc123", - role="user", - content="How does AI work? Explain it in simple terms.", - ) - print(thread_message) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const threadMessages = await openai.beta.threads.messages.create( - "thread_abc123", - { role: "user", content: "How does AI work? Explain it in simple terms." } - ); - - console.log(threadMessages); - } - main(); - response: | - { - "id": "msg_abc123", - "object": "thread.message", - "created_at": 1713226573, - "assistant_id": null, - "thread_id": "thread_abc123", - "run_id": null, - "role": "user", - "content": [ - { - "type": "text", - "text": { - "value": "How does AI work? Explain it in simple terms.", - "annotations": [] - } - } - ], - "attachments": [], - "metadata": {} - } + const openai = new OpenAI(); - /threads/{thread_id}/messages/{message_id}: - get: - operationId: getMessage - tags: - - Assistants - summary: Retrieve a message. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the [thread](/docs/api-reference/threads) to which this message belongs. - - in: path - name: message_id - required: true - schema: - type: string - description: The ID of the message to retrieve. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/MessageObject" - x-oaiMeta: - name: Retrieve message - group: threads - beta: true - returns: The [message](/docs/api-reference/messages/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - message = client.beta.threads.messages.retrieve( - message_id="msg_abc123", - thread_id="thread_abc123", - ) - print(message) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const message = await openai.beta.threads.messages.retrieve( - "thread_abc123", - "msg_abc123" - ); - - console.log(message); - } - main(); - response: | - { - "id": "msg_abc123", - "object": "thread.message", - "created_at": 1699017614, - "assistant_id": null, - "thread_id": "thread_abc123", - "run_id": null, - "role": "user", - "content": [ - { - "type": "text", - "text": { - "value": "How does AI work? Explain it in simple terms.", - "annotations": [] - } - } - ], - "attachments": [], - "metadata": {} - } - post: - operationId: modifyMessage - tags: - - Assistants - summary: Modifies a message. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to which this message belongs. - - in: path - name: message_id - required: true - schema: - type: string - description: The ID of the message to modify. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/ModifyMessageRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/MessageObject" - x-oaiMeta: - name: Modify message - group: threads - beta: true - returns: The modified [message](/docs/api-reference/messages/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "metadata": { - "modified": "true", - "user": "abc123" - } - }' - python: | - from openai import OpenAI - client = OpenAI() - - message = client.beta.threads.messages.update( - message_id="msg_abc12", - thread_id="thread_abc123", - metadata={ - "modified": "true", - "user": "abc123", - }, - ) - print(message) - node.js: |- - import OpenAI from "openai"; + async function main() { + const run = await openai.beta.threads.createAndRun({ + assistant_id: "asst_abc123", + thread: { + messages: [ + { role: "user", content: "Explain deep learning to a 5 year old." }, + ], + }, + }); + + console.log(run); + } + + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699076792, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "queued", + "started_at": null, + "expires_at": 1699077392, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "required_action": null, + "last_error": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant.", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "temperature": 1.0, + "top_p": 1.0, + "max_completion_tokens": null, + "max_prompt_tokens": null, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "incomplete_details": null, + "usage": null, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_123", + "thread": { + "messages": [ + {"role": "user", "content": "Hello"} + ] + }, + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + stream = client.beta.threads.create_and_run( + assistant_id="asst_123", + thread={ + "messages": [ + {"role": "user", "content": "Hello"} + ] + }, + stream=True + ) + + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const stream = await openai.beta.threads.createAndRun({ + assistant_id: "asst_123", + thread: { + messages: [ + { role: "user", content: "Hello" }, + ], + }, + stream: true + }); - const openai = new OpenAI(); + for await (const event of stream) { + console.log(event); + } + } - async function main() { - const message = await openai.beta.threads.messages.update( - "thread_abc123", - "msg_abc123", - { - metadata: { - modified: "true", - user: "abc123", - }, - } - }' - response: | - { - "id": "msg_abc123", - "object": "thread.message", - "created_at": 1699017614, - "assistant_id": null, - "thread_id": "thread_abc123", - "run_id": null, - "role": "user", - "content": [ - { - "type": "text", - "text": { - "value": "How does AI work? Explain it in simple terms.", - "annotations": [] - } - } - ], - "file_ids": [], - "metadata": { - "modified": "true", - "user": "abc123" - } - } - delete: - operationId: deleteMessage - tags: - - Assistants - summary: Deletes a message. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to which this message belongs. - - in: path - name: message_id - required: true - schema: - type: string - description: The ID of the message to delete. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/DeleteMessageResponse" - x-oaiMeta: - name: Delete message - group: threads - beta: true - returns: Deletion status - examples: - request: - curl: | - curl -X DELETE https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - deleted_message = client.beta.threads.messages.delete( - message_id="msg_abc12", - thread_id="thread_abc123", - ) - print(deleted_message) - node.js: |- - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const deletedMessage = await openai.beta.threads.messages.del( - "thread_abc123", - "msg_abc123" - ); - - console.log(deletedMessage); - } - response: | - { - "id": "msg_abc123", - "object": "thread.message.deleted", - "deleted": true - } + main(); + response: > + event: thread.created - /threads/runs: - post: - operationId: createThreadAndRun - tags: - - Assistants - summary: Create a thread and run it in one request. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateThreadAndRunRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Create thread and run - group: threads - beta: true - returns: A [run](/docs/api-reference/runs/object) object. - examples: - - title: Default - request: - curl: | - curl https://api.openai.com/v1/threads/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "assistant_id": "asst_abc123", - "thread": { - "messages": [ - {"role": "user", "content": "Explain deep learning to a 5 year old."} - ] - } - }' - python: | - from openai import OpenAI - client = OpenAI() - - run = client.beta.threads.create_and_run( - assistant_id="asst_abc123", - thread={ - "messages": [ - {"role": "user", "content": "Explain deep learning to a 5 year old."} - ] - } - ) + data: + {"id":"thread_123","object":"thread","created_at":1710348075,"metadata":{}} - print(run) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); + event: thread.run.created - async function main() { - const run = await openai.beta.threads.createAndRun({ - assistant_id: "asst_abc123", - thread: { - messages: [ - { role: "user", content: "Explain deep learning to a 5 year old." }, - ], - }, - }); + data: + {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - console.log(run); - } - main(); - response: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699076792, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "queued", - "started_at": null, - "expires_at": 1699077392, - "cancelled_at": null, - "failed_at": null, - "completed_at": null, - "required_action": null, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": "You are a helpful assistant.", - "tools": [], - "tool_resources": {}, - "metadata": {}, - "temperature": 1.0, - "top_p": 1.0, - "max_completion_tokens": null, - "max_prompt_tokens": null, - "truncation_strategy": { - "type": "auto", - "last_messages": null - }, - "incomplete_details": null, - "usage": null, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - } + event: thread.run.queued - - title: Streaming - request: - curl: | - curl https://api.openai.com/v1/threads/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "assistant_id": "asst_123", - "thread": { - "messages": [ - {"role": "user", "content": "Hello"} - ] - }, - "stream": true - }' - python: | - from openai import OpenAI - client = OpenAI() - - stream = client.beta.threads.create_and_run( - assistant_id="asst_123", - thread={ - "messages": [ - {"role": "user", "content": "Hello"} - ] - }, - stream=True - ) - - for event in stream: - print(event) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const stream = await openai.beta.threads.createAndRun({ - assistant_id: "asst_123", - thread: { - messages: [ - { role: "user", content: "Hello" }, - ], - }, - stream: true - }); - - for await (const event of stream) { - console.log(event); - } - } + data: + {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - main(); - response: | - event: thread.created - data: {"id":"thread_123","object":"thread","created_at":1710348075,"metadata":{}} - - event: thread.run.created - data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - - event: thread.run.queued - data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - - event: thread.run.in_progress - data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - - event: thread.run.step.created - data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - - event: thread.run.step.in_progress - data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - - event: thread.message.created - data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}} - - event: thread.message.in_progress - data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}} - - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} - - ... - - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} - - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} - - event: thread.message.completed - data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}], "metadata":{}} - - event: thread.run.step.completed - data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} - - event: thread.run.completed - {"id":"run_123","object":"thread.run","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1713226836,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1713226837,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - - event: done - data: [DONE] - - - title: Streaming with Functions - request: - curl: | - curl https://api.openai.com/v1/threads/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "assistant_id": "asst_abc123", - "thread": { - "messages": [ - {"role": "user", "content": "What is the weather like in San Francisco?"} - ] - }, - "tools": [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA" - }, - "unit": { - "type": "string", - "enum": ["celsius", "fahrenheit"] - } - }, - "required": ["location"] - } - } - } - ], - "stream": true - }' - python: | - from openai import OpenAI - client = OpenAI() - - tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, - }, - "required": ["location"], - }, - } - } - ] - stream = client.beta.threads.create_and_run( - thread={ - "messages": [ - {"role": "user", "content": "What is the weather like in San Francisco?"} - ] - }, - assistant_id="asst_abc123", - tools=tools, - stream=True - ) - - for event in stream: - print(event) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - const tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, - }, - "required": ["location"], - }, - } - } - ]; - - async function main() { - const stream = await openai.beta.threads.createAndRun({ - assistant_id: "asst_123", - thread: { - messages: [ - { role: "user", content: "What is the weather like in San Francisco?" }, - ], - }, - tools: tools, - stream: true - }); - - for await (const event of stream) { - console.log(event); - } - } + event: thread.run.in_progress - main(); - response: | - event: thread.created - data: {"id":"thread_123","object":"thread","created_at":1710351818,"metadata":{}} + data: + {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - event: thread.run.created - data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - event: thread.run.queued - data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + event: thread.run.step.created - event: thread.run.in_progress - data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + data: + {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - event: thread.run.step.created - data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} - event: thread.run.step.in_progress - data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} + event: thread.run.step.in_progress - event: thread.run.step.delta - data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"","output":null}}]}}} + data: + {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - event: thread.run.step.delta - data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]}}} - event: thread.run.step.delta - data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"location"}}]}}} + event: thread.message.created - ... + data: + {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], + "metadata":{}} - event: thread.run.step.delta - data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"ahrenheit"}}]}}} - event: thread.run.step.delta - data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]}}} + event: thread.message.in_progress - event: thread.run.requires_action - data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"requires_action","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":{"type":"submit_tool_outputs","submit_tool_outputs":{"tool_calls":[{"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"fahrenheit\"}"}}]}},"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + data: + {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], + "metadata":{}} - event: done - data: [DONE] - /threads/{thread_id}/runs: - get: - operationId: listRuns - tags: - - Assistants - summary: Returns a list of runs belonging to a thread. - parameters: - - name: thread_id - in: path - required: true - schema: - type: string - description: The ID of the thread the run belongs to. - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListRunsResponse" - x-oaiMeta: - name: List runs - group: threads - beta: true - returns: A list of [run](/docs/api-reference/runs/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - runs = client.beta.threads.runs.list( - "thread_abc123" - ) - - print(runs) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const runs = await openai.beta.threads.runs.list( - "thread_abc123" - ); - - console.log(runs); - } + event: thread.message.delta - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699075072, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699075072, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699075073, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": null, - "incomplete_details": null, - "tools": [ - { - "type": "code_interpreter" - } - ], - "tool_resources": { - "code_interpreter": { - "file_ids": [ - "file-abc123", - "file-abc456" - ] - } - }, - "metadata": {}, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - }, - "temperature": 1.0, - "top_p": 1.0, - "max_prompt_tokens": 1000, - "max_completion_tokens": 1000, - "truncation_strategy": { - "type": "auto", - "last_messages": null - }, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - }, - { - "id": "run_abc456", - "object": "thread.run", - "created_at": 1699063290, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699063290, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699063291, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": null, - "incomplete_details": null, - "tools": [ - { - "type": "code_interpreter" - } - ], - "tool_resources": { - "code_interpreter": { - "file_ids": [ - "file-abc123", - "file-abc456" - ] - } - }, - "metadata": {}, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - }, - "temperature": 1.0, - "top_p": 1.0, - "max_prompt_tokens": 1000, - "max_completion_tokens": 1000, - "truncation_strategy": { - "type": "auto", - "last_messages": null - }, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - } - ], - "first_id": "run_abc123", - "last_id": "run_abc456", - "has_more": false - } - post: - operationId: createRun - tags: - - Assistants - summary: Create a run. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to run. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateRunRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Create run - group: threads - beta: true - returns: A [run](/docs/api-reference/runs/object) object. - examples: - - title: Default - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "assistant_id": "asst_abc123" - }' - python: | - from openai import OpenAI - client = OpenAI() - - run = client.beta.threads.runs.create( - thread_id="thread_abc123", - assistant_id="asst_abc123" - ) - - print(run) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const run = await openai.beta.threads.runs.create( - "thread_abc123", - { assistant_id: "asst_abc123" } - ); - - console.log(run); - } + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} - main(); - response: &run_object_example | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699063290, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "queued", - "started_at": 1699063290, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699063291, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": null, - "incomplete_details": null, - "tools": [ - { - "type": "code_interpreter" - } - ], - "metadata": {}, - "usage": null, - "temperature": 1.0, - "top_p": 1.0, - "max_prompt_tokens": 1000, - "max_completion_tokens": 1000, - "truncation_strategy": { - "type": "auto", - "last_messages": null - }, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - } - - title: Streaming - request: - curl: | - curl https://api.openai.com/v1/threads/thread_123/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "assistant_id": "asst_123", - "stream": true - }' - python: | - from openai import OpenAI - client = OpenAI() - - stream = client.beta.threads.runs.create( - thread_id="thread_123", - assistant_id="asst_123", - stream=True - ) - - for event in stream: - print(event) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const stream = await openai.beta.threads.runs.create( - "thread_123", - { assistant_id: "asst_123", stream: true } - ); - - for await (const event of stream) { - console.log(event); - } - } - main(); - response: | - event: thread.run.created - data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - - event: thread.run.queued - data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - - event: thread.run.in_progress - data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710330641,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - - event: thread.run.step.created - data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - - event: thread.run.step.in_progress - data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - - event: thread.message.created - data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - - event: thread.message.in_progress - data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} - - ... - - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} - - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} - - event: thread.message.completed - data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710330642,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}],"metadata":{}} - - event: thread.run.step.completed - data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710330642,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} - - event: thread.run.completed - data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710330641,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710330642,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - - event: done - data: [DONE] - - - title: Streaming with Functions - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "assistant_id": "asst_abc123", - "tools": [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA" - }, - "unit": { - "type": "string", - "enum": ["celsius", "fahrenheit"] - } - }, - "required": ["location"] - } - } - } - ], - "stream": true - }' - python: | - from openai import OpenAI - client = OpenAI() - - tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, - }, - "required": ["location"], - }, - } - } - ] - - stream = client.beta.threads.runs.create( - thread_id="thread_abc123", - assistant_id="asst_abc123", - tools=tools, - stream=True - ) - - for event in stream: - print(event) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - const tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, - }, - "required": ["location"], - }, - } - } - ]; - - async function main() { - const stream = await openai.beta.threads.runs.create( - "thread_abc123", - { - assistant_id: "asst_abc123", - tools: tools, - stream: true - } - ); - - for await (const event of stream) { - console.log(event); - } - } + ... - main(); - response: | - event: thread.run.created - data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - event: thread.run.queued - data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + event: thread.message.delta - event: thread.run.in_progress - data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710348075,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" + today"}}]}} - event: thread.run.step.created - data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - event: thread.run.step.in_progress - data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + event: thread.message.delta - event: thread.message.created - data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} - event: thread.message.in_progress - data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} + event: thread.message.completed - ... + data: + {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! + How can I assist you today?","annotations":[]}}], "metadata":{}} - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} - event: thread.message.delta - data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} + event: thread.run.step.completed - event: thread.message.completed - data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}],"metadata":{}} + data: + {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} - event: thread.run.step.completed - data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} - event: thread.run.completed - data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710348075,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710348077,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + event: thread.run.completed - event: done - data: [DONE] + {"id":"run_123","object":"thread.run","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1713226836,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1713226837,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} - /threads/{thread_id}/runs/{run_id}: - get: - operationId: getRun - tags: - - Assistants - summary: Retrieves a run. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the [thread](/docs/api-reference/threads) that was run. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run to retrieve. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Retrieve run - group: threads - beta: true - returns: The [run](/docs/api-reference/runs/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - run = client.beta.threads.runs.retrieve( - thread_id="thread_abc123", - run_id="run_abc123" - ) - - print(run) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const run = await openai.beta.threads.runs.retrieve( - "thread_abc123", - "run_abc123" - ); - - console.log(run); - } - main(); - response: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699075072, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699075072, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699075073, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": null, - "incomplete_details": null, - "tools": [ - { - "type": "code_interpreter" - } - ], - "metadata": {}, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - }, - "temperature": 1.0, - "top_p": 1.0, - "max_prompt_tokens": 1000, - "max_completion_tokens": 1000, - "truncation_strategy": { - "type": "auto", - "last_messages": null - }, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true + event: done + + data: [DONE] + - title: Streaming with Functions + request: + curl: > + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "thread": { + "messages": [ + {"role": "user", "content": "What is the weather like in San Francisco?"} + ] + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } } - post: - operationId: modifyRun - tags: - - Assistants - summary: Modifies a run. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the [thread](/docs/api-reference/threads) that was run. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run to modify. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/ModifyRunRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Modify run - group: threads - beta: true - returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "metadata": { - "user_id": "user_abc123" - } - }' - python: | - from openai import OpenAI - client = OpenAI() - - run = client.beta.threads.runs.update( - thread_id="thread_abc123", - run_id="run_abc123", - metadata={"user_id": "user_abc123"}, - ) - - print(run) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const run = await openai.beta.threads.runs.update( - "thread_abc123", - "run_abc123", - { - metadata: { - user_id: "user_abc123", - }, - } - ); + } + ], + "stream": true + }' + python: > + from openai import OpenAI - console.log(run); - } + client = OpenAI() - main(); - response: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699075072, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699075072, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699075073, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": null, - "incomplete_details": null, - "tools": [ - { - "type": "code_interpreter" - } - ], - "tool_resources": { - "code_interpreter": { - "file_ids": [ - "file-abc123", - "file-abc456" - ] - } - }, - "metadata": { - "user_id": "user_abc123" - }, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - }, - "temperature": 1.0, - "top_p": 1.0, - "max_prompt_tokens": 1000, - "max_completion_tokens": 1000, - "truncation_strategy": { - "type": "auto", - "last_messages": null + + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", }, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - } + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ] - /threads/{thread_id}/runs/{run_id}/submit_tool_outputs: - post: - operationId: submitToolOuputsToRun - tags: - - Assistants - summary: | - When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the [thread](/docs/api-reference/threads) to which this run belongs. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run that requires the tool output submission. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/SubmitToolOutputsRunRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Submit tool outputs to run - group: threads - beta: true - returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. - examples: - - title: Default - request: - curl: | - curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "tool_outputs": [ - { - "tool_call_id": "call_001", - "output": "70 degrees and sunny." - } - ] - }' - python: | - from openai import OpenAI - client = OpenAI() - - run = client.beta.threads.runs.submit_tool_outputs( - thread_id="thread_123", - run_id="run_123", - tool_outputs=[ - { - "tool_call_id": "call_001", - "output": "70 degrees and sunny." - } - ] - ) - - print(run) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const run = await openai.beta.threads.runs.submitToolOutputs( - "thread_123", - "run_123", - { - tool_outputs: [ - { - tool_call_id: "call_001", - output: "70 degrees and sunny.", - }, - ], - } - ); - - console.log(run); - } - main(); - response: | - { - "id": "run_123", - "object": "thread.run", - "created_at": 1699075592, - "assistant_id": "asst_123", - "thread_id": "thread_123", - "status": "queued", - "started_at": 1699075592, - "expires_at": 1699076192, - "cancelled_at": null, - "failed_at": null, - "completed_at": null, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": null, - "tools": [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather in a given location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA" - }, - "unit": { - "type": "string", - "enum": ["celsius", "fahrenheit"] - } - }, - "required": ["location"] - } - } - } - ], - "metadata": {}, - "usage": null, - "temperature": 1.0, - "top_p": 1.0, - "max_prompt_tokens": 1000, - "max_completion_tokens": 1000, - "truncation_strategy": { - "type": "auto", - "last_messages": null - }, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - } + stream = client.beta.threads.create_and_run( + thread={ + "messages": [ + {"role": "user", "content": "What is the weather like in San Francisco?"} + ] + }, + assistant_id="asst_abc123", + tools=tools, + stream=True + ) - - title: Streaming - request: - curl: | - curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "tool_outputs": [ - { - "tool_call_id": "call_001", - "output": "70 degrees and sunny." - } - ], - "stream": true - }' - python: | - from openai import OpenAI - client = OpenAI() - - stream = client.beta.threads.runs.submit_tool_outputs( - thread_id="thread_123", - run_id="run_123", - tool_outputs=[ - { - "tool_call_id": "call_001", - "output": "70 degrees and sunny." - } - ], - stream=True - ) - - for event in stream: - print(event) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const stream = await openai.beta.threads.runs.submitToolOutputs( - "thread_123", - "run_123", - { - tool_outputs: [ - { - tool_call_id: "call_001", - output: "70 degrees and sunny.", - }, - ], - } - ); - - for await (const event of stream) { - console.log(event); - } - } - main(); - response: | - event: thread.run.step.completed - data: {"id":"step_001","object":"thread.run.step","created_at":1710352449,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"completed","cancelled_at":null,"completed_at":1710352475,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[{"id":"call_iWr0kQ2EaYMaxNdl0v3KYkx7","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"fahrenheit\"}","output":"70 degrees and sunny."}}]},"usage":{"prompt_tokens":291,"completion_tokens":24,"total_tokens":315}} + for event in stream: + print(event) + node.js: > + import OpenAI from "openai"; - event: thread.run.queued - data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":1710352448,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - event: thread.run.in_progress - data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710352475,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + const openai = new OpenAI(); - event: thread.run.step.created - data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} - event: thread.run.step.in_progress - data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; - event: thread.message.created - data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - event: thread.message.in_progress - data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + async function main() { + const stream = await openai.beta.threads.createAndRun({ + assistant_id: "asst_123", + thread: { + messages: [ + { role: "user", content: "What is the weather like in San Francisco?" }, + ], + }, + tools: tools, + stream: true + }); - event: thread.message.delta - data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"The","annotations":[]}}]}} + for await (const event of stream) { + console.log(event); + } + } - event: thread.message.delta - data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" current"}}]}} - event: thread.message.delta - data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" weather"}}]}} + main(); + response: > + event: thread.created - ... + data: + {"id":"thread_123","object":"thread","created_at":1710351818,"metadata":{}} - event: thread.message.delta - data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" sunny"}}]}} - event: thread.message.delta - data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"."}}]}} + event: thread.run.created - event: thread.message.completed - data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710352477,"role":"assistant","content":[{"type":"text","text":{"value":"The current weather in San Francisco, CA is 70 degrees Fahrenheit and sunny.","annotations":[]}}],"metadata":{}} + data: + {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get + the current weather in a given + location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The + city and state, e.g. San Francisco, + CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - event: thread.run.step.completed - data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710352477,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":{"prompt_tokens":329,"completion_tokens":18,"total_tokens":347}} - event: thread.run.completed - data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710352475,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710352477,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + event: thread.run.queued - event: done - data: [DONE] + data: + {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get + the current weather in a given + location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The + city and state, e.g. San Francisco, + CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - /threads/{thread_id}/runs/{run_id}/cancel: - post: - operationId: cancelRun - tags: - - Assistants - summary: Cancels a run that is `in_progress`. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to which this run belongs. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run to cancel. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Cancel a run - group: threads - beta: true - returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/cancel \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v2" \ - -X POST - python: | - from openai import OpenAI - client = OpenAI() - - run = client.beta.threads.runs.cancel( - thread_id="thread_abc123", - run_id="run_abc123" - ) - - print(run) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const run = await openai.beta.threads.runs.cancel( - "thread_abc123", - "run_abc123" - ); - - console.log(run); - } - main(); - response: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699076126, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "cancelling", - "started_at": 1699076126, - "expires_at": 1699076726, - "cancelled_at": null, - "failed_at": null, - "completed_at": null, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": "You summarize books.", - "tools": [ - { - "type": "file_search" - } - ], - "tool_resources": { - "file_search": { - "vector_store_ids": ["vs_123"] - } - }, - "metadata": {}, - "usage": null, - "temperature": 1.0, - "top_p": 1.0, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - } + event: thread.run.in_progress - /threads/{thread_id}/runs/{run_id}/steps: - get: - operationId: listRunSteps - tags: - - Assistants - summary: Returns a list of run steps belonging to a run. - parameters: - - name: thread_id - in: path - required: true - schema: - type: string - description: The ID of the thread the run and run steps belong to. - - name: run_id - in: path - required: true - schema: - type: string - description: The ID of the run the run steps belong to. - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListRunStepsResponse" - x-oaiMeta: - name: List run steps - group: threads - beta: true - returns: A list of [run step](/docs/api-reference/runs/step-object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - run_steps = client.beta.threads.runs.steps.list( - thread_id="thread_abc123", - run_id="run_abc123" - ) - - print(run_steps) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const runStep = await openai.beta.threads.runs.steps.list( - "thread_abc123", - "run_abc123" - ); - console.log(runStep); - } + data: + {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get + the current weather in a given + location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The + city and state, e.g. San Francisco, + CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "step_abc123", - "object": "thread.run.step", - "created_at": 1699063291, - "run_id": "run_abc123", - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "type": "message_creation", - "status": "completed", - "cancelled_at": null, - "completed_at": 1699063291, - "expired_at": null, - "failed_at": null, - "last_error": null, - "step_details": { - "type": "message_creation", - "message_creation": { - "message_id": "msg_abc123" - } - }, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } - } - ], - "first_id": "step_abc123", - "last_id": "step_abc456", - "has_more": false - } - /threads/{thread_id}/runs/{run_id}/steps/{step_id}: - get: - operationId: getRunStep - tags: - - Assistants - summary: Retrieves a run step. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to which the run and run step belongs. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run to which the run step belongs. - - in: path - name: step_id - required: true - schema: - type: string - description: The ID of the run step to retrieve. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunStepObject" - x-oaiMeta: - name: Retrieve run step - group: threads - beta: true - returns: The [run step](/docs/api-reference/runs/step-object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - run_step = client.beta.threads.runs.steps.retrieve( - thread_id="thread_abc123", - run_id="run_abc123", - step_id="step_abc123" - ) - - print(run_step) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const runStep = await openai.beta.threads.runs.steps.retrieve( - "thread_abc123", - "run_abc123", - "step_abc123" - ); - console.log(runStep); - } + event: thread.run.step.created - main(); - response: &run_step_object_example | - { - "id": "step_abc123", - "object": "thread.run.step", - "created_at": 1699063291, - "run_id": "run_abc123", - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "type": "message_creation", - "status": "completed", - "cancelled_at": null, - "completed_at": 1699063291, - "expired_at": null, - "failed_at": null, - "last_error": null, - "step_details": { - "type": "message_creation", - "message_creation": { - "message_id": "msg_abc123" - } - }, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } - } + data: + {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} - /vector_stores: - get: - operationId: listVectorStores - tags: - - Vector Stores - summary: Returns a list of vector stores. - parameters: - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListVectorStoresResponse" - x-oaiMeta: - name: List vector stores - group: vector_stores - beta: true - returns: A list of [vector store](/docs/api-reference/vector-stores/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - vector_stores = client.beta.vector_stores.list() - print(vector_stores) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStores = await openai.beta.vectorStores.list(); - console.log(vectorStores); - } - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "vs_abc123", - "object": "vector_store", - "created_at": 1699061776, - "name": "Support FAQ", - "bytes": 139920, - "file_counts": { - "in_progress": 0, - "completed": 3, - "failed": 0, - "cancelled": 0, - "total": 3 - } - }, - { - "id": "vs_abc456", - "object": "vector_store", - "created_at": 1699061776, - "name": "Support FAQ v2", - "bytes": 139920, - "file_counts": { - "in_progress": 0, - "completed": 3, - "failed": 0, - "cancelled": 0, - "total": 3 - } - } - ], - "first_id": "vs_abc123", - "last_id": "vs_abc456", - "has_more": false - } - post: - operationId: createVectorStore - tags: - - Vector Stores - summary: Create a vector store. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateVectorStoreRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreObject" - x-oaiMeta: - name: Create vector store - group: vector_stores - beta: true - returns: A [vector store](/docs/api-reference/vector-stores/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - -d '{ - "name": "Support FAQ" - }' - python: | - from openai import OpenAI - client = OpenAI() - - vector_store = client.beta.vector_stores.create( - name="Support FAQ" - ) - print(vector_store) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStore = await openai.beta.vectorStores.create({ - name: "Support FAQ" - }); - console.log(vectorStore); - } + event: thread.run.step.in_progress - main(); - response: | - { - "id": "vs_abc123", - "object": "vector_store", - "created_at": 1699061776, - "name": "Support FAQ", - "bytes": 139920, - "file_counts": { - "in_progress": 0, - "completed": 3, - "failed": 0, - "cancelled": 0, - "total": 3 - } - } + data: + {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} - /vector_stores/{vector_store_id}: - get: - operationId: getVectorStore - tags: - - Vector Stores - summary: Retrieves a vector store. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - description: The ID of the vector store to retrieve. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreObject" - x-oaiMeta: - name: Retrieve vector store - group: vector_stores - beta: true - returns: The [vector store](/docs/api-reference/vector-stores/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - vector_store = client.beta.vector_stores.retrieve( - vector_store_id="vs_abc123" - ) - print(vector_store) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStore = await openai.beta.vectorStores.retrieve( - "vs_abc123" - ); - console.log(vectorStore); - } - main(); - response: | - { - "id": "vs_abc123", - "object": "vector_store", - "created_at": 1699061776 - } - post: - operationId: modifyVectorStore - tags: - - Vector Stores - summary: Modifies a vector store. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - description: The ID of the vector store to modify. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/UpdateVectorStoreRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreObject" - x-oaiMeta: - name: Modify vector store - group: vector_stores - beta: true - returns: The modified [vector store](/docs/api-reference/vector-stores/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - -d '{ - "name": "Support FAQ" - }' - python: | - from openai import OpenAI - client = OpenAI() - - vector_store = client.beta.vector_stores.update( - vector_store_id="vs_abc123", - name="Support FAQ" - ) - print(vector_store) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStore = await openai.beta.vectorStores.update( - "vs_abc123", - { - name: "Support FAQ" - } - ); - console.log(vectorStore); - } + event: thread.run.step.delta - main(); - response: | - { - "id": "vs_abc123", - "object": "vector_store", - "created_at": 1699061776, - "name": "Support FAQ", - "bytes": 139920, - "file_counts": { - "in_progress": 0, - "completed": 3, - "failed": 0, - "cancelled": 0, - "total": 3 - } - } + data: + {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"","output":null}}]}}} - delete: - operationId: deleteVectorStore - tags: - - Vector Stores - summary: Delete a vector store. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - description: The ID of the vector store to delete. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/DeleteVectorStoreResponse" - x-oaiMeta: - name: Delete vector store - group: vector_stores - beta: true - returns: Deletion status - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -X DELETE - python: | - from openai import OpenAI - client = OpenAI() - - deleted_vector_store = client.beta.vector_stores.delete( - vector_store_id="vs_abc123" - ) - print(deleted_vector_store) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const deletedVectorStore = await openai.beta.vectorStores.del( - "vs_abc123" - ); - console.log(deletedVectorStore); - } - main(); - response: | - { - id: "vs_abc123", - object: "vector_store.deleted", - deleted: true - } + event: thread.run.step.delta - /vector_stores/{vector_store_id}/files: - get: - operationId: listVectorStoreFiles - tags: - - Vector Stores - summary: Returns a list of vector store files. - parameters: - - name: vector_store_id - in: path - description: The ID of the vector store that the files belong to. - required: true - schema: - type: string - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string - - name: filter - in: query - description: "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`." - schema: - type: string - enum: ["in_progress", "completed", "failed", "cancelled"] - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListVectorStoreFilesResponse" - x-oaiMeta: - name: List vector store files - group: vector_stores - beta: true - returns: A list of [vector store file](/docs/api-reference/vector-stores-files/file-object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - vector_store_files = client.beta.vector_stores.files.list( - vector_store_id="vs_abc123" - ) - print(vector_store_files) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStoreFiles = await openai.beta.vectorStores.files.list( - "vs_abc123" - ); - console.log(vectorStoreFiles); - } + data: + {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]}}} - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "file-abc123", - "object": "vector_store.file", - "created_at": 1699061776, - "vector_store_id": "vs_abc123" - }, - { - "id": "file-abc456", - "object": "vector_store.file", - "created_at": 1699061776, - "vector_store_id": "vs_abc123" - } - ], - "first_id": "file-abc123", - "last_id": "file-abc456", - "has_more": false - } - post: - operationId: createVectorStoreFile - tags: - - Vector Stores - summary: Create a vector store file by attaching a [File](/docs/api-reference/files) to a [vector store](/docs/api-reference/vector-stores/object). - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - example: vs_abc123 - description: | - The ID of the vector store for which to create a File. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateVectorStoreFileRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreFileObject" - x-oaiMeta: - name: Create vector store file - group: vector_stores - beta: true - returns: A [vector store file](/docs/api-reference/vector-stores-files/file-object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "file_id": "file-abc123" - }' - python: | - from openai import OpenAI - client = OpenAI() - - vector_store_file = client.beta.vector_stores.files.create( - vector_store_id="vs_abc123", - file_id="file-abc123" - ) - print(vector_store_file) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const myVectorStoreFile = await openai.beta.vectorStores.files.create( - "vs_abc123", - { - file_id: "file-abc123" - } - ); - console.log(myVectorStoreFile); - } - main(); - response: | - { - "id": "file-abc123", - "object": "vector_store.file", - "created_at": 1699061776, - "usage_bytes": 1234, - "vector_store_id": "vs_abcd", - "status": "completed", - "last_error": null - } + event: thread.run.step.delta - /vector_stores/{vector_store_id}/files/{file_id}: - get: - operationId: getVectorStoreFile - tags: - - Vector Stores - summary: Retrieves a vector store file. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - example: vs_abc123 - description: The ID of the vector store that the file belongs to. - - in: path - name: file_id - required: true - schema: - type: string - example: file-abc123 - description: The ID of the file being retrieved. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreFileObject" - x-oaiMeta: - name: Retrieve vector store file - group: vector_stores - beta: true - returns: The [vector store file](/docs/api-reference/vector-stores-files/file-object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - vector_store_file = client.beta.vector_stores.files.retrieve( - vector_store_id="vs_abc123", - file_id="file-abc123" - ) - print(vector_store_file) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStoreFile = await openai.beta.vectorStores.files.retrieve( - "vs_abc123", - "file-abc123" - ); - console.log(vectorStoreFile); - } + data: + {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"location"}}]}}} - main(); - response: | - { - "id": "file-abc123", - "object": "vector_store.file", - "created_at": 1699061776, - "vector_store_id": "vs_abcd", - "status": "completed", - "last_error": null - } - delete: - operationId: deleteVectorStoreFile - tags: - - Vector Stores - summary: Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](/docs/api-reference/files/delete) endpoint. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - description: The ID of the vector store that the file belongs to. - - in: path - name: file_id - required: true - schema: - type: string - description: The ID of the file to delete. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/DeleteVectorStoreFileResponse" - x-oaiMeta: - name: Delete vector store file - group: vector_stores - beta: true - returns: Deletion status - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -X DELETE - python: | - from openai import OpenAI - client = OpenAI() - - deleted_vector_store_file = client.beta.vector_stores.files.delete( - vector_store_id="vs_abc123", - file_id="file-abc123" - ) - print(deleted_vector_store_file) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const deletedVectorStoreFile = await openai.beta.vectorStores.files.del( - "vs_abc123", - "file-abc123" - ); - console.log(deletedVectorStoreFile); - } - main(); - response: | - { - id: "file-abc123", - object: "vector_store.file.deleted", - deleted: true - } + ... - /vector_stores/{vector_store_id}/file_batches: - post: - operationId: createVectorStoreFileBatch - tags: - - Vector Stores - summary: Create a vector store file batch. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - example: vs_abc123 - description: | - The ID of the vector store for which to create a File Batch. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateVectorStoreFileBatchRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreFileBatchObject" - x-oaiMeta: - name: Create vector store file batch - group: vector_stores - beta: true - returns: A [vector store file batch](/docs/api-reference/vector-stores-file-batches/batch-object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/file_batches \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json \ - -H "OpenAI-Beta: assistants=v2" \ - -d '{ - "file_ids": ["file-abc123", "file-abc456"] - }' - python: | - from openai import OpenAI - client = OpenAI() - - vector_store_file_batch = client.beta.vector_stores.file_batches.create( - vector_store_id="vs_abc123", - file_ids=["file-abc123", "file-abc456"] - ) - print(vector_store_file_batch) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const myVectorStoreFileBatch = await openai.beta.vectorStores.fileBatches.create( - "vs_abc123", - { - file_ids: ["file-abc123", "file-abc456"] - } - ); - console.log(myVectorStoreFileBatch); - } - main(); - response: | - { - "id": "vsfb_abc123", - "object": "vector_store.file_batch", - "created_at": 1699061776, - "vector_store_id": "vs_abc123", - "status": "in_progress", - "file_counts": { - "in_progress": 1, - "completed": 1, - "failed": 0, - "cancelled": 0, - "total": 0, - } - } + event: thread.run.step.delta - /vector_stores/{vector_store_id}/file_batches/{batch_id}: - get: - operationId: getVectorStoreFileBatch - tags: - - Vector Stores - summary: Retrieves a vector store file batch. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - example: vs_abc123 - description: The ID of the vector store that the file batch belongs to. - - in: path - name: batch_id - required: true - schema: - type: string - example: vsfb_abc123 - description: The ID of the file batch being retrieved. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreFileBatchObject" - x-oaiMeta: - name: Retrieve vector store file batch - group: vector_stores - beta: true - returns: The [vector store file batch](/docs/api-reference/vector-stores-file-batches/batch-object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - vector_store_file_batch = client.beta.vector_stores.file_batches.retrieve( - vector_store_id="vs_abc123", - batch_id="vsfb_abc123" - ) - print(vector_store_file_batch) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStoreFileBatch = await openai.beta.vectorStores.fileBatches.retrieve( - "vs_abc123", - "vsfb_abc123" - ); - console.log(vectorStoreFileBatch); - } + data: + {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"ahrenheit"}}]}}} - main(); - response: | - { - "id": "vsfb_abc123", - "object": "vector_store.file_batch", - "created_at": 1699061776, - "vector_store_id": "vs_abc123", - "status": "in_progress", - "file_counts": { - "in_progress": 1, - "completed": 1, - "failed": 0, - "cancelled": 0, - "total": 0, - } - } - /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel: - post: - operationId: cancelVectorStoreFileBatch - tags: - - Vector Stores - summary: Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible. - parameters: - - in: path - name: vector_store_id - required: true - schema: - type: string - description: The ID of the vector store that the file batch belongs to. - - in: path - name: batch_id - required: true - schema: - type: string - description: The ID of the file batch to cancel. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/VectorStoreFileBatchObject" - x-oaiMeta: - name: Cancel vector store file batch - group: vector_stores - beta: true - returns: The modified vector store file batch object. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/cancel \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" \ - -X POST - python: | - from openai import OpenAI - client = OpenAI() - - deleted_vector_store_file_batch = client.beta.vector_stores.file_batches.cancel( - vector_store_id="vs_abc123", - file_batch_id="vsfb_abc123" - ) - print(deleted_vector_store_file_batch) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const deletedVectorStoreFileBatch = await openai.vector_stores.fileBatches.cancel( - "vs_abc123", - "vsfb_abc123" - ); - console.log(deletedVectorStoreFileBatch); - } + event: thread.run.step.delta - main(); - response: | - { - "id": "vsfb_abc123", - "object": "vector_store.file_batch", - "created_at": 1699061776, - "vector_store_id": "vs_abc123", - "status": "cancelling", - "file_counts": { - "in_progress": 12, - "completed": 3, - "failed": 0, - "cancelled": 0, - "total": 15, - } - } + data: + {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]}}} - /vector_stores/{vector_store_id}/file_batches/{batch_id}/files: - get: - operationId: listFilesInVectorStoreBatch - tags: - - Vector Stores - summary: Returns a list of vector store files in a batch. - parameters: - - name: vector_store_id - in: path - description: The ID of the vector store that the files belong to. - required: true - schema: - type: string - - name: batch_id - in: path - description: The ID of the file batch that the files belong to. - required: true - schema: - type: string - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string - - name: filter - in: query - description: "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`." - schema: - type: string - enum: ["in_progress", "completed", "failed", "cancelled"] - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListVectorStoreFilesResponse" - x-oaiMeta: - name: List vector store files in a batch - group: vector_stores - beta: true - returns: A list of [vector store file](/docs/api-reference/vector-stores-files/file-object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/files \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v2" - python: | - from openai import OpenAI - client = OpenAI() - - vector_store_files = client.beta.vector_stores.file_batches.list_files( - vector_store_id="vs_abc123", - batch_id="vsfb_abc123" - ) - print(vector_store_files) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const vectorStoreFiles = await openai.beta.vectorStores.fileBatches.listFiles( - "vs_abc123", - "vsfb_abc123" - ); - console.log(vectorStoreFiles); - } - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "file-abc123", - "object": "vector_store.file", - "created_at": 1699061776, - "vector_store_id": "vs_abc123" - }, - { - "id": "file-abc456", - "object": "vector_store.file", - "created_at": 1699061776, - "vector_store_id": "vs_abc123" - } - ], - "first_id": "file-abc123", - "last_id": "file-abc456", - "has_more": false - } + event: thread.run.requires_action - /batches: - post: - summary: Creates and executes a batch from an uploaded file of requests - operationId: createBatch - tags: - - Batch - requestBody: - required: true - content: - application/json: - schema: - type: object - required: - - input_file_id - - endpoint - - completion_window - properties: - input_file_id: - type: string - description: | - The ID of an uploaded file that contains requests for the new batch. - - See [upload file](/docs/api-reference/files/create) for how to upload a file. - - Your input file must be formatted as a [JSONL file](/docs/api-reference/batch/request-input), and must be uploaded with the purpose `batch`. The file can contain up to 50,000 requests, and can be up to 100 MB in size. - endpoint: - type: string - enum: - [ - "/v1/chat/completions", - "/v1/embeddings", - "/v1/completions", - ] - description: The endpoint to be used for all requests in the batch. Currently `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch. - completion_window: - type: string - enum: ["24h"] - description: The time frame within which the batch should be processed. Currently only `24h` is supported. - metadata: - type: object - additionalProperties: - type: string - description: Optional custom metadata for the batch. - nullable: true - responses: - "200": - description: Batch created successfully. - content: - application/json: - schema: - $ref: "#/components/schemas/Batch" - x-oaiMeta: - name: Create batch - group: batch - returns: The created [Batch](/docs/api-reference/batch/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/batches \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -d '{ - "input_file_id": "file-abc123", - "endpoint": "/v1/chat/completions", - "completion_window": "24h" - }' - python: | - from openai import OpenAI - client = OpenAI() - - client.batches.create( - input_file_id="file-abc123", - endpoint="/v1/chat/completions", - completion_window="24h" - ) - node: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const batch = await openai.batches.create({ - input_file_id: "file-abc123", - endpoint: "/v1/chat/completions", - completion_window: "24h" - }); - - console.log(batch); - } + data: + {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"requires_action","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":{"type":"submit_tool_outputs","submit_tool_outputs":{"tool_calls":[{"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San + Francisco, + CA\",\"unit\":\"fahrenheit\"}"}}]}},"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get + the current weather in a given + location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The + city and state, e.g. San Francisco, + CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - main(); - response: | - { - "id": "batch_abc123", - "object": "batch", - "endpoint": "/v1/chat/completions", - "errors": null, - "input_file_id": "file-abc123", - "completion_window": "24h", - "status": "validating", - "output_file_id": null, - "error_file_id": null, - "created_at": 1711471533, - "in_progress_at": null, - "expires_at": null, - "finalizing_at": null, - "completed_at": null, - "failed_at": null, - "expired_at": null, - "cancelling_at": null, - "cancelled_at": null, - "request_counts": { - "total": 0, - "completed": 0, - "failed": 0 - }, - "metadata": { - "customer_id": "user_123456789", - "batch_description": "Nightly eval job", - } - } - get: - operationId: listBatches - tags: - - Batch - summary: List your organization's batches. - parameters: - - in: query - name: after - required: false - schema: - type: string - description: *pagination_after_param_description - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - responses: - "200": - description: Batch listed successfully. - content: - application/json: - schema: - $ref: "#/components/schemas/ListBatchesResponse" - x-oaiMeta: - name: List batch - group: batch - returns: A list of paginated [Batch](/docs/api-reference/batch/object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/batches?limit=2 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" - python: | - from openai import OpenAI - client = OpenAI() - - client.batches.list() - node: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const list = await openai.batches.list(); - - for await (const batch of list) { - console.log(batch); - } - } - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "batch_abc123", - "object": "batch", - "endpoint": "/v1/chat/completions", - "errors": null, - "input_file_id": "file-abc123", - "completion_window": "24h", - "status": "completed", - "output_file_id": "file-cvaTdG", - "error_file_id": "file-HOWS94", - "created_at": 1711471533, - "in_progress_at": 1711471538, - "expires_at": 1711557933, - "finalizing_at": 1711493133, - "completed_at": 1711493163, - "failed_at": null, - "expired_at": null, - "cancelling_at": null, - "cancelled_at": null, - "request_counts": { - "total": 100, - "completed": 95, - "failed": 5 - }, - "metadata": { - "customer_id": "user_123456789", - "batch_description": "Nightly job", - } - }, - { ... }, - ], - "first_id": "batch_abc123", - "last_id": "batch_abc456", - "has_more": true - } + event: done - /batches/{batch_id}: - get: - operationId: retrieveBatch - tags: - - Batch - summary: Retrieves a batch. - parameters: - - in: path - name: batch_id - required: true - schema: - type: string - description: The ID of the batch to retrieve. - responses: - "200": - description: Batch retrieved successfully. - content: - application/json: - schema: - $ref: "#/components/schemas/Batch" - x-oaiMeta: - name: Retrieve batch - group: batch - returns: The [Batch](/docs/api-reference/batch/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/batches/batch_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - python: | - from openai import OpenAI - client = OpenAI() - - client.batches.retrieve("batch_abc123") - node: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const batch = await openai.batches.retrieve("batch_abc123"); - - console.log(batch); - } + data: [DONE] + /threads/{thread_id}: + get: + operationId: getThread + tags: + - Assistants + summary: Retrieves a thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ThreadObject" + x-oaiMeta: + name: Retrieve thread + group: threads + beta: true + returns: The [thread](/docs/api-reference/threads/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + my_thread = client.beta.threads.retrieve("thread_abc123") + print(my_thread) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const myThread = await openai.beta.threads.retrieve( + "thread_abc123" + ); + + console.log(myThread); + } + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "metadata": {}, + "tool_resources": { + "code_interpreter": { + "file_ids": [] + } + } + } + post: + operationId: modifyThread + tags: + - Assistants + summary: Modifies a thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to modify. Only the `metadata` can be modified. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyThreadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ThreadObject" + x-oaiMeta: + name: Modify thread + group: threads + beta: true + returns: The modified [thread](/docs/api-reference/threads/object) object + matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "metadata": { + "modified": "true", + "user": "abc123" + } + }' + python: | + from openai import OpenAI + client = OpenAI() + + my_updated_thread = client.beta.threads.update( + "thread_abc123", + metadata={ + "modified": "true", + "user": "abc123" + } + ) + print(my_updated_thread) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const updatedThread = await openai.beta.threads.update( + "thread_abc123", + { + metadata: { modified: "true", user: "abc123" }, + } + ); + + console.log(updatedThread); + } + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "metadata": { + "modified": "true", + "user": "abc123" + }, + "tool_resources": {} + } + delete: + operationId: deleteThread + tags: + - Assistants + summary: Delete a thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteThreadResponse" + x-oaiMeta: + name: Delete thread + group: threads + beta: true + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + response = client.beta.threads.delete("thread_abc123") + print(response) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const response = await openai.beta.threads.del("thread_abc123"); + + console.log(response); + } + main(); + response: | + { + "id": "thread_abc123", + "object": "thread.deleted", + "deleted": true + } + /threads/{thread_id}/messages: + get: + operationId: listMessages + tags: + - Assistants + summary: Returns a list of messages for a given thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) the messages + belong to. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: run_id + in: query + description: | + Filter messages by the run ID that generated them. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListMessagesResponse" + x-oaiMeta: + name: List messages + group: threads + beta: true + returns: A list of [message](/docs/api-reference/messages) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/messages \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: > + from openai import OpenAI + + client = OpenAI() + + + thread_messages = + client.beta.threads.messages.list("thread_abc123") + + print(thread_messages.data) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const threadMessages = await openai.beta.threads.messages.list( + "thread_abc123" + ); + + console.log(threadMessages.data); + } + + main(); + response: > + { + "object": "list", + "data": [ + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1699016383, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + }, + { + "id": "msg_abc456", + "object": "thread.message", + "created_at": 1699016383, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "Hello, what is AI?", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + } + ], + "first_id": "msg_abc123", + "last_id": "msg_abc456", + "has_more": false + } + post: + operationId: createMessage + tags: + - Assistants + summary: Create a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) to create a + message for. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateMessageRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/MessageObject" + x-oaiMeta: + name: Create message + group: threads + beta: true + returns: A [message](/docs/api-reference/messages/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/messages \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }' + python: | + from openai import OpenAI + client = OpenAI() + + thread_message = client.beta.threads.messages.create( + "thread_abc123", + role="user", + content="How does AI work? Explain it in simple terms.", + ) + print(thread_message) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const threadMessages = await openai.beta.threads.messages.create( + "thread_abc123", + { role: "user", content: "How does AI work? Explain it in simple terms." } + ); + + console.log(threadMessages); + } + + + main(); + response: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1713226573, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + } + /threads/{thread_id}/messages/{message_id}: + get: + operationId: getMessage + tags: + - Assistants + summary: Retrieve a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) to which this + message belongs. + - in: path + name: message_id + required: true + schema: + type: string + description: The ID of the message to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/MessageObject" + x-oaiMeta: + name: Retrieve message + group: threads + beta: true + returns: The [message](/docs/api-reference/messages/object) object matching the + specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 + \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + message = client.beta.threads.messages.retrieve( + message_id="msg_abc123", + thread_id="thread_abc123", + ) + print(message) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const message = await openai.beta.threads.messages.retrieve( + "thread_abc123", + "msg_abc123" + ); + + console.log(message); + } + + main(); + response: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1699017614, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + } + post: + operationId: modifyMessage + tags: + - Assistants + summary: Modifies a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which this message belongs. + - in: path + name: message_id + required: true + schema: + type: string + description: The ID of the message to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyMessageRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/MessageObject" + x-oaiMeta: + name: Modify message + group: threads + beta: true + returns: The modified [message](/docs/api-reference/messages/object) object. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 + \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "metadata": { + "modified": "true", + "user": "abc123" + } + }' + python: | + from openai import OpenAI + client = OpenAI() + + message = client.beta.threads.messages.update( + message_id="msg_abc12", + thread_id="thread_abc123", + metadata={ + "modified": "true", + "user": "abc123", + }, + ) + print(message) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const message = await openai.beta.threads.messages.update( + "thread_abc123", + "msg_abc123", + { + metadata: { + modified: "true", + user: "abc123", + }, + } + }' + response: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1699017614, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "file_ids": [], + "metadata": { + "modified": "true", + "user": "abc123" + } + } + delete: + operationId: deleteMessage + tags: + - Assistants + summary: Deletes a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which this message belongs. + - in: path + name: message_id + required: true + schema: + type: string + description: The ID of the message to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteMessageResponse" + x-oaiMeta: + name: Delete message + group: threads + beta: true + returns: Deletion status + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 + \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + deleted_message = client.beta.threads.messages.delete( + message_id="msg_abc12", + thread_id="thread_abc123", + ) + print(deleted_message) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const deletedMessage = await openai.beta.threads.messages.del( + "thread_abc123", + "msg_abc123" + ); + + console.log(deletedMessage); + } + response: | + { + "id": "msg_abc123", + "object": "thread.message.deleted", + "deleted": true + } + /threads/{thread_id}/runs: + get: + operationId: listRuns + tags: + - Assistants + summary: Returns a list of runs belonging to a thread. + parameters: + - name: thread_id + in: path + required: true + schema: + type: string + description: The ID of the thread the run belongs to. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListRunsResponse" + x-oaiMeta: + name: List runs + group: threads + beta: true + returns: A list of [run](/docs/api-reference/runs/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + runs = client.beta.threads.runs.list( + "thread_abc123" + ) + + print(runs) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const runs = await openai.beta.threads.runs.list( + "thread_abc123" + ); + + console.log(runs); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699075072, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699075073, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + }, + { + "id": "run_abc456", + "object": "thread.run", + "created_at": 1699063290, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699063290, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699063291, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + ], + "first_id": "run_abc123", + "last_id": "run_abc456", + "has_more": false + } + post: + operationId: createRun + tags: + - Assistants + summary: Create a run. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to run. + - name: include[] + in: query + description: > + A list of additional fields to include in the response. Currently + the only supported value is + `step_details.tool_calls[*].file_search.results[*].content` to fetch + the file search result content. + + + See the [file search tool + documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) + for more information. + schema: + type: array + items: + type: string + enum: + - step_details.tool_calls[*].file_search.results[*].content + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Create run + group: threads + beta: true + returns: A [run](/docs/api-reference/runs/object) object. + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123" + }' + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.create( + thread_id="thread_abc123", + assistant_id="asst_abc123" + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.create( + "thread_abc123", + { assistant_id: "asst_abc123" } + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699063290, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "queued", + "started_at": 1699063290, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699063291, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/thread_123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_123", + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + stream = client.beta.threads.runs.create( + thread_id="thread_123", + assistant_id="asst_123", + stream=True + ) + + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const stream = await openai.beta.threads.runs.create( + "thread_123", + { assistant_id: "asst_123", stream: true } + ); + + for await (const event of stream) { + console.log(event); + } + } - main(); - response: &batch_object | - { - "id": "batch_abc123", - "object": "batch", - "endpoint": "/v1/completions", - "errors": null, - "input_file_id": "file-abc123", - "completion_window": "24h", - "status": "completed", - "output_file_id": "file-cvaTdG", - "error_file_id": "file-HOWS94", - "created_at": 1711471533, - "in_progress_at": 1711471538, - "expires_at": 1711557933, - "finalizing_at": 1711493133, - "completed_at": 1711493163, - "failed_at": null, - "expired_at": null, - "cancelling_at": null, - "cancelled_at": null, - "request_counts": { - "total": 100, - "completed": 95, - "failed": 5 - }, - "metadata": { - "customer_id": "user_123456789", - "batch_description": "Nightly eval job", - } - } + main(); + response: > + event: thread.run.created - /batches/{batch_id}/cancel: - post: - operationId: cancelBatch - tags: - - Batch - summary: Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to `cancelled`, where it will have partial results (if any) available in the output file. - parameters: - - in: path - name: batch_id - required: true - schema: - type: string - description: The ID of the batch to cancel. - responses: - "200": - description: Batch is cancelling. Returns the cancelling batch's details. - content: - application/json: - schema: - $ref: "#/components/schemas/Batch" - x-oaiMeta: - name: Cancel batch - group: batch - returns: The [Batch](/docs/api-reference/batch/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/batches/batch_abc123/cancel \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -X POST - python: | - from openai import OpenAI - client = OpenAI() - - client.batches.cancel("batch_abc123") - node: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const batch = await openai.batches.cancel("batch_abc123"); - - console.log(batch); - } + data: + {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - main(); - response: | - { - "id": "batch_abc123", - "object": "batch", - "endpoint": "/v1/chat/completions", - "errors": null, - "input_file_id": "file-abc123", - "completion_window": "24h", - "status": "cancelling", - "output_file_id": null, - "error_file_id": null, - "created_at": 1711471533, - "in_progress_at": 1711471538, - "expires_at": 1711557933, - "finalizing_at": null, - "completed_at": null, - "failed_at": null, - "expired_at": null, - "cancelling_at": 1711475133, - "cancelled_at": null, - "request_counts": { - "total": 100, - "completed": 23, - "failed": 1 - }, - "metadata": { - "customer_id": "user_123456789", - "batch_description": "Nightly eval job", - } - } -components: - securitySchemes: - ApiKeyAuth: - type: http - scheme: "bearer" + event: thread.run.queued - schemas: - Error: - type: object - properties: - code: - type: string - nullable: true - message: - type: string - nullable: false - param: - type: string - nullable: true - type: - type: string - nullable: false - required: - - type - - message - - param - - code - ErrorResponse: - type: object - properties: - error: - $ref: "#/components/schemas/Error" - required: - - error + data: + {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - ListModelsResponse: - type: object - properties: - object: - type: string - enum: [list] - data: - type: array - items: - $ref: "#/components/schemas/Model" - required: - - object - - data - DeleteModelResponse: - type: object - properties: - id: - type: string - deleted: - type: boolean - object: - type: string - required: - - id - - object - - deleted - CreateCompletionRequest: - type: object - properties: - model: - description: &model_description | - ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them. - anyOf: - - type: string - - type: string - enum: ["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"] - x-oaiTypeLabel: string - prompt: - description: &completions_prompt_description | - The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. - - Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. - default: "<|endoftext|>" - nullable: true - oneOf: - - type: string - default: "" - example: "This is a test." - - type: array - items: - type: string - default: "" - example: "This is a test." - - type: array - minItems: 1 - items: - type: integer - example: "[1212, 318, 257, 1332, 13]" - - type: array - minItems: 1 - items: - type: array - minItems: 1 - items: - type: integer - example: "[[1212, 318, 257, 1332, 13]]" - best_of: - type: integer - default: 1 - minimum: 0 - maximum: 20 - nullable: true - description: &completions_best_of_description | - Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. + event: thread.run.in_progress - When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`. + data: + {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710330641,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. - echo: - type: boolean - default: false - nullable: true - description: &completions_echo_description > - Echo back the prompt in addition to the completion - frequency_penalty: - type: number - default: 0 - minimum: -2 - maximum: 2 - nullable: true - description: &completions_frequency_penalty_description | - Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) - logit_bias: &completions_logit_bias - type: object - x-oaiTypeLabel: map - # default: null - nullable: true - additionalProperties: - type: integer - description: &completions_logit_bias_description | - Modify the likelihood of specified tokens appearing in the completion. + event: thread.run.step.created - Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. + data: + {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. - logprobs: &completions_logprobs_configuration - type: integer - minimum: 0 - maximum: 5 - # default: null - nullable: true - description: &completions_logprobs_description | - Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. - The maximum value for `logprobs` is 5. - max_tokens: - type: integer - minimum: 0 - default: 16 - example: 16 - nullable: true - description: &completions_max_tokens_description | - The maximum number of [tokens](/tokenizer) that can be generated in the completion. + event: thread.run.step.in_progress - The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. - n: - type: integer - minimum: 1 - maximum: 128 - default: 1 - example: 1 - nullable: true - description: &completions_completions_description | - How many completions to generate for each prompt. + data: + {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. - presence_penalty: - type: number - default: 0 - minimum: -2 - maximum: 2 - nullable: true - description: &completions_presence_penalty_description | - Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) - seed: &completions_seed_param - type: integer - minimum: -9223372036854775808 - maximum: 9223372036854775807 - nullable: true - description: | - If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. - - Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. - stop: - description: &completions_stop_description > - Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. - # default: null - nullable: true - oneOf: - - type: string - default: <|endoftext|> - example: "\n" - nullable: true - - type: array - minItems: 1 - maxItems: 4 - items: - type: string - example: '["\n"]' - stream: - description: > - Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) - as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). - type: boolean - nullable: true - default: false - stream_options: - $ref: "#/components/schemas/ChatCompletionStreamOptions" - suffix: - description: | - The suffix that comes after a completion of inserted text. - - This parameter is only supported for `gpt-3.5-turbo-instruct`. - # default: null - nullable: true - type: string - example: "test." - temperature: - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - description: &completions_temperature_description | - What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + event: thread.message.created - We generally recommend altering this or `top_p` but not both. - top_p: - type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: &completions_top_p_description | - An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + data: + {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - We generally recommend altering this or `temperature` but not both. - user: &end_user_param_configuration - type: string - example: user-1234 - description: | - A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids). - required: - - model - - prompt - CreateCompletionResponse: - type: object - description: | - Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint). - properties: - id: - type: string - description: A unique identifier for the completion. - choices: - type: array - description: The list of completion choices the model generated for the input prompt. - items: - type: object - required: - - finish_reason - - index - - logprobs - - text - properties: - finish_reason: - type: string - description: &completion_finish_reason_description | - The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, - `length` if the maximum number of tokens specified in the request was reached, - or `content_filter` if content was omitted due to a flag from our content filters. - enum: ["stop", "length", "content_filter"] - index: - type: integer - logprobs: - type: object - nullable: true - properties: - text_offset: - type: array - items: - type: integer - token_logprobs: - type: array - items: - type: number - tokens: - type: array - items: - type: string - top_logprobs: - type: array - items: - type: object - additionalProperties: - type: number - text: - type: string - created: - type: integer - description: The Unix timestamp (in seconds) of when the completion was created. - model: - type: string - description: The model used for completion. - system_fingerprint: - type: string - description: | - This fingerprint represents the backend configuration that the model runs with. + event: thread.message.in_progress - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. - object: - type: string - description: The object type, which is always "text_completion" - enum: [text_completion] - usage: - $ref: "#/components/schemas/CompletionUsage" - required: - - id - - object - - created - - model - - choices - x-oaiMeta: - name: The completion object - legacy: true - example: | - { - "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", - "object": "text_completion", - "created": 1589478378, - "model": "gpt-4-turbo", - "choices": [ - { - "text": "\n\nThis is indeed a test", - "index": 0, - "logprobs": null, - "finish_reason": "length" - } - ], - "usage": { - "prompt_tokens": 5, - "completion_tokens": 7, - "total_tokens": 12 - } - } + data: + {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - ChatCompletionRequestMessageContentPart: - oneOf: - - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" - - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartImage" - x-oaiExpandable: true - ChatCompletionRequestMessageContentPartImage: - type: object - title: Image content part - properties: - type: - type: string - enum: ["image_url"] - description: The type of the content part. - image_url: - type: object - properties: - url: - type: string - description: Either a URL of the image or the base64 encoded image data. - format: uri - detail: - type: string - description: Specifies the detail level of the image. Learn more in the [Vision guide](/docs/guides/vision/low-or-high-fidelity-image-understanding). - enum: ["auto", "low", "high"] - default: "auto" - required: - - url - required: - - type - - image_url + event: thread.message.delta - ChatCompletionRequestMessageContentPartText: - type: object - title: Text content part - properties: - type: - type: string - enum: ["text"] - description: The type of the content part. - text: - type: string - description: The text content. - required: - - type - - text + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} - ChatCompletionRequestMessage: - oneOf: - - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" - - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" - - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" - - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" - - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" - x-oaiExpandable: true - ChatCompletionRequestSystemMessage: - type: object - title: System message - properties: - content: - description: The contents of the system message. - type: string - role: - type: string - enum: ["system"] - description: The role of the messages author, in this case `system`. - name: - type: string - description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. - required: - - content - - role + ... - ChatCompletionRequestUserMessage: - type: object - title: User message - properties: - content: - description: | - The contents of the user message. - oneOf: - - type: string - description: The text contents of the message. - title: Text content - - type: array - description: An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4o` model. - title: Array of content parts - items: - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPart" - minItems: 1 - x-oaiExpandable: true - role: - type: string - enum: ["user"] - description: The role of the messages author, in this case `user`. - name: - type: string - description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. - required: - - content - - role - ChatCompletionRequestAssistantMessage: - type: object - title: Assistant message - properties: - content: - nullable: true - type: string - description: | - The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. - role: - type: string - enum: ["assistant"] - description: The role of the messages author, in this case `assistant`. - name: - type: string - description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. - tool_calls: - $ref: "#/components/schemas/ChatCompletionMessageToolCalls" - function_call: - type: object - deprecated: true - description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." - nullable: true - properties: - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - name: - type: string - description: The name of the function to call. - required: - - arguments - - name - required: - - role - - FineTuneChatCompletionRequestAssistantMessage: - allOf: - - type: object - title: Assistant message - deprecated: false - properties: - weight: - type: integer - enum: [0, 1] - description: "Controls whether the assistant message is trained against (0 or 1)" - - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" - required: - - role + event: thread.message.delta - ChatCompletionRequestToolMessage: - type: object - title: Tool message - properties: - role: - type: string - enum: ["tool"] - description: The role of the messages author, in this case `tool`. - content: - type: string - description: The contents of the tool message. - tool_call_id: - type: string - description: Tool call that this message is responding to. - required: - - role - - content - - tool_call_id + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" + today"}}]}} - ChatCompletionRequestFunctionMessage: - type: object - title: Function message - deprecated: true - properties: - role: - type: string - enum: ["function"] - description: The role of the messages author, in this case `function`. - content: - nullable: true - type: string - description: The contents of the function message. - name: - type: string - description: The name of the function to call. - required: - - role - - content - - name - FunctionParameters: - type: object - description: "The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. \n\nOmitting `parameters` defines a function with an empty parameter list." - additionalProperties: true + event: thread.message.delta - ChatCompletionFunctions: - type: object - deprecated: true - properties: - description: - type: string - description: A description of what the function does, used by the model to choose when and how to call the function. - name: - type: string - description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. - parameters: - $ref: "#/components/schemas/FunctionParameters" - required: - - name + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} - ChatCompletionFunctionCallOption: - type: object - description: > - Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. - properties: - name: - type: string - description: The name of the function to call. - required: - - name - ChatCompletionTool: - type: object - properties: - type: - type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - $ref: "#/components/schemas/FunctionObject" - required: - - type - - function + event: thread.message.completed - FunctionObject: - type: object - properties: - description: - type: string - description: A description of what the function does, used by the model to choose when and how to call the function. - name: - type: string - description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. - parameters: - $ref: "#/components/schemas/FunctionParameters" - required: - - name + data: + {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710330642,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! + How can I assist you today?","annotations":[]}}],"metadata":{}} - ChatCompletionToolChoiceOption: - description: | - Controls which (if any) tool is called by the model. - `none` means the model will not call any tool and instead generates a message. - `auto` means the model can pick between generating a message or calling one or more tools. - `required` means the model must call one or more tools. - Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. - `none` is the default when no tools are present. `auto` is the default if tools are present. - oneOf: - - type: string - description: > - `none` means the model will not call any tool and instead generates a message. - `auto` means the model can pick between generating a message or calling one or more tools. - `required` means the model must call one or more tools. - enum: [none, auto, required] - - $ref: "#/components/schemas/ChatCompletionNamedToolChoice" - x-oaiExpandable: true + event: thread.run.step.completed - ChatCompletionNamedToolChoice: - type: object - description: Specifies a tool the model should use. Use to force the model to call a specific function. - properties: - type: - type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - type: object - properties: - name: - type: string - description: The name of the function to call. - required: - - name - required: - - type - - function + data: + {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710330642,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} - ParallelToolCalls: - description: Whether to enable [parallel function calling](/docs/guides/function-calling/parallel-function-calling) during tool use. - type: boolean - default: true - ChatCompletionMessageToolCalls: - type: array - description: The tool calls generated by the model, such as function calls. - items: - $ref: "#/components/schemas/ChatCompletionMessageToolCall" + event: thread.run.completed - ChatCompletionMessageToolCall: - type: object - properties: - # TODO: index included when streaming - id: - type: string - description: The ID of the tool call. - type: - type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - type: object - description: The function that the model called. - properties: - name: - type: string - description: The name of the function to call. - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - required: - - name - - arguments - required: - - id - - type - - function + data: + {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710330641,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710330642,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - ChatCompletionMessageToolCallChunk: - type: object - properties: - index: - type: integer - id: - type: string - description: The ID of the tool call. - type: - type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - type: object - properties: - name: - type: string - description: The name of the function to call. - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - required: - - index - # Note, this isn't referenced anywhere, but is kept as a convenience to record all possible roles in one place. - ChatCompletionRole: - type: string - description: The role of the author of a message - enum: - - system - - user - - assistant - - tool - - function + event: done - ChatCompletionStreamOptions: - description: | - Options for streaming response. Only set this when you set `stream: true`. - type: object - nullable: true - # default: null - properties: - include_usage: - type: boolean - description: | - If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value. + data: [DONE] + - title: Streaming with Functions + request: + curl: > + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } + } + ], + "stream": true + }' + python: > + from openai import OpenAI - ChatCompletionResponseMessage: - type: object - description: A chat completion message generated by the model. - properties: - content: - type: string - description: The contents of the message. - nullable: true - tool_calls: - $ref: "#/components/schemas/ChatCompletionMessageToolCalls" - role: - type: string - enum: ["assistant"] - description: The role of the author of this message. - function_call: - type: object - deprecated: true - description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." - properties: - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - name: - type: string - description: The name of the function to call. - required: - - name - - arguments - required: - - role - - content + client = OpenAI() - ChatCompletionStreamResponseDelta: - type: object - description: A chat completion delta generated by streamed model responses. - properties: - content: - type: string - description: The contents of the chunk message. - nullable: true - function_call: - deprecated: true - type: object - description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." - properties: - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - name: - type: string - description: The name of the function to call. - tool_calls: - type: array - items: - $ref: "#/components/schemas/ChatCompletionMessageToolCallChunk" - role: - type: string - enum: ["system", "user", "assistant", "tool"] - description: The role of the author of this message. - CreateChatCompletionRequest: - type: object - properties: - messages: - description: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). - type: array - minItems: 1 - items: - $ref: "#/components/schemas/ChatCompletionRequestMessage" - model: - description: ID of the model to use. See the [model endpoint compatibility](/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. - example: "gpt-4-turbo" - anyOf: - - type: string - - type: string - enum: - [ - "gpt-4o", - "gpt-4o-2024-05-13", - "gpt-4o-mini", - "gpt-4o-mini-2024-07-18", - "gpt-4-turbo", - "gpt-4-turbo-2024-04-09", - "gpt-4-0125-preview", - "gpt-4-turbo-preview", - "gpt-4-1106-preview", - "gpt-4-vision-preview", - "gpt-4", - "gpt-4-0314", - "gpt-4-0613", - "gpt-4-32k", - "gpt-4-32k-0314", - "gpt-4-32k-0613", - "gpt-3.5-turbo", - "gpt-3.5-turbo-16k", - "gpt-3.5-turbo-0301", - "gpt-3.5-turbo-0613", - "gpt-3.5-turbo-1106", - "gpt-3.5-turbo-0125", - "gpt-3.5-turbo-16k-0613", - ] - x-oaiTypeLabel: string - frequency_penalty: - type: number - default: 0 - minimum: -2 - maximum: 2 - nullable: true - description: *completions_frequency_penalty_description - logit_bias: - type: object - x-oaiTypeLabel: map - # default: null - nullable: true - additionalProperties: - type: integer - description: | - Modify the likelihood of specified tokens appearing in the completion. - - Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. - logprobs: - description: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. - type: boolean - default: false - nullable: true - top_logprobs: - description: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. - type: integer - minimum: 0 - maximum: 20 - nullable: true - max_tokens: - description: | - The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ] - The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. - type: integer - nullable: true - n: - type: integer - minimum: 1 - maximum: 128 - default: 1 - example: 1 - nullable: true - description: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. - presence_penalty: - type: number - default: 0 - minimum: -2 - maximum: 2 - nullable: true - description: *completions_presence_penalty_description - response_format: - type: object - description: | - An object specifying the format that the model must output. Compatible with [GPT-4 Turbo](/docs/models/gpt-4-and-gpt-4-turbo) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. - Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. + stream = client.beta.threads.runs.create( + thread_id="thread_abc123", + assistant_id="asst_abc123", + tools=tools, + stream=True + ) - **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. - properties: - type: - type: string - enum: ["text", "json_object"] - example: "json_object" - default: "text" - description: Must be one of `text` or `json_object`. - seed: - type: integer - minimum: -9223372036854775808 - maximum: 9223372036854775807 - nullable: true - description: | - This feature is in Beta. - If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. - Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. - x-oaiMeta: - beta: true - service_tier: - description: | - Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - - If set to 'auto', the system will utilize scale tier credits until they are exhausted. - - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - - When not set, the default behavior is 'auto'. - - When this parameter is set, the response body will include the `service_tier` utilized. - type: string - enum: ["auto", "default"] - nullable: true - # default: null - stop: - description: | - Up to 4 sequences where the API will stop generating further tokens. - # default: null - oneOf: - - type: string - nullable: true - - type: array - minItems: 1 - maxItems: 4 - items: - type: string - stream: - description: > - If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) - as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). - type: boolean - nullable: true - default: false - stream_options: - $ref: "#/components/schemas/ChatCompletionStreamOptions" - temperature: - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - description: *completions_temperature_description - top_p: - type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: *completions_top_p_description - tools: - type: array - description: > - A list of tools the model may call. Currently, only functions are supported as a tool. - Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. - items: - $ref: "#/components/schemas/ChatCompletionTool" - tool_choice: - $ref: "#/components/schemas/ChatCompletionToolChoiceOption" - parallel_tool_calls: - $ref: "#/components/schemas/ParallelToolCalls" - user: *end_user_param_configuration - function_call: - deprecated: true - description: | - Deprecated in favor of `tool_choice`. - - Controls which (if any) function is called by the model. - `none` means the model will not call a function and instead generates a message. - `auto` means the model can pick between generating a message or calling a function. - Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. - - `none` is the default when no functions are present. `auto` is the default if functions are present. - oneOf: - - type: string - description: > - `none` means the model will not call a function and instead generates a message. - `auto` means the model can pick between generating a message or calling a function. - enum: [none, auto] - - $ref: "#/components/schemas/ChatCompletionFunctionCallOption" - x-oaiExpandable: true - functions: - deprecated: true - description: | - Deprecated in favor of `tools`. - A list of functions the model may generate JSON inputs for. - type: array - minItems: 1 - maxItems: 128 - items: - $ref: "#/components/schemas/ChatCompletionFunctions" + for event in stream: + print(event) + node.js: > + import OpenAI from "openai"; - required: - - model - - messages - CreateChatCompletionResponse: - type: object - description: Represents a chat completion response returned by model, based on the provided input. - properties: - id: - type: string - description: A unique identifier for the chat completion. - choices: - type: array - description: A list of chat completion choices. Can be more than one if `n` is greater than 1. - items: - type: object - required: - - finish_reason - - index - - message - - logprobs - properties: - finish_reason: - type: string - description: &chat_completion_finish_reason_description | - The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, - `length` if the maximum number of tokens specified in the request was reached, - `content_filter` if content was omitted due to a flag from our content filters, - `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. - enum: - [ - "stop", - "length", - "tool_calls", - "content_filter", - "function_call", - ] - index: - type: integer - description: The index of the choice in the list of choices. - message: - $ref: "#/components/schemas/ChatCompletionResponseMessage" - logprobs: &chat_completion_response_logprobs - description: Log probability information for the choice. - type: object - nullable: true - properties: - content: - description: A list of message content tokens with log probability information. - type: array - items: - $ref: "#/components/schemas/ChatCompletionTokenLogprob" - nullable: true - required: - - content - created: - type: integer - description: The Unix timestamp (in seconds) of when the chat completion was created. - model: - type: string - description: The model used for the chat completion. - service_tier: - description: The service tier used for processing the request. This field is only included if the `service_tier` parameter is specified in the request. - type: string - enum: ["scale", "default"] - example: "scale" - nullable: true - system_fingerprint: - type: string - description: | - This fingerprint represents the backend configuration that the model runs with. + const openai = new OpenAI(); - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. - object: - type: string - description: The object type, which is always `chat.completion`. - enum: [chat.completion] - usage: - $ref: "#/components/schemas/CompletionUsage" - required: - - choices - - created - - id - - model - - object - x-oaiMeta: - name: The chat completion object - group: chat - example: *chat_completion_example - CreateChatCompletionFunctionResponse: - type: object - description: Represents a chat completion response returned by model, based on the provided input. - properties: - id: - type: string - description: A unique identifier for the chat completion. - choices: - type: array - description: A list of chat completion choices. Can be more than one if `n` is greater than 1. - items: - type: object - required: - - finish_reason - - index - - message - - logprobs - properties: - finish_reason: - type: string - description: - &chat_completion_function_finish_reason_description | - The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, or `function_call` if the model called a function. - enum: - ["stop", "length", "function_call", "content_filter"] - index: - type: integer - description: The index of the choice in the list of choices. - message: - $ref: "#/components/schemas/ChatCompletionResponseMessage" - created: - type: integer - description: The Unix timestamp (in seconds) of when the chat completion was created. - model: - type: string - description: The model used for the chat completion. - system_fingerprint: - type: string - description: | - This fingerprint represents the backend configuration that the model runs with. + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. - object: - type: string - description: The object type, which is always `chat.completion`. - enum: [chat.completion] - usage: - $ref: "#/components/schemas/CompletionUsage" - required: - - choices - - created - - id - - model - - object - x-oaiMeta: - name: The chat completion object - group: chat - example: *chat_completion_function_example - ChatCompletionTokenLogprob: - type: object - properties: - token: &chat_completion_response_logprobs_token - description: The token. - type: string - logprob: &chat_completion_response_logprobs_token_logprob - description: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. - type: number - bytes: &chat_completion_response_logprobs_bytes - description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. - type: array - items: - type: integer - nullable: true - top_logprobs: - description: List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. - type: array - items: - type: object - properties: - token: *chat_completion_response_logprobs_token - logprob: *chat_completion_response_logprobs_token_logprob - bytes: *chat_completion_response_logprobs_bytes - required: - - token - - logprob - - bytes - required: - - token - - logprob - - bytes - - top_logprobs + async function main() { + const stream = await openai.beta.threads.runs.create( + "thread_abc123", + { + assistant_id: "asst_abc123", + tools: tools, + stream: true + } + ); - ListPaginatedFineTuningJobsResponse: - type: object - properties: - data: - type: array - items: - $ref: "#/components/schemas/FineTuningJob" - has_more: - type: boolean - object: - type: string - enum: [list] - required: - - object - - data - - has_more + for await (const event of stream) { + console.log(event); + } + } - CreateChatCompletionStreamResponse: - type: object - description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. - properties: - id: - type: string - description: A unique identifier for the chat completion. Each chunk has the same ID. - choices: - type: array - description: | - A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. Can also be empty for the - last chunk if you set `stream_options: {"include_usage": true}`. - items: - type: object - required: - - delta - - finish_reason - - index - properties: - delta: - $ref: "#/components/schemas/ChatCompletionStreamResponseDelta" - logprobs: *chat_completion_response_logprobs - finish_reason: - type: string - description: *chat_completion_finish_reason_description - enum: - [ - "stop", - "length", - "tool_calls", - "content_filter", - "function_call", - ] - nullable: true - index: - type: integer - description: The index of the choice in the list of choices. - created: - type: integer - description: The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. - model: - type: string - description: The model to generate the completion. - service_tier: - description: The service tier used for processing the request. This field is only included if the `service_tier` parameter is specified in the request. - type: string - enum: ["scale", "default"] - example: "scale" - nullable: true - system_fingerprint: - type: string - description: | - This fingerprint represents the backend configuration that the model runs with. - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. - object: - type: string - description: The object type, which is always `chat.completion.chunk`. - enum: [chat.completion.chunk] - usage: - type: object - description: | - An optional field that will only be present when you set `stream_options: {"include_usage": true}` in your request. - When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request. - properties: - completion_tokens: - type: integer - description: Number of tokens in the generated completion. - prompt_tokens: - type: integer - description: Number of tokens in the prompt. - total_tokens: - type: integer - description: Total number of tokens used in the request (prompt + completion). - required: - - prompt_tokens - - completion_tokens - - total_tokens - required: - - choices - - created - - id - - model - - object - x-oaiMeta: - name: The chat completion chunk object - group: chat - example: *chat_completion_chunk_example - CreateChatCompletionImageResponse: - type: object - description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. - x-oaiMeta: - name: The chat completion chunk object - group: chat - example: *chat_completion_image_example + main(); + response: > + event: thread.run.created - CreateImageRequest: - type: object - properties: - prompt: - description: A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`. - type: string - example: "A cute baby sea otter" - model: - anyOf: - - type: string - - type: string - enum: ["dall-e-2", "dall-e-3"] - x-oaiTypeLabel: string - default: "dall-e-2" - example: "dall-e-3" - nullable: true - description: The model to use for image generation. - n: &images_n - type: integer - minimum: 1 - maximum: 10 - default: 1 - example: 1 - nullable: true - description: The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported. - quality: - type: string - enum: ["standard", "hd"] - default: "standard" - example: "standard" - description: The quality of the image that will be generated. `hd` creates images with finer details and greater consistency across the image. This param is only supported for `dall-e-3`. - response_format: &images_response_format - type: string - enum: ["url", "b64_json"] - default: "url" - example: "url" - nullable: true - description: The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. - size: &images_size - type: string - enum: ["256x256", "512x512", "1024x1024", "1792x1024", "1024x1792"] - default: "1024x1024" - example: "1024x1024" - nullable: true - description: The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`. Must be one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3` models. - style: - type: string - enum: ["vivid", "natural"] - default: "vivid" - example: "vivid" - nullable: true - description: The style of the generated images. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for `dall-e-3`. - user: *end_user_param_configuration - required: - - prompt + data: + {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - ImagesResponse: - properties: - created: - type: integer - data: - type: array - items: - $ref: "#/components/schemas/Image" - required: - - created - - data - Image: - type: object - description: Represents the url or the content of an image generated by the OpenAI API. - properties: - b64_json: - type: string - description: The base64-encoded JSON of the generated image, if `response_format` is `b64_json`. - url: - type: string - description: The URL of the generated image, if `response_format` is `url` (default). - revised_prompt: - type: string - description: The prompt that was used to generate the image, if there was any revision to the prompt. - x-oaiMeta: - name: The image object - example: | - { - "url": "...", - "revised_prompt": "..." - } + event: thread.run.queued - CreateImageEditRequest: - type: object - properties: - image: - description: The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask. - type: string - format: binary - prompt: - description: A text description of the desired image(s). The maximum length is 1000 characters. - type: string - example: "A cute baby sea otter wearing a beret" - mask: - description: An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`. - type: string - format: binary - model: - anyOf: - - type: string - - type: string - enum: ["dall-e-2"] - x-oaiTypeLabel: string - default: "dall-e-2" - example: "dall-e-2" - nullable: true - description: The model to use for image generation. Only `dall-e-2` is supported at this time. - n: - type: integer - minimum: 1 - maximum: 10 - default: 1 - example: 1 - nullable: true - description: The number of images to generate. Must be between 1 and 10. - size: &dalle2_images_size - type: string - enum: ["256x256", "512x512", "1024x1024"] - default: "1024x1024" - example: "1024x1024" - nullable: true - description: The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`. - response_format: *images_response_format - user: *end_user_param_configuration - required: - - prompt - - image + data: + {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - CreateImageVariationRequest: - type: object - properties: - image: - description: The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square. - type: string - format: binary - model: - anyOf: - - type: string - - type: string - enum: ["dall-e-2"] - x-oaiTypeLabel: string - default: "dall-e-2" - example: "dall-e-2" - nullable: true - description: The model to use for image generation. Only `dall-e-2` is supported at this time. - n: *images_n - response_format: *images_response_format - size: *dalle2_images_size - user: *end_user_param_configuration - required: - - image - CreateModerationRequest: - type: object - properties: - input: - description: The input text to classify - oneOf: - - type: string - default: "" - example: "I want to kill them." - - type: array - items: - type: string - default: "" - example: "I want to kill them." - model: - description: | - Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`. - - The default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`. - nullable: false - default: "text-moderation-latest" - example: "text-moderation-stable" - anyOf: - - type: string - - type: string - enum: ["text-moderation-latest", "text-moderation-stable"] - x-oaiTypeLabel: string - required: - - input + event: thread.run.in_progress - CreateModerationResponse: - type: object - description: Represents if a given text input is potentially harmful. - properties: - id: - type: string - description: The unique identifier for the moderation request. - model: - type: string - description: The model used to generate the moderation results. - results: - type: array - description: A list of moderation objects. - items: - type: object - properties: - flagged: - type: boolean - description: Whether any of the below categories are flagged. - categories: - type: object - description: A list of the categories, and whether they are flagged or not. - properties: - hate: - type: boolean - description: Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment. - hate/threatening: - type: boolean - description: Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. - harassment: - type: boolean - description: Content that expresses, incites, or promotes harassing language towards any target. - harassment/threatening: - type: boolean - description: Harassment content that also includes violence or serious harm towards any target. - self-harm: - type: boolean - description: Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders. - self-harm/intent: - type: boolean - description: Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders. - self-harm/instructions: - type: boolean - description: Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts. - sexual: - type: boolean - description: Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness). - sexual/minors: - type: boolean - description: Sexual content that includes an individual who is under 18 years old. - violence: - type: boolean - description: Content that depicts death, violence, or physical injury. - violence/graphic: - type: boolean - description: Content that depicts death, violence, or physical injury in graphic detail. - required: - - hate - - hate/threatening - - harassment - - harassment/threatening - - self-harm - - self-harm/intent - - self-harm/instructions - - sexual - - sexual/minors - - violence - - violence/graphic - category_scores: - type: object - description: A list of the categories along with their scores as predicted by model. - properties: - hate: - type: number - description: The score for the category 'hate'. - hate/threatening: - type: number - description: The score for the category 'hate/threatening'. - harassment: - type: number - description: The score for the category 'harassment'. - harassment/threatening: - type: number - description: The score for the category 'harassment/threatening'. - self-harm: - type: number - description: The score for the category 'self-harm'. - self-harm/intent: - type: number - description: The score for the category 'self-harm/intent'. - self-harm/instructions: - type: number - description: The score for the category 'self-harm/instructions'. - sexual: - type: number - description: The score for the category 'sexual'. - sexual/minors: - type: number - description: The score for the category 'sexual/minors'. - violence: - type: number - description: The score for the category 'violence'. - violence/graphic: - type: number - description: The score for the category 'violence/graphic'. - required: - - hate - - hate/threatening - - harassment - - harassment/threatening - - self-harm - - self-harm/intent - - self-harm/instructions - - sexual - - sexual/minors - - violence - - violence/graphic - required: - - flagged - - categories - - category_scores - required: - - id - - model - - results - x-oaiMeta: - name: The moderation object - example: *moderation_example + data: + {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710348075,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - ListFilesResponse: - type: object - properties: - data: - type: array - items: - $ref: "#/components/schemas/OpenAIFile" - object: - type: string - enum: [list] - required: - - object - - data - CreateFileRequest: - type: object - additionalProperties: false - properties: - file: - description: | - The File object (not file name) to be uploaded. - type: string - format: binary - purpose: - description: | - The intended purpose of the uploaded file. + event: thread.run.step.created - Use "assistants" for [Assistants](/docs/api-reference/assistants) and [Message](/docs/api-reference/messages) files, "vision" for Assistants image file inputs, "batch" for [Batch API](/docs/guides/batch), and "fine-tune" for [Fine-tuning](/docs/api-reference/fine-tuning). - type: string - enum: ["assistants", "batch", "fine-tune", "vision"] - required: - - file - - purpose + data: + {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - DeleteFileResponse: - type: object - properties: - id: - type: string - object: - type: string - enum: [file] - deleted: - type: boolean - required: - - id - - object - - deleted - CreateUploadRequest: - type: object - additionalProperties: false - properties: - filename: - description: | - The name of the file to upload. - type: string - purpose: - description: | - The intended purpose of the uploaded file. - - See the [documentation on File purposes](/docs/api-reference/files/create#files-create-purpose). - type: string - enum: ["assistants", "batch", "fine-tune", "vision"] - bytes: - description: | - The number of bytes in the file you are uploading. - type: integer - mime_type: - description: | - The MIME type of the file. - - This must fall within the supported MIME types for your file purpose. See the supported MIME types for assistants and vision. - type: string - required: - - filename - - purpose - - bytes - - mime_type + event: thread.run.step.in_progress - AddUploadPartRequest: - type: object - additionalProperties: false - properties: - data: - description: | - The chunk of bytes for this Part. - type: string - format: binary - required: - - data + data: + {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} - CompleteUploadRequest: - type: object - additionalProperties: false - properties: - part_ids: - type: array - description: | - The ordered list of Part IDs. - items: - type: string - md5: - description: | - The optional md5 checksum for the file contents to verify if the bytes uploaded matches what you expect. - type: string - required: - - part_ids - CancelUploadRequest: - type: object - additionalProperties: false + event: thread.message.created - CreateFineTuningJobRequest: - type: object - properties: - model: - description: | - The name of the model to fine-tune. You can select one of the - [supported models](/docs/guides/fine-tuning/what-models-can-be-fine-tuned). - example: "gpt-3.5-turbo" - anyOf: - - type: string - - type: string - enum: ["babbage-002", "davinci-002", "gpt-3.5-turbo"] - x-oaiTypeLabel: string - training_file: - description: | - The ID of an uploaded file that contains training data. - - See [upload file](/docs/api-reference/files/create) for how to upload a file. - - Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`. - - The contents of the file should differ depending on if the model uses the [chat](/docs/api-reference/fine-tuning/chat-input) or [completions](/docs/api-reference/fine-tuning/completions-input) format. - - See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. - type: string - example: "file-abc123" - hyperparameters: - type: object - description: The hyperparameters used for the fine-tuning job. - properties: - batch_size: - description: | - Number of examples in each batch. A larger batch size means that model parameters - are updated less frequently, but with lower variance. - oneOf: - - type: string - enum: [auto] - - type: integer - minimum: 1 - maximum: 256 - default: auto - learning_rate_multiplier: - description: | - Scaling factor for the learning rate. A smaller learning rate may be useful to avoid - overfitting. - oneOf: - - type: string - enum: [auto] - - type: number - minimum: 0 - exclusiveMinimum: true - default: auto - n_epochs: - description: | - The number of epochs to train the model for. An epoch refers to one full cycle - through the training dataset. - oneOf: - - type: string - enum: [auto] - - type: integer - minimum: 1 - maximum: 50 - default: auto - suffix: - description: | - A string of up to 18 characters that will be added to your fine-tuned model name. - - For example, a `suffix` of "custom-model-name" would produce a model name like `ft:gpt-3.5-turbo:openai:custom-model-name:7p4lURel`. - type: string - minLength: 1 - maxLength: 40 - # default: null - nullable: true - validation_file: - description: | - The ID of an uploaded file that contains validation data. + data: + {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - If you provide this file, the data is used to generate validation - metrics periodically during fine-tuning. These metrics can be viewed in - the fine-tuning results file. - The same data should not be present in both train and validation files. - Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`. + event: thread.message.in_progress - See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. - type: string - nullable: true - example: "file-abc123" - integrations: - type: array - description: A list of integrations to enable for your fine-tuning job. - nullable: true - items: - type: object - required: - - type - - wandb - properties: - type: - description: | - The type of integration to enable. Currently, only "wandb" (Weights and Biases) is supported. - oneOf: - - type: string - enum: [wandb] - wandb: - type: object - description: | - The settings for your integration with Weights and Biases. This payload specifies the project that - metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags - to your run, and set a default entity (team, username, etc) to be associated with your run. - required: - - project - properties: - project: - description: | - The name of the project that the new run will be created under. - type: string - example: "my-wandb-project" - name: - description: | - A display name to set for the run. If not set, we will use the Job ID as the name. - nullable: true - type: string - entity: - description: | - The entity to use for the run. This allows you to set the team or username of the WandB user that you would - like associated with the run. If not set, the default entity for the registered WandB API key is used. - nullable: true - type: string - tags: - description: | - A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some - default tags are generated by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}". - type: array - items: - type: string - example: "custom-tag" - - seed: - description: | - The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. - If a seed is not specified, one will be generated for you. - type: integer - nullable: true - minimum: 0 - maximum: 2147483647 - example: 42 - required: - - model - - training_file + data: + {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} - ListFineTuningJobEventsResponse: - type: object - properties: - data: - type: array - items: - $ref: "#/components/schemas/FineTuningJobEvent" - object: - type: string - enum: [list] - required: - - object - - data - ListFineTuningJobCheckpointsResponse: - type: object - properties: - data: - type: array - items: - $ref: "#/components/schemas/FineTuningJobCheckpoint" - object: - type: string - enum: [list] - first_id: - type: string - nullable: true - last_id: - type: string - nullable: true - has_more: - type: boolean - required: - - object - - data - - has_more + event: thread.message.delta - CreateEmbeddingRequest: - type: object - additionalProperties: false - properties: - input: - description: | - Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. - example: "The quick brown fox jumped over the lazy dog" - oneOf: - - type: string - title: string - description: The string that will be turned into an embedding. - default: "" - example: "This is a test." - - type: array - title: array - description: The array of strings that will be turned into an embedding. - minItems: 1 - maxItems: 2048 - items: - type: string - default: "" - example: "['This is a test.']" - - type: array - title: array - description: The array of integers that will be turned into an embedding. - minItems: 1 - maxItems: 2048 - items: - type: integer - example: "[1212, 318, 257, 1332, 13]" - - type: array - title: array - description: The array of arrays containing integers that will be turned into an embedding. - minItems: 1 - maxItems: 2048 - items: - type: array - minItems: 1 - items: - type: integer - example: "[[1212, 318, 257, 1332, 13]]" - x-oaiExpandable: true - model: - description: *model_description - example: "text-embedding-3-small" - anyOf: - - type: string - - type: string - enum: - [ - "text-embedding-ada-002", - "text-embedding-3-small", - "text-embedding-3-large", - ] - x-oaiTypeLabel: string - encoding_format: - description: "The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/)." - example: "float" - default: "float" - type: string - enum: ["float", "base64"] - dimensions: - description: | - The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models. - type: integer - minimum: 1 - user: *end_user_param_configuration - required: - - model - - input + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} - CreateEmbeddingResponse: - type: object - properties: - data: - type: array - description: The list of embeddings generated by the model. - items: - $ref: "#/components/schemas/Embedding" - model: - type: string - description: The name of the model used to generate the embedding. - object: - type: string - description: The object type, which is always "list". - enum: [list] - usage: - type: object - description: The usage information for the request. - properties: - prompt_tokens: - type: integer - description: The number of tokens used by the prompt. - total_tokens: - type: integer - description: The total number of tokens used by the request. - required: - - prompt_tokens - - total_tokens - required: - - object - - model - - data - - usage - CreateTranscriptionRequest: - type: object - additionalProperties: false - properties: - file: - description: | - The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. - type: string - x-oaiTypeLabel: file - format: binary - model: - description: | - ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available. - example: whisper-1 - anyOf: - - type: string - - type: string - enum: ["whisper-1"] - x-oaiTypeLabel: string - language: - description: | - The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency. - type: string - prompt: - description: | - An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the audio language. - type: string - response_format: - description: | - The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. - type: string - enum: - - json - - text - - srt - - verbose_json - - vtt - default: json - temperature: - description: | - The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. - type: number - default: 0 - timestamp_granularities[]: - description: | - The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. - type: array - items: - type: string - enum: - - word - - segment - default: [segment] - required: - - file - - model + ... - # Note: This does not currently support the non-default response format types. - CreateTranscriptionResponseJson: - type: object - description: Represents a transcription response returned by model, based on the provided input. - properties: - text: - type: string - description: The transcribed text. - required: - - text - x-oaiMeta: - name: The transcription object (JSON) - group: audio - example: *basic_transcription_response_example - TranscriptionSegment: - type: object - properties: - id: - type: integer - description: Unique identifier of the segment. - seek: - type: integer - description: Seek offset of the segment. - start: - type: number - format: float - description: Start time of the segment in seconds. - end: - type: number - format: float - description: End time of the segment in seconds. - text: - type: string - description: Text content of the segment. - tokens: - type: array - items: - type: integer - description: Array of token IDs for the text content. - temperature: - type: number - format: float - description: Temperature parameter used for generating the segment. - avg_logprob: - type: number - format: float - description: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed. - compression_ratio: - type: number - format: float - description: Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed. - no_speech_prob: - type: number - format: float - description: Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent. - required: - - id - - seek - - start - - end - - text - - tokens - - temperature - - avg_logprob - - compression_ratio - - no_speech_prob + event: thread.message.delta - TranscriptionWord: - type: object - properties: - word: - type: string - description: The text content of the word. - start: - type: number - format: float - description: Start time of the word in seconds. - end: - type: number - format: float - description: End time of the word in seconds. - required: [word, start, end] + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" + today"}}]}} - CreateTranscriptionResponseVerboseJson: - type: object - description: Represents a verbose json transcription response returned by model, based on the provided input. - properties: - language: - type: string - description: The language of the input audio. - duration: - type: string - description: The duration of the input audio. - text: - type: string - description: The transcribed text. - words: - type: array - description: Extracted words and their corresponding timestamps. - items: - $ref: "#/components/schemas/TranscriptionWord" - segments: - type: array - description: Segments of the transcribed text and their corresponding details. - items: - $ref: "#/components/schemas/TranscriptionSegment" - required: [language, duration, text] - x-oaiMeta: - name: The transcription object (Verbose JSON) - group: audio - example: *verbose_transcription_response_example - - CreateTranslationRequest: - type: object - additionalProperties: false - properties: - file: - description: | - The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. - type: string - x-oaiTypeLabel: file - format: binary - model: - description: | - ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available. - example: whisper-1 - anyOf: - - type: string - - type: string - enum: ["whisper-1"] - x-oaiTypeLabel: string - prompt: - description: | - An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in English. - type: string - response_format: - description: | - The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. - type: string - default: json - temperature: - description: | - The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. - type: number - default: 0 - required: - - file - - model - # Note: This does not currently support the non-default response format types. - CreateTranslationResponseJson: - type: object - properties: - text: - type: string - required: - - text + event: thread.message.delta - CreateTranslationResponseVerboseJson: - type: object - properties: - language: - type: string - description: The language of the output translation (always `english`). - duration: - type: string - description: The duration of the input audio. - text: - type: string - description: The translated text. - segments: - type: array - description: Segments of the translated text and their corresponding details. - items: - $ref: "#/components/schemas/TranscriptionSegment" - required: [language, duration, text] + data: + {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} - CreateSpeechRequest: - type: object - additionalProperties: false - properties: - model: - description: | - One of the available [TTS models](/docs/models/tts): `tts-1` or `tts-1-hd` - anyOf: - - type: string - - type: string - enum: ["tts-1", "tts-1-hd"] - x-oaiTypeLabel: string - input: - type: string - description: The text to generate audio for. The maximum length is 4096 characters. - maxLength: 4096 - voice: - description: The voice to use when generating the audio. Supported voices are `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are available in the [Text to speech guide](/docs/guides/text-to-speech/voice-options). - type: string - enum: ["alloy", "echo", "fable", "onyx", "nova", "shimmer"] - response_format: - description: "The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`." - default: "mp3" - type: string - enum: ["mp3", "opus", "aac", "flac", "wav", "pcm"] - speed: - description: "The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default." - type: number - default: 1.0 - minimum: 0.25 - maximum: 4.0 - required: - - model - - input - - voice - Model: - title: Model - description: Describes an OpenAI model offering that can be used with the API. - properties: - id: - type: string - description: The model identifier, which can be referenced in the API endpoints. - created: - type: integer - description: The Unix timestamp (in seconds) when the model was created. - object: - type: string - description: The object type, which is always "model". - enum: [model] - owned_by: - type: string - description: The organization that owns the model. - required: - - id - - object - - created - - owned_by - x-oaiMeta: - name: The model object - example: *retrieve_model_response - - OpenAIFile: - title: OpenAIFile - description: The `File` object represents a document that has been uploaded to OpenAI. - properties: - id: - type: string - description: The file identifier, which can be referenced in the API endpoints. - bytes: - type: integer - description: The size of the file, in bytes. - created_at: - type: integer - description: The Unix timestamp (in seconds) for when the file was created. - filename: - type: string - description: The name of the file. - object: - type: string - description: The object type, which is always `file`. - enum: ["file"] - purpose: - type: string - description: The intended purpose of the file. Supported values are `assistants`, `assistants_output`, `batch`, `batch_output`, `fine-tune`, `fine-tune-results` and `vision`. - enum: - [ - "assistants", - "assistants_output", - "batch", - "batch_output", - "fine-tune", - "fine-tune-results", - "vision", - ] - status: - type: string - deprecated: true - description: Deprecated. The current status of the file, which can be either `uploaded`, `processed`, or `error`. - enum: ["uploaded", "processed", "error"] - status_details: - type: string - deprecated: true - description: Deprecated. For details on why a fine-tuning training file failed validation, see the `error` field on `fine_tuning.job`. - required: - - id - - object - - bytes - - created_at - - filename - - purpose - - status - x-oaiMeta: - name: The file object - example: | - { - "id": "file-abc123", - "object": "file", - "bytes": 120000, - "created_at": 1677610602, - "filename": "salesOverview.pdf", - "purpose": "assistants", + event: thread.message.completed + + data: + {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! + How can I assist you today?","annotations":[]}}],"metadata":{}} + + + event: thread.run.step.completed + + data: + {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} + + + event: thread.run.completed + + data: + {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710348075,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710348077,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + + event: done + + data: [DONE] + /threads/{thread_id}/runs/{run_id}: + get: + operationId: getRun + tags: + - Assistants + summary: Retrieves a run. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) that was run. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Retrieve run + group: threads + beta: true + returns: The [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.retrieve( + thread_id="thread_abc123", + run_id="run_abc123" + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.retrieve( + "thread_abc123", + "run_abc123" + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699075072, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699075073, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + post: + operationId: modifyRun + tags: + - Assistants + summary: Modifies a run. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) that was run. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Modify run + group: threads + beta: true + returns: The modified [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "metadata": { + "user_id": "user_abc123" + } + }' + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.update( + thread_id="thread_abc123", + run_id="run_abc123", + metadata={"user_id": "user_abc123"}, + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.update( + "thread_abc123", + "run_abc123", + { + metadata: { + user_id: "user_abc123", + }, + } + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699075072, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699075073, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": { + "user_id": "user_abc123" + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + /threads/{thread_id}/runs/{run_id}/cancel: + post: + operationId: cancelRun + tags: + - Assistants + summary: Cancels a run that is `in_progress`. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which this run belongs. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Cancel a run + group: threads + beta: true + returns: The modified [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/cancel + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -X POST + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.cancel( + thread_id="thread_abc123", + run_id="run_abc123" + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.cancel( + "thread_abc123", + "run_abc123" + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699076126, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "cancelling", + "started_at": 1699076126, + "expires_at": 1699076726, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "last_error": null, + "model": "gpt-4o", + "instructions": "You summarize books.", + "tools": [ + { + "type": "file_search" + } + ], + "tool_resources": { + "file_search": { + "vector_store_ids": ["vs_123"] + } + }, + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + /threads/{thread_id}/runs/{run_id}/steps: + get: + operationId: listRunSteps + tags: + - Assistants + summary: Returns a list of run steps belonging to a run. + parameters: + - name: thread_id + in: path + required: true + schema: + type: string + description: The ID of the thread the run and run steps belong to. + - name: run_id + in: path + required: true + schema: + type: string + description: The ID of the run the run steps belong to. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: include[] + in: query + description: > + A list of additional fields to include in the response. Currently + the only supported value is + `step_details.tool_calls[*].file_search.results[*].content` to fetch + the file search result content. + + + See the [file search tool + documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) + for more information. + schema: + type: array + items: + type: string + enum: + - step_details.tool_calls[*].file_search.results[*].content + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListRunStepsResponse" + x-oaiMeta: + name: List run steps + group: threads + beta: true + returns: A list of [run step](/docs/api-reference/run-steps/step-object) + objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + run_steps = client.beta.threads.runs.steps.list( + thread_id="thread_abc123", + run_id="run_abc123" + ) + + print(run_steps) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const runStep = await openai.beta.threads.runs.steps.list( + "thread_abc123", + "run_abc123" + ); + console.log(runStep); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" } - Upload: - type: object - title: Upload - description: | - The Upload object can accept byte chunks in the form of Parts. - properties: - id: - type: string - description: The Upload unique identifier, which can be referenced in API endpoints. - created_at: - type: integer - description: The Unix timestamp (in seconds) for when the Upload was created. - filename: - type: string - description: The name of the file to be uploaded. - bytes: - type: integer - description: The intended number of bytes to be uploaded. - purpose: - type: string - description: The intended purpose of the file. [Please refer here](/docs/api-reference/files/object#files/object-purpose) for acceptable values. - status: - type: string - description: The status of the Upload. - enum: ["pending", "completed", "cancelled", "expired"] - expires_at: - type: integer - description: The Unix timestamp (in seconds) for when the Upload was created. - object: - type: string - description: The object type, which is always "upload". - enum: [upload] - file: - $ref: "#/components/schemas/OpenAIFile" - nullable: true - description: The ready File object after the Upload is completed. - required: - - bytes - - created_at - - expires_at - - filename - - id - - purpose - - status - - step_number - x-oaiMeta: - name: The upload object - example: | - { - "id": "upload_abc123", - "object": "upload", - "bytes": 2147483648, - "created_at": 1719184911, - "filename": "training_examples.jsonl", - "purpose": "fine-tune", - "status": "completed", - "expires_at": 1719127296, - "file": { - "id": "file-xyz321", - "object": "file", - "bytes": 2147483648, - "created_at": 1719186911, - "filename": "training_examples.jsonl", - "purpose": "fine-tune", + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } + } + ], + "first_id": "step_abc123", + "last_id": "step_abc456", + "has_more": false + } + /threads/{thread_id}/runs/{run_id}/steps/{step_id}: + get: + operationId: getRunStep + tags: + - Assistants + summary: Retrieves a run step. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which the run and run step belongs. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to which the run step belongs. + - in: path + name: step_id + required: true + schema: + type: string + description: The ID of the run step to retrieve. + - name: include[] + in: query + description: > + A list of additional fields to include in the response. Currently + the only supported value is + `step_details.tool_calls[*].file_search.results[*].content` to fetch + the file search result content. + + + See the [file search tool + documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) + for more information. + schema: + type: array + items: + type: string + enum: + - step_details.tool_calls[*].file_search.results[*].content + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunStepObject" + x-oaiMeta: + name: Retrieve run step + group: threads + beta: true + returns: The [run step](/docs/api-reference/run-steps/step-object) object + matching the specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_abc123 + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + run_step = client.beta.threads.runs.steps.retrieve( + thread_id="thread_abc123", + run_id="run_abc123", + step_id="step_abc123" + ) + + print(run_step) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const runStep = await openai.beta.threads.runs.steps.retrieve( + "thread_abc123", + "run_abc123", + "step_abc123" + ); + console.log(runStep); + } + + main(); + response: | + { + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" + } + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } + } + /threads/{thread_id}/runs/{run_id}/submit_tool_outputs: + post: + operationId: submitToolOuputsToRun + tags: + - Assistants + summary: > + When a run has the `status: "requires_action"` and + `required_action.type` is `submit_tool_outputs`, this endpoint can be + used to submit the outputs from the tool calls once they're all + completed. All outputs must be submitted in a single request. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) to which this + run belongs. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run that requires the tool output submission. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/SubmitToolOutputsRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Submit tool outputs to run + group: threads + beta: true + returns: The modified [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + - title: Default + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "tool_outputs": [ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." } - } - UploadPart: - type: object - title: UploadPart - description: | - The upload Part represents a chunk of bytes we can add to an Upload object. - properties: - id: - type: string - description: The upload Part unique identifier, which can be referenced in API endpoints. - created_at: - type: integer - description: The Unix timestamp (in seconds) for when the Part was created. - upload_id: - type: string - description: The ID of the Upload object that this Part was added to. - object: - type: string - description: The object type, which is always `upload.part`. - enum: ['upload.part'] - required: - - created_at - - id - - object - - upload_id - x-oaiMeta: - name: The upload part object - example: | - { - "id": "part_def456", - "object": "upload.part", - "created_at": 1719186911, - "upload_id": "upload_abc123" - } - Embedding: - type: object - description: | - Represents an embedding vector returned by embedding endpoint. - properties: - index: - type: integer - description: The index of the embedding in the list of embeddings. - embedding: - type: array - description: | - The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](/docs/guides/embeddings). - items: - type: number - object: - type: string - description: The object type, which is always "embedding". - enum: [embedding] - required: - - index - - object - - embedding - x-oaiMeta: - name: The embedding object - example: | + ] + }' + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.submit_tool_outputs( + thread_id="thread_123", + run_id="run_123", + tool_outputs=[ { - "object": "embedding", - "embedding": [ - 0.0023064255, - -0.009327292, - .... (1536 floats total for ada-002) - -0.0028842222, - ], - "index": 0 + "tool_call_id": "call_001", + "output": "70 degrees and sunny." } + ] + ) - FineTuningJob: - type: object - title: FineTuningJob - description: | - The `fine_tuning.job` object represents a fine-tuning job that has been created through the API. - properties: - id: - type: string - description: The object identifier, which can be referenced in the API endpoints. - created_at: - type: integer - description: The Unix timestamp (in seconds) for when the fine-tuning job was created. - error: - type: object - nullable: true - description: For fine-tuning jobs that have `failed`, this will contain more information on the cause of the failure. - properties: - code: - type: string - description: A machine-readable error code. - message: - type: string - description: A human-readable error message. - param: - type: string - description: The parameter that was invalid, usually `training_file` or `validation_file`. This field will be null if the failure was not parameter-specific. - nullable: true - required: - - code - - message - - param - fine_tuned_model: - type: string - nullable: true - description: The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running. - finished_at: - type: integer - nullable: true - description: The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running. - hyperparameters: - type: object - description: The hyperparameters used for the fine-tuning job. See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. - properties: - n_epochs: - oneOf: - - type: string - enum: [auto] - - type: integer - minimum: 1 - maximum: 50 - default: auto - description: - The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. - - "auto" decides the optimal number of epochs based on the size of the dataset. If setting the number manually, we support any number between 1 and 50 epochs. - required: - - n_epochs - model: - type: string - description: The base model that is being fine-tuned. - object: - type: string - description: The object type, which is always "fine_tuning.job". - enum: [fine_tuning.job] - organization_id: - type: string - description: The organization that owns the fine-tuning job. - result_files: - type: array - description: The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](/docs/api-reference/files/retrieve-contents). - items: - type: string - example: file-abc123 - status: - type: string - description: The current status of the fine-tuning job, which can be either `validating_files`, `queued`, `running`, `succeeded`, `failed`, or `cancelled`. - enum: - [ - "validating_files", - "queued", - "running", - "succeeded", - "failed", - "cancelled", - ] - trained_tokens: - type: integer - nullable: true - description: The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running. - training_file: - type: string - description: The file ID used for training. You can retrieve the training data with the [Files API](/docs/api-reference/files/retrieve-contents). - validation_file: - type: string - nullable: true - description: The file ID used for validation. You can retrieve the validation results with the [Files API](/docs/api-reference/files/retrieve-contents). - integrations: - type: array - nullable: true - description: A list of integrations to enable for this fine-tuning job. - maxItems: 5 - items: - oneOf: - - $ref: "#/components/schemas/FineTuningIntegration" - x-oaiExpandable: true - seed: - type: integer - description: The seed used for the fine-tuning job. - estimated_finish: - type: integer - nullable: true - description: The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running. - required: - - created_at - - error - - finished_at - - fine_tuned_model - - hyperparameters - - id - - model - - object - - organization_id - - result_files - - status - - trained_tokens - - training_file - - validation_file - - seed - x-oaiMeta: - name: The fine-tuning job object - example: *fine_tuning_example - - FineTuningIntegration: - type: object - title: Fine-Tuning Job Integration - required: - - type - - wandb - properties: - type: - type: string - description: "The type of the integration being enabled for the fine-tuning job" - enum: ["wandb"] - wandb: - type: object - description: | - The settings for your integration with Weights and Biases. This payload specifies the project that - metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags - to your run, and set a default entity (team, username, etc) to be associated with your run. - required: - - project - properties: - project: - description: | - The name of the project that the new run will be created under. - type: string - example: "my-wandb-project" - name: - description: | - A display name to set for the run. If not set, we will use the Job ID as the name. - nullable: true - type: string - entity: - description: | - The entity to use for the run. This allows you to set the team or username of the WandB user that you would - like associated with the run. If not set, the default entity for the registered WandB API key is used. - nullable: true - type: string - tags: - description: | - A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some - default tags are generated by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}". - type: array - items: - type: string - example: "custom-tag" + print(run) + node.js: | + import OpenAI from "openai"; - FineTuningJobEvent: - type: object - description: Fine-tuning job event object - properties: - id: - type: string - created_at: - type: integer - level: - type: string - enum: ["info", "warn", "error"] - message: - type: string - object: - type: string - enum: [fine_tuning.job.event] - required: - - id - - object - - created_at - - level - - message - x-oaiMeta: - name: The fine-tuning job event object - example: | - { - "object": "fine_tuning.job.event", - "id": "ftevent-abc123" - "created_at": 1677610602, - "level": "info", - "message": "Created fine-tuning job" - } + const openai = new OpenAI(); - FineTuningJobCheckpoint: - type: object - title: FineTuningJobCheckpoint - description: | - The `fine_tuning.job.checkpoint` object represents a model checkpoint for a fine-tuning job that is ready to use. - properties: - id: - type: string - description: The checkpoint identifier, which can be referenced in the API endpoints. - created_at: - type: integer - description: The Unix timestamp (in seconds) for when the checkpoint was created. - fine_tuned_model_checkpoint: - type: string - description: The name of the fine-tuned checkpoint model that is created. - step_number: - type: integer - description: The step number that the checkpoint was created at. - metrics: - type: object - description: Metrics at the step number during the fine-tuning job. - properties: - step: - type: number - train_loss: - type: number - train_mean_token_accuracy: - type: number - valid_loss: - type: number - valid_mean_token_accuracy: - type: number - full_valid_loss: - type: number - full_valid_mean_token_accuracy: - type: number - fine_tuning_job_id: - type: string - description: The name of the fine-tuning job that this checkpoint was created from. - object: - type: string - description: The object type, which is always "fine_tuning.job.checkpoint". - enum: [fine_tuning.job.checkpoint] - required: - - created_at - - fine_tuning_job_id - - fine_tuned_model_checkpoint - - id - - metrics - - object - - step_number - x-oaiMeta: - name: The fine-tuning job checkpoint object - example: | + async function main() { + const run = await openai.beta.threads.runs.submitToolOutputs( + "thread_123", + "run_123", { - "object": "fine_tuning.job.checkpoint", - "id": "ftckpt_qtZ5Gyk4BLq1SfLFWp3RtO3P", - "created_at": 1712211699, - "fine_tuned_model_checkpoint": "ft:gpt-3.5-turbo-0125:my-org:custom_suffix:9ABel2dg:ckpt-step-88", - "fine_tuning_job_id": "ftjob-fpbNQ3H1GrMehXRf8cO97xTN", - "metrics": { - "step": 88, - "train_loss": 0.478, - "train_mean_token_accuracy": 0.924, - "valid_loss": 10.112, - "valid_mean_token_accuracy": 0.145, - "full_valid_loss": 0.567, - "full_valid_mean_token_accuracy": 0.944 - }, - "step_number": 88 + tool_outputs: [ + { + tool_call_id: "call_001", + output: "70 degrees and sunny.", + }, + ], } - - FinetuneChatRequestInput: - type: object - description: The per-line training example of a fine-tuning input file for chat models - properties: - messages: - type: array - minItems: 1 - items: - oneOf: - - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" - - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" - - $ref: "#/components/schemas/FineTuneChatCompletionRequestAssistantMessage" - - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" - - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" - x-oaiExpandable: true - tools: - type: array - description: A list of tools the model may generate JSON inputs for. - items: - $ref: "#/components/schemas/ChatCompletionTool" - parallel_tool_calls: - $ref: "#/components/schemas/ParallelToolCalls" - functions: - deprecated: true - description: - A list of functions the model may generate JSON inputs for. - type: array - minItems: 1 - maxItems: 128 - items: - $ref: "#/components/schemas/ChatCompletionFunctions" - x-oaiMeta: - name: Training format for chat models - example: | + ); + + console.log(run); + } + + main(); + response: > + { + "id": "run_123", + "object": "thread.run", + "created_at": 1699075592, + "assistant_id": "asst_123", + "thread_id": "thread_123", + "status": "queued", + "started_at": 1699075592, + "expires_at": 1699076192, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "tools": [ { - "messages": [ - { "role": "user", "content": "What is the weather in San Francisco?" }, - { - "role": "assistant", - "tool_calls": [ - { - "id": "call_id", - "type": "function", - "function": { - "name": "get_current_weather", - "arguments": "{\"location\": \"San Francisco, USA\", \"format\": \"celsius\"}" - } + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] } - ] + }, + "required": ["location"] } - ], - "parallel_tool_calls": false, - "tools": [ + } + } + ], + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + - title: Streaming + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "tool_outputs": [ { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and country, eg. San Francisco, USA" - }, - "format": { "type": "string", "enum": ["celsius", "fahrenheit"] } - }, - "required": ["location", "format"] - } - } + "tool_call_id": "call_001", + "output": "70 degrees and sunny." } - ] - } - - FinetuneCompletionRequestInput: - type: object - description: The per-line training example of a fine-tuning input file for completions models - properties: - prompt: - type: string - description: The input prompt for this training example. - completion: - type: string - description: The desired completion for this training example. - x-oaiMeta: - name: Training format for completions models - example: | + ], + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + stream = client.beta.threads.runs.submit_tool_outputs( + thread_id="thread_123", + run_id="run_123", + tool_outputs=[ { - "prompt": "What is the answer to 2+2", - "completion": "4" + "tool_call_id": "call_001", + "output": "70 degrees and sunny." } + ], + stream=True + ) - CompletionUsage: - type: object - description: Usage statistics for the completion request. - properties: - completion_tokens: - type: integer - description: Number of tokens in the generated completion. - prompt_tokens: - type: integer - description: Number of tokens in the prompt. - total_tokens: - type: integer - description: Total number of tokens used in the request (prompt + completion). - required: - - prompt_tokens - - completion_tokens - - total_tokens - - RunCompletionUsage: - type: object - description: Usage statistics related to the run. This value will be `null` if the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.). - properties: - completion_tokens: - type: integer - description: Number of completion tokens used over the course of the run. - prompt_tokens: - type: integer - description: Number of prompt tokens used over the course of the run. - total_tokens: - type: integer - description: Total number of tokens used (prompt + completion). - required: - - prompt_tokens - - completion_tokens - - total_tokens - nullable: true - - RunStepCompletionUsage: - type: object - description: Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. - properties: - completion_tokens: - type: integer - description: Number of completion tokens used over the course of the run step. - prompt_tokens: - type: integer - description: Number of prompt tokens used over the course of the run step. - total_tokens: - type: integer - description: Total number of tokens used (prompt + completion). - required: - - prompt_tokens - - completion_tokens - - total_tokens - nullable: true - - AssistantsApiResponseFormatOption: - description: | - Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models/gpt-4o), [GPT-4 Turbo](/docs/models/gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. - - Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. - - **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. - oneOf: - - type: string - description: > - `auto` is the default value - enum: [none, auto] - - $ref: "#/components/schemas/AssistantsApiResponseFormat" - x-oaiExpandable: true - - AssistantsApiResponseFormat: - type: object - description: | - An object describing the expected output of the model. If `json_object` only `function` type `tools` are allowed to be passed to the Run. If `text` the model can return text or any value needed. - properties: - type: - type: string - enum: ["text", "json_object"] - example: "json_object" - default: "text" - description: Must be one of `text` or `json_object`. - - AssistantObject: - type: object - title: Assistant - description: Represents an `assistant` that can call the model and use tools. - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `assistant`. - type: string - enum: [assistant] - created_at: - description: The Unix timestamp (in seconds) for when the assistant was created. - type: integer - name: - description: &assistant_name_param_description | - The name of the assistant. The maximum length is 256 characters. - type: string - maxLength: 256 - nullable: true - description: - description: &assistant_description_param_description | - The description of the assistant. The maximum length is 512 characters. - type: string - maxLength: 512 - nullable: true - model: - description: *model_description - type: string - instructions: - description: &assistant_instructions_param_description | - The system instructions that the assistant uses. The maximum length is 256,000 characters. - type: string - maxLength: 256000 - nullable: true - tools: - description: &assistant_tools_param_description | - A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`. - default: [] - type: array - maxItems: 128 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearch" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - tool_resources: - type: object - description: | - A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. - properties: - code_interpreter: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool. - default: [] - maxItems: 20 - items: - type: string - file_search: - type: object - properties: - vector_store_ids: - type: array - description: | - The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - maxItems: 1 - items: - type: string - nullable: true - metadata: - description: &metadata_description | - Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long. - type: object - x-oaiTypeLabel: map - nullable: true - temperature: - description: &run_temperature_description | - What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - top_p: - type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: &run_top_p_description | - An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. - - We generally recommend altering this or temperature but not both. - response_format: - $ref: "#/components/schemas/AssistantsApiResponseFormatOption" - nullable: true - required: - - id - - object - - created_at - - name - - description - - model - - instructions - - tools - - metadata - x-oaiMeta: - name: The assistant object - beta: true - example: *create_assistants_example - - CreateAssistantRequest: - type: object - additionalProperties: false - properties: - model: - description: *model_description - example: "gpt-4-turbo" - anyOf: - - type: string - - type: string - enum: - [ - "gpt-4o", - "gpt-4o-2024-05-13", - "gpt-4o-mini", - "gpt-4o-mini-2024-07-18", - "gpt-4-turbo", - "gpt-4-turbo-2024-04-09", - "gpt-4-0125-preview", - "gpt-4-turbo-preview", - "gpt-4-1106-preview", - "gpt-4-vision-preview", - "gpt-4", - "gpt-4-0314", - "gpt-4-0613", - "gpt-4-32k", - "gpt-4-32k-0314", - "gpt-4-32k-0613", - "gpt-3.5-turbo", - "gpt-3.5-turbo-16k", - "gpt-3.5-turbo-0613", - "gpt-3.5-turbo-1106", - "gpt-3.5-turbo-0125", - "gpt-3.5-turbo-16k-0613", - ] - x-oaiTypeLabel: string - name: - description: *assistant_name_param_description - type: string - nullable: true - maxLength: 256 - description: - description: *assistant_description_param_description - type: string - nullable: true - maxLength: 512 - instructions: - description: *assistant_instructions_param_description - type: string - nullable: true - maxLength: 256000 - tools: - description: *assistant_tools_param_description - default: [] - type: array - maxItems: 128 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearch" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - tool_resources: - type: object - description: | - A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. - properties: - code_interpreter: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. - default: [] - maxItems: 20 - items: - type: string - file_search: - type: object - properties: - vector_store_ids: - type: array - description: | - The [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - maxItems: 1 - items: - type: string - vector_stores: - type: array - description: | - A helper to create a [vector store](/docs/api-reference/vector-stores/object) with file_ids and attach it to this assistant. There can be a maximum of 1 vector store attached to the assistant. - maxItems: 1 - items: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs to add to the vector store. There can be a maximum of 10000 files in a vector store. - maxItems: 10000 - items: - type: string - chunking_strategy: - # Ideally we'd reuse the chunking strategy schema here, but it doesn't expand properly - type: object - description: The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. - oneOf: - - type: object - title: Auto Chunking Strategy - description: The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. - additionalProperties: false - properties: - type: - type: string - description: Always `auto`. - enum: ["auto"] - required: - - type - - type: object - title: Static Chunking Strategy - additionalProperties: false - properties: - type: - type: string - description: Always `static`. - enum: ["static"] - static: - type: object - additionalProperties: false - properties: - max_chunk_size_tokens: - type: integer - minimum: 100 - maximum: 4096 - description: The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`. - chunk_overlap_tokens: - type: integer - description: | - The number of tokens that overlap between chunks. The default value is `400`. - - Note that the overlap must not exceed half of `max_chunk_size_tokens`. - required: - - max_chunk_size_tokens - - chunk_overlap_tokens - required: - - type - - static - x-oaiExpandable: true - metadata: - type: object - description: | - Set of 16 key-value pairs that can be attached to a vector store. This can be useful for storing additional information about the vector store in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long. - x-oaiTypeLabel: map - oneOf: - - required: [vector_store_ids] - - required: [vector_stores] - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - temperature: - description: &run_temperature_description | - What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - top_p: - type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: &run_top_p_description | - An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. - - We generally recommend altering this or temperature but not both. - response_format: - $ref: "#/components/schemas/AssistantsApiResponseFormatOption" - nullable: true - required: - - model - - ModifyAssistantRequest: - type: object - additionalProperties: false - properties: - model: - description: *model_description - anyOf: - - type: string - name: - description: *assistant_name_param_description - type: string - nullable: true - maxLength: 256 - description: - description: *assistant_description_param_description - type: string - nullable: true - maxLength: 512 - instructions: - description: *assistant_instructions_param_description - type: string - nullable: true - maxLength: 256000 - tools: - description: *assistant_tools_param_description - default: [] - type: array - maxItems: 128 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearch" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - tool_resources: - type: object - description: | - A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. - properties: - code_interpreter: - type: object - properties: - file_ids: - type: array - description: | - Overrides the list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. - default: [] - maxItems: 20 - items: - type: string - file_search: - type: object - properties: - vector_store_ids: - type: array - description: | - Overrides the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - maxItems: 1 - items: - type: string - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - temperature: - description: *run_temperature_description - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - top_p: - type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: &run_top_p_description | - An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. - - We generally recommend altering this or temperature but not both. - response_format: - $ref: "#/components/schemas/AssistantsApiResponseFormatOption" - nullable: true - - DeleteAssistantResponse: - type: object - properties: - id: - type: string - deleted: - type: boolean - object: - type: string - enum: [assistant.deleted] - required: - - id - - object - - deleted - - ListAssistantsResponse: - type: object - properties: - object: - type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/AssistantObject" - first_id: - type: string - example: "asst_abc123" - last_id: - type: string - example: "asst_abc456" - has_more: - type: boolean - example: false - required: - - object - - data - - first_id - - last_id - - has_more - x-oaiMeta: - name: List assistants response object - group: chat - example: *list_assistants_example - - AssistantToolsCode: - type: object - title: Code interpreter tool - properties: - type: - type: string - description: "The type of tool being defined: `code_interpreter`" - enum: ["code_interpreter"] - required: - - type - - AssistantToolsFileSearch: - type: object - title: FileSearch tool - properties: - type: - type: string - description: "The type of tool being defined: `file_search`" - enum: ["file_search"] - file_search: - type: object - description: Overrides for the file search tool. - properties: - max_num_results: - type: integer - minimum: 1 - maximum: 50 - description: | - The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive. - - Note that the file search tool may output fewer than `max_num_results` results. See the [file search tool documentation](/docs/assistants/tools/file-search/number-of-chunks-returned) for more information. - required: - - type - - AssistantToolsFileSearchTypeOnly: - type: object - title: FileSearch tool - properties: - type: - type: string - description: "The type of tool being defined: `file_search`" - enum: ["file_search"] - required: - - type - - AssistantToolsFunction: - type: object - title: Function tool - properties: - type: - type: string - description: "The type of tool being defined: `function`" - enum: ["function"] - function: - $ref: "#/components/schemas/FunctionObject" - required: - - type - - function - - TruncationObject: - type: object - title: Thread Truncation Controls - description: Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run. - properties: - type: - type: string - description: The truncation strategy to use for the thread. The default is `auto`. If set to `last_messages`, the thread will be truncated to the n most recent messages in the thread. When set to `auto`, messages in the middle of the thread will be dropped to fit the context length of the model, `max_prompt_tokens`. - enum: ["auto", "last_messages"] - last_messages: - type: integer - description: The number of most recent messages from the thread when constructing the context for the run. - minimum: 1 - nullable: true - required: - - type - - AssistantsApiToolChoiceOption: - description: | - Controls which (if any) tool is called by the model. - `none` means the model will not call any tools and instead generates a message. - `auto` is the default value and means the model can pick between generating a message or calling one or more tools. - `required` means the model must call one or more tools before responding to the user. - Specifying a particular tool like `{"type": "file_search"}` or `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. - - oneOf: - - type: string - description: > - `none` means the model will not call any tools and instead generates a message. - `auto` means the model can pick between generating a message or calling one or more tools. - `required` means the model must call one or more tools before responding to the user. - enum: [none, auto, required] - - $ref: "#/components/schemas/AssistantsNamedToolChoice" - x-oaiExpandable: true - - AssistantsNamedToolChoice: - type: object - description: Specifies a tool the model should use. Use to force the model to call a specific tool. - properties: - type: - type: string - enum: ["function", "code_interpreter", "file_search"] - description: The type of the tool. If type is `function`, the function name must be set - function: - type: object - properties: - name: - type: string - description: The name of the function to call. - required: - - name - required: - - type - - RunObject: - type: object - title: A run on a thread - description: Represents an execution run on a [thread](/docs/api-reference/threads). - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.run`. - type: string - enum: ["thread.run"] - created_at: - description: The Unix timestamp (in seconds) for when the run was created. - type: integer - thread_id: - description: The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - type: string - assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - type: string - status: - description: The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, `incomplete`, or `expired`. - type: string - enum: - [ - "queued", - "in_progress", - "requires_action", - "cancelling", - "cancelled", - "failed", - "completed", - "incomplete", - "expired", - ] - required_action: - type: object - description: Details on the action required to continue the run. Will be `null` if no action is required. - nullable: true - properties: - type: - description: For now, this is always `submit_tool_outputs`. - type: string - enum: ["submit_tool_outputs"] - submit_tool_outputs: - type: object - description: Details on the tool outputs needed for this run to continue. - properties: - tool_calls: - type: array - description: A list of the relevant tool calls. - items: - $ref: "#/components/schemas/RunToolCallObject" - required: - - tool_calls - required: - - type - - submit_tool_outputs - last_error: - type: object - description: The last error associated with this run. Will be `null` if there are no errors. - nullable: true - properties: - code: - type: string - description: One of `server_error`, `rate_limit_exceeded`, or `invalid_prompt`. - enum: - ["server_error", "rate_limit_exceeded", "invalid_prompt"] - message: - type: string - description: A human-readable description of the error. - required: - - code - - message - expires_at: - description: The Unix timestamp (in seconds) for when the run will expire. - type: integer - nullable: true - started_at: - description: The Unix timestamp (in seconds) for when the run was started. - type: integer - nullable: true - cancelled_at: - description: The Unix timestamp (in seconds) for when the run was cancelled. - type: integer - nullable: true - failed_at: - description: The Unix timestamp (in seconds) for when the run failed. - type: integer - nullable: true - completed_at: - description: The Unix timestamp (in seconds) for when the run was completed. - type: integer - nullable: true - incomplete_details: - description: Details on why the run is incomplete. Will be `null` if the run is not incomplete. - type: object - nullable: true - properties: - reason: - description: The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run. - type: string - enum: ["max_completion_tokens", "max_prompt_tokens"] - model: - description: The model that the [assistant](/docs/api-reference/assistants) used for this run. - type: string - instructions: - description: The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - type: string - tools: - description: The list of tools that the [assistant](/docs/api-reference/assistants) used for this run. - default: [] - type: array - maxItems: 20 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearch" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - usage: - $ref: "#/components/schemas/RunCompletionUsage" - temperature: - description: The sampling temperature used for this run. If not set, defaults to 1. - type: number - nullable: true - top_p: - description: The nucleus sampling value used for this run. If not set, defaults to 1. - type: number - nullable: true - max_prompt_tokens: - type: integer - nullable: true - description: | - The maximum number of prompt tokens specified to have been used over the course of the run. - minimum: 256 - max_completion_tokens: - type: integer - nullable: true - description: | - The maximum number of completion tokens specified to have been used over the course of the run. - minimum: 256 - truncation_strategy: - $ref: "#/components/schemas/TruncationObject" - nullable: true - tool_choice: - $ref: "#/components/schemas/AssistantsApiToolChoiceOption" - nullable: true - parallel_tool_calls: - $ref: "#/components/schemas/ParallelToolCalls" - response_format: - $ref: "#/components/schemas/AssistantsApiResponseFormatOption" - nullable: true - required: - - id - - object - - created_at - - thread_id - - assistant_id - - status - - required_action - - last_error - - expires_at - - started_at - - cancelled_at - - failed_at - - completed_at - - model - - instructions - - tools - - metadata - - usage - - incomplete_details - - max_prompt_tokens - - max_completion_tokens - - truncation_strategy - - tool_choice - - parallel_tool_calls - - response_format - x-oaiMeta: - name: The run object - beta: true - example: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1698107661, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699073476, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699073498, - "last_error": null, - "model": "gpt-4-turbo", - "instructions": null, - "tools": [{"type": "file_search"}, {"type": "code_interpreter"}], - "metadata": {}, - "incomplete_details": null, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - }, - "temperature": 1.0, - "top_p": 1.0, - "max_prompt_tokens": 1000, - "max_completion_tokens": 1000, - "truncation_strategy": { - "type": "auto", - "last_messages": null - }, - "response_format": "auto", - "tool_choice": "auto", - "parallel_tool_calls": true - } - CreateRunRequest: - type: object - additionalProperties: false - properties: - assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. - type: string - model: - description: The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. - example: "gpt-4-turbo" - anyOf: - - type: string - - type: string - enum: - [ - "gpt-4o", - "gpt-4o-2024-05-13", - "gpt-4o-mini", - "gpt-4o-mini-2024-07-18", - "gpt-4-turbo", - "gpt-4-turbo-2024-04-09", - "gpt-4-0125-preview", - "gpt-4-turbo-preview", - "gpt-4-1106-preview", - "gpt-4-vision-preview", - "gpt-4", - "gpt-4-0314", - "gpt-4-0613", - "gpt-4-32k", - "gpt-4-32k-0314", - "gpt-4-32k-0613", - "gpt-3.5-turbo", - "gpt-3.5-turbo-16k", - "gpt-3.5-turbo-0613", - "gpt-3.5-turbo-1106", - "gpt-3.5-turbo-0125", - "gpt-3.5-turbo-16k-0613", - ] - x-oaiTypeLabel: string - nullable: true - instructions: - description: Overrides the [instructions](/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis. - type: string - nullable: true - additional_instructions: - description: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions. - type: string - nullable: true - additional_messages: - description: Adds additional messages to the thread before creating the run. - type: array - items: - $ref: "#/components/schemas/CreateMessageRequest" - nullable: true - tools: - description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. - nullable: true - type: array - maxItems: 20 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearch" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - temperature: - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - description: *run_temperature_description - top_p: - type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: &run_top_p_description | - An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + for event in stream: + print(event) + node.js: > + import OpenAI from "openai"; - We generally recommend altering this or temperature but not both. - stream: - type: boolean - nullable: true - description: | - If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. - max_prompt_tokens: - type: integer - nullable: true - description: | - The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. - minimum: 256 - max_completion_tokens: - type: integer - nullable: true - description: | - The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. - minimum: 256 - truncation_strategy: - $ref: "#/components/schemas/TruncationObject" - nullable: true - tool_choice: - $ref: "#/components/schemas/AssistantsApiToolChoiceOption" - nullable: true - parallel_tool_calls: - $ref: "#/components/schemas/ParallelToolCalls" - response_format: - $ref: "#/components/schemas/AssistantsApiResponseFormatOption" - nullable: true - required: - - thread_id - - assistant_id - ListRunsResponse: - type: object - properties: - object: - type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/RunObject" - first_id: - type: string - example: "run_abc123" - last_id: - type: string - example: "run_abc456" - has_more: - type: boolean - example: false - required: - - object - - data - - first_id - - last_id - - has_more - ModifyRunRequest: - type: object - additionalProperties: false - properties: - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - SubmitToolOutputsRunRequest: - type: object - additionalProperties: false - properties: - tool_outputs: - description: A list of tools for which the outputs are being submitted. - type: array - items: - type: object - properties: - tool_call_id: - type: string - description: The ID of the tool call in the `required_action` object within the run object the output is being submitted for. - output: - type: string - description: The output of the tool call to be submitted to continue the run. - stream: - type: boolean - nullable: true - description: | - If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. - required: - - tool_outputs - RunToolCallObject: - type: object - description: Tool call objects - properties: - id: - type: string - description: The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the [Submit tool outputs to run](/docs/api-reference/runs/submitToolOutputs) endpoint. - type: - type: string - description: The type of tool call the output is required for. For now, this is always `function`. - enum: ["function"] - function: - type: object - description: The function definition. - properties: - name: - type: string - description: The name of the function. - arguments: - type: string - description: The arguments that the model expects you to pass to the function. - required: - - name - - arguments - required: - - id - - type - - function + const openai = new OpenAI(); - CreateThreadAndRunRequest: - type: object - additionalProperties: false - properties: - assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. - type: string - thread: - $ref: "#/components/schemas/CreateThreadRequest" - description: If no thread is provided, an empty thread will be created. - model: - description: The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. - example: "gpt-4-turbo" - anyOf: - - type: string - - type: string - enum: - [ - "gpt-4o", - "gpt-4o-2024-05-13", - "gpt-4o-mini", - "gpt-4o-mini-2024-07-18", - "gpt-4-turbo", - "gpt-4-turbo-2024-04-09", - "gpt-4-0125-preview", - "gpt-4-turbo-preview", - "gpt-4-1106-preview", - "gpt-4-vision-preview", - "gpt-4", - "gpt-4-0314", - "gpt-4-0613", - "gpt-4-32k", - "gpt-4-32k-0314", - "gpt-4-32k-0613", - "gpt-3.5-turbo", - "gpt-3.5-turbo-16k", - "gpt-3.5-turbo-0613", - "gpt-3.5-turbo-1106", - "gpt-3.5-turbo-0125", - "gpt-3.5-turbo-16k-0613", - ] - x-oaiTypeLabel: string - nullable: true - instructions: - description: Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis. - type: string - nullable: true - tools: - description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. - nullable: true - type: array - maxItems: 20 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearch" - - $ref: "#/components/schemas/AssistantToolsFunction" - tool_resources: - type: object - description: | - A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. - properties: - code_interpreter: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. - default: [] - maxItems: 20 - items: - type: string - file_search: - type: object - properties: - vector_store_ids: - type: array - description: | - The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - maxItems: 1 - items: - type: string - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - temperature: - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - description: *run_temperature_description - top_p: - type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: *run_top_p_description - stream: - type: boolean - nullable: true - description: | - If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. - max_prompt_tokens: - type: integer - nullable: true - description: | - The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. - minimum: 256 - max_completion_tokens: - type: integer - nullable: true - description: | - The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. - minimum: 256 - truncation_strategy: - $ref: "#/components/schemas/TruncationObject" - nullable: true - tool_choice: - $ref: "#/components/schemas/AssistantsApiToolChoiceOption" - nullable: true - parallel_tool_calls: - $ref: "#/components/schemas/ParallelToolCalls" - response_format: - $ref: "#/components/schemas/AssistantsApiResponseFormatOption" - nullable: true - required: - - thread_id - - assistant_id - - ThreadObject: - type: object - title: Thread - description: Represents a thread that contains [messages](/docs/api-reference/messages). - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread`. - type: string - enum: ["thread"] - created_at: - description: The Unix timestamp (in seconds) for when the thread was created. - type: integer - tool_resources: - type: object - description: | - A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. - properties: - code_interpreter: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. - default: [] - maxItems: 20 - items: - type: string - file_search: - type: object - properties: - vector_store_ids: - type: array - description: | - The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. There can be a maximum of 1 vector store attached to the thread. - maxItems: 1 - items: - type: string - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - required: - - id - - object - - created_at - - tool_resources - - metadata - x-oaiMeta: - name: The thread object - beta: true - example: | - { - "id": "thread_abc123", - "object": "thread", - "created_at": 1698107661, - "metadata": {} - } - - CreateThreadRequest: - type: object - additionalProperties: false - properties: - messages: - description: A list of [messages](/docs/api-reference/messages) to start the thread with. - type: array - items: - $ref: "#/components/schemas/CreateMessageRequest" - tool_resources: - type: object - description: | - A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. - properties: - code_interpreter: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. - default: [] - maxItems: 20 - items: - type: string - file_search: - type: object - properties: - vector_store_ids: - type: array - description: | - The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. There can be a maximum of 1 vector store attached to the thread. - maxItems: 1 - items: - type: string - vector_stores: - type: array - description: | - A helper to create a [vector store](/docs/api-reference/vector-stores/object) with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread. - maxItems: 1 - items: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs to add to the vector store. There can be a maximum of 10000 files in a vector store. - maxItems: 10000 - items: - type: string - chunking_strategy: - # Ideally we'd reuse the chunking strategy schema here, but it doesn't expand properly - type: object - description: The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. - oneOf: - - type: object - title: Auto Chunking Strategy - description: The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. - additionalProperties: false - properties: - type: - type: string - description: Always `auto`. - enum: ["auto"] - required: - - type - - type: object - title: Static Chunking Strategy - additionalProperties: false - properties: - type: - type: string - description: Always `static`. - enum: ["static"] - static: - type: object - additionalProperties: false - properties: - max_chunk_size_tokens: - type: integer - minimum: 100 - maximum: 4096 - description: The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`. - chunk_overlap_tokens: - type: integer - description: | - The number of tokens that overlap between chunks. The default value is `400`. - - Note that the overlap must not exceed half of `max_chunk_size_tokens`. - required: - - max_chunk_size_tokens - - chunk_overlap_tokens - required: - - type - - static - x-oaiExpandable: true - metadata: - type: object - description: | - Set of 16 key-value pairs that can be attached to a vector store. This can be useful for storing additional information about the vector store in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long. - x-oaiTypeLabel: map - x-oaiExpandable: true - oneOf: - - required: [vector_store_ids] - - required: [vector_stores] - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - - ModifyThreadRequest: - type: object - additionalProperties: false - properties: - tool_resources: - type: object - description: | - A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. - properties: - code_interpreter: - type: object - properties: - file_ids: - type: array - description: | - A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. - default: [] - maxItems: 20 - items: - type: string - file_search: - type: object - properties: - vector_store_ids: - type: array - description: | - The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. There can be a maximum of 1 vector store attached to the thread. - maxItems: 1 - items: - type: string - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - - DeleteThreadResponse: - type: object - properties: - id: - type: string - deleted: - type: boolean - object: - type: string - enum: [thread.deleted] - required: - - id - - object - - deleted - - ListThreadsResponse: - properties: - object: - type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/ThreadObject" - first_id: - type: string - example: "asst_abc123" - last_id: - type: string - example: "asst_abc456" - has_more: - type: boolean - example: false - required: - - object - - data - - first_id - - last_id - - has_more - - MessageObject: - type: object - title: The message object - description: Represents a message within a [thread](/docs/api-reference/threads). - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.message`. - type: string - enum: ["thread.message"] - created_at: - description: The Unix timestamp (in seconds) for when the message was created. - type: integer - thread_id: - description: The [thread](/docs/api-reference/threads) ID that this message belongs to. - type: string - status: - description: The status of the message, which can be either `in_progress`, `incomplete`, or `completed`. - type: string - enum: ["in_progress", "incomplete", "completed"] - incomplete_details: - description: On an incomplete message, details about why the message is incomplete. - type: object - properties: - reason: - type: string - description: The reason the message is incomplete. - enum: - [ - "content_filter", - "max_tokens", - "run_cancelled", - "run_expired", - "run_failed", - ] - nullable: true - required: - - reason - completed_at: - description: The Unix timestamp (in seconds) for when the message was completed. - type: integer - nullable: true - incomplete_at: - description: The Unix timestamp (in seconds) for when the message was marked as incomplete. - type: integer - nullable: true - role: - description: The entity that produced the message. One of `user` or `assistant`. - type: string - enum: ["user", "assistant"] - content: - description: The content of the message in array of text and/or images. - type: array - items: - oneOf: - - $ref: "#/components/schemas/MessageContentImageFileObject" - - $ref: "#/components/schemas/MessageContentImageUrlObject" - - $ref: "#/components/schemas/MessageContentTextObject" - x-oaiExpandable: true - assistant_id: - description: If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - type: string - nullable: true - run_id: - description: The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. - type: string - nullable: true - attachments: - type: array - items: - type: object - properties: - file_id: - type: string - description: The ID of the file to attach to the message. - tools: - description: The tools to add this file to. - type: array - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearchTypeOnly" - x-oaiExpandable: true - description: A list of files attached to the message, and the tools they were added to. - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - required: - - id - - object - - created_at - - thread_id - - status - - incomplete_details - - completed_at - - incomplete_at - - role - - content - - assistant_id - - run_id - - attachments - - metadata - x-oaiMeta: - name: The message object - beta: true - example: | + + async function main() { + const stream = await openai.beta.threads.runs.submitToolOutputs( + "thread_123", + "run_123", { - "id": "msg_abc123", - "object": "thread.message", - "created_at": 1698983503, - "thread_id": "thread_abc123", - "role": "assistant", - "content": [ + tool_outputs: [ { - "type": "text", - "text": { - "value": "Hi! How can I help you today?", - "annotations": [] - } - } + tool_call_id: "call_001", + output: "70 degrees and sunny.", + }, ], - "assistant_id": "asst_abc123", - "run_id": "run_abc123", - "attachments": [], - "metadata": {} } + ); - MessageDeltaObject: - type: object - title: Message delta object - description: | - Represents a message delta i.e. any changed fields on a message during streaming. - properties: - id: - description: The identifier of the message, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.message.delta`. - type: string - enum: ["thread.message.delta"] - delta: - description: The delta containing the fields that have changed on the Message. - type: object - properties: - role: - description: The entity that produced the message. One of `user` or `assistant`. - type: string - enum: ["user", "assistant"] - content: - description: The content of the message in array of text and/or images. - type: array - items: - oneOf: - - $ref: "#/components/schemas/MessageDeltaContentImageFileObject" - - $ref: "#/components/schemas/MessageDeltaContentTextObject" - - $ref: "#/components/schemas/MessageDeltaContentImageUrlObject" - x-oaiExpandable: true - required: - - id - - object - - delta - x-oaiMeta: - name: The message delta object - beta: true - example: | - { - "id": "msg_123", - "object": "thread.message.delta", - "delta": { - "content": [ - { - "index": 0, - "type": "text", - "text": { "value": "Hello", "annotations": [] } - } - ] - } - } + for await (const event of stream) { + console.log(event); + } + } - CreateMessageRequest: - type: object - additionalProperties: false - required: - - role - - content - properties: - role: - type: string - enum: ["user", "assistant"] - description: | - The role of the entity that is creating the message. Allowed values include: - - `user`: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages. - - `assistant`: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation. - content: - oneOf: - - type: string - description: The text contents of the message. - title: Text content - - type: array - description: An array of content parts with a defined type, each can be of type `text` or images can be passed with `image_url` or `image_file`. Image types are only supported on [Vision-compatible models](/docs/models/overview). - title: Array of content parts - items: - oneOf: - - $ref: "#/components/schemas/MessageContentImageFileObject" - - $ref: "#/components/schemas/MessageContentImageUrlObject" - - $ref: "#/components/schemas/MessageRequestContentTextObject" - x-oaiExpandable: true - minItems: 1 - x-oaiExpandable: true - attachments: - type: array - items: - type: object - properties: - file_id: - type: string - description: The ID of the file to attach to the message. - tools: - description: The tools to add this file to. - type: array - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsFileSearchTypeOnly" - x-oaiExpandable: true - description: A list of files attached to the message, and the tools they should be added to. - required: - - file_id - - tools - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - ModifyMessageRequest: - type: object - additionalProperties: false - properties: - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true + main(); + response: > + event: thread.run.step.completed - DeleteMessageResponse: - type: object - properties: - id: - type: string - deleted: - type: boolean - object: - type: string - enum: [thread.message.deleted] - required: - - id - - object - - deleted + data: + {"id":"step_001","object":"thread.run.step","created_at":1710352449,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"completed","cancelled_at":null,"completed_at":1710352475,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[{"id":"call_iWr0kQ2EaYMaxNdl0v3KYkx7","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San + Francisco, CA\",\"unit\":\"fahrenheit\"}","output":"70 degrees and + sunny."}}]},"usage":{"prompt_tokens":291,"completion_tokens":24,"total_tokens":315}} - ListMessagesResponse: - properties: - object: - type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/MessageObject" - first_id: - type: string - example: "msg_abc123" - last_id: - type: string - example: "msg_abc123" - has_more: - type: boolean - example: false - required: - - object - - data - - first_id - - last_id - - has_more - - MessageContentImageFileObject: - title: Image file - type: object - description: References an image [File](/docs/api-reference/files) in the content of a message. - properties: - type: - description: Always `image_file`. - type: string - enum: ["image_file"] - image_file: - type: object - properties: - file_id: - description: The [File](/docs/api-reference/files) ID of the image in the message content. Set `purpose="vision"` when uploading the File if you need to later display the file content. - type: string - detail: - type: string - description: Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`. - enum: ["auto", "low", "high"] - default: "auto" - required: - - file_id - required: - - type - - image_file - MessageDeltaContentImageFileObject: - title: Image file - type: object - description: References an image [File](/docs/api-reference/files) in the content of a message. - properties: - index: - type: integer - description: The index of the content part in the message. - type: - description: Always `image_file`. - type: string - enum: ["image_file"] - image_file: - type: object - properties: - file_id: - description: The [File](/docs/api-reference/files) ID of the image in the message content. Set `purpose="vision"` when uploading the File if you need to later display the file content. - type: string - detail: - type: string - description: Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`. - enum: ["auto", "low", "high"] - default: "auto" - required: - - index - - type + event: thread.run.queued - MessageContentImageUrlObject: - title: Image URL - type: object - description: References an image URL in the content of a message. - properties: - type: - type: string - enum: ["image_url"] - description: The type of the content part. - image_url: - type: object - properties: - url: - type: string - description: "The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp." - format: uri - detail: - type: string - description: Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`. Default value is `auto` - enum: ["auto", "low", "high"] - default: "auto" - required: - - url - required: - - type - - image_url + data: + {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":1710352448,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get + the current weather in a given + location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The + city and state, e.g. San Francisco, + CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - MessageDeltaContentImageUrlObject: - title: Image URL - type: object - description: References an image URL in the content of a message. - properties: - index: - type: integer - description: The index of the content part in the message. - type: - description: Always `image_url`. - type: string - enum: ["image_url"] - image_url: - type: object - properties: - url: - description: "The URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp." - type: string - detail: - type: string - description: Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`. - enum: ["auto", "low", "high"] - default: "auto" - required: - - index - - type - MessageContentTextObject: - title: Text - type: object - description: The text content that is part of a message. - properties: - type: - description: Always `text`. - type: string - enum: ["text"] - text: - type: object - properties: - value: - description: The data that makes up the text. - type: string - annotations: - type: array - items: - oneOf: - - $ref: "#/components/schemas/MessageContentTextAnnotationsFileCitationObject" - - $ref: "#/components/schemas/MessageContentTextAnnotationsFilePathObject" - x-oaiExpandable: true - required: - - value - - annotations - required: - - type - - text + event: thread.run.in_progress - MessageRequestContentTextObject: - title: Text - type: object - description: The text content that is part of a message. - properties: - type: - description: Always `text`. - type: string - enum: ["text"] - text: - type: string - description: Text content to be sent to the model - required: - - type - - text + data: + {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710352475,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get + the current weather in a given + location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The + city and state, e.g. San Francisco, + CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - MessageContentTextAnnotationsFileCitationObject: - title: File citation - type: object - description: A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files. - properties: - type: - description: Always `file_citation`. - type: string - enum: ["file_citation"] - text: - description: The text in the message content that needs to be replaced. - type: string - file_citation: - type: object - properties: - file_id: - description: The ID of the specific File the citation is from. - type: string - required: - - file_id - start_index: - type: integer - minimum: 0 - end_index: - type: integer - minimum: 0 - required: - - type - - text - - file_citation - - start_index - - end_index - MessageContentTextAnnotationsFilePathObject: - title: File path - type: object - description: A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. - properties: - type: - description: Always `file_path`. - type: string - enum: ["file_path"] - text: - description: The text in the message content that needs to be replaced. - type: string - file_path: - type: object - properties: - file_id: - description: The ID of the file that was generated. - type: string - required: - - file_id - start_index: - type: integer - minimum: 0 - end_index: - type: integer - minimum: 0 - required: - - type - - text - - file_path - - start_index - - end_index + event: thread.run.step.created - MessageDeltaContentTextObject: - title: Text - type: object - description: The text content that is part of a message. - properties: - index: - type: integer - description: The index of the content part in the message. - type: - description: Always `text`. - type: string - enum: ["text"] - text: - type: object - properties: - value: - description: The data that makes up the text. - type: string - annotations: - type: array - items: - oneOf: - - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFileCitationObject" - - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFilePathObject" - x-oaiExpandable: true - required: - - index - - type + data: + {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} - MessageDeltaContentTextAnnotationsFileCitationObject: - title: File citation - type: object - description: A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files. - properties: - index: - type: integer - description: The index of the annotation in the text content part. - type: - description: Always `file_citation`. - type: string - enum: ["file_citation"] - text: - description: The text in the message content that needs to be replaced. - type: string - file_citation: - type: object - properties: - file_id: - description: The ID of the specific File the citation is from. - type: string - quote: - description: The specific quote in the file. - type: string - start_index: - type: integer - minimum: 0 - end_index: - type: integer - minimum: 0 - required: - - index - - type - MessageDeltaContentTextAnnotationsFilePathObject: - title: File path - type: object - description: A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. - properties: - index: - type: integer - description: The index of the annotation in the text content part. - type: - description: Always `file_path`. - type: string - enum: ["file_path"] - text: - description: The text in the message content that needs to be replaced. - type: string - file_path: - type: object - properties: - file_id: - description: The ID of the file that was generated. - type: string - start_index: - type: integer - minimum: 0 - end_index: - type: integer - minimum: 0 - required: - - index - - type + event: thread.run.step.in_progress - RunStepObject: - type: object - title: Run steps - description: | - Represents a step in execution of a run. - properties: - id: - description: The identifier of the run step, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.run.step`. - type: string - enum: ["thread.run.step"] - created_at: - description: The Unix timestamp (in seconds) for when the run step was created. - type: integer - assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. - type: string - thread_id: - description: The ID of the [thread](/docs/api-reference/threads) that was run. - type: string - run_id: - description: The ID of the [run](/docs/api-reference/runs) that this run step is a part of. - type: string - type: - description: The type of run step, which can be either `message_creation` or `tool_calls`. - type: string - enum: ["message_creation", "tool_calls"] - status: - description: The status of the run step, which can be either `in_progress`, `cancelled`, `failed`, `completed`, or `expired`. - type: string - enum: ["in_progress", "cancelled", "failed", "completed", "expired"] - step_details: - type: object - description: The details of the run step. - oneOf: - - $ref: "#/components/schemas/RunStepDetailsMessageCreationObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsObject" - x-oaiExpandable: true - last_error: - type: object - description: The last error associated with this run step. Will be `null` if there are no errors. - nullable: true - properties: - code: - type: string - description: One of `server_error` or `rate_limit_exceeded`. - enum: ["server_error", "rate_limit_exceeded"] - message: - type: string - description: A human-readable description of the error. - required: - - code - - message - expired_at: - description: The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. - type: integer - nullable: true - cancelled_at: - description: The Unix timestamp (in seconds) for when the run step was cancelled. - type: integer - nullable: true - failed_at: - description: The Unix timestamp (in seconds) for when the run step failed. - type: integer - nullable: true - completed_at: - description: The Unix timestamp (in seconds) for when the run step completed. - type: integer - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - usage: - $ref: "#/components/schemas/RunStepCompletionUsage" - required: - - id - - object - - created_at - - assistant_id - - thread_id - - run_id - - type - - status - - step_details - - last_error - - expired_at - - cancelled_at - - failed_at - - completed_at - - metadata - - usage - x-oaiMeta: - name: The run step object - beta: true - example: *run_step_object_example - - RunStepDeltaObject: - type: object - title: Run step delta object - description: | - Represents a run step delta i.e. any changed fields on a run step during streaming. - properties: - id: - description: The identifier of the run step, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.run.step.delta`. - type: string - enum: ["thread.run.step.delta"] - delta: - description: The delta containing the fields that have changed on the run step. - type: object - properties: - step_details: - type: object - description: The details of the run step. - oneOf: - - $ref: "#/components/schemas/RunStepDeltaStepDetailsMessageCreationObject" - - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsObject" - x-oaiExpandable: true - required: - - id - - object - - delta - x-oaiMeta: - name: The run step delta object - beta: true - example: | - { - "id": "step_123", - "object": "thread.run.step.delta", - "delta": { - "step_details": { - "type": "tool_calls", - "tool_calls": [ - { - "index": 0, - "id": "call_123", - "type": "code_interpreter", - "code_interpreter": { "input": "", "outputs": [] } - } - ] - } - } - } + data: + {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} + + + event: thread.message.created + + data: + {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + + event: thread.message.in_progress + + data: + {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + + event: thread.message.delta + + data: + {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"The","annotations":[]}}]}} + + + event: thread.message.delta + + data: + {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" + current"}}]}} + + + event: thread.message.delta + + data: + {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" + weather"}}]}} + + + ... - ListRunStepsResponse: - properties: - object: - type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/RunStepObject" - first_id: - type: string - example: "step_abc123" - last_id: - type: string - example: "step_abc456" - has_more: - type: boolean - example: false - required: - - object - - data - - first_id - - last_id - - has_more - - RunStepDetailsMessageCreationObject: - title: Message creation - type: object - description: Details of the message creation by the run step. - properties: - type: - description: Always `message_creation`. - type: string - enum: ["message_creation"] - message_creation: - type: object - properties: - message_id: - type: string - description: The ID of the message that was created by this run step. - required: - - message_id - required: - - type - - message_creation - RunStepDeltaStepDetailsMessageCreationObject: - title: Message creation - type: object - description: Details of the message creation by the run step. - properties: - type: - description: Always `message_creation`. - type: string - enum: ["message_creation"] - message_creation: - type: object - properties: - message_id: - type: string - description: The ID of the message that was created by this run step. - required: - - type + event: thread.message.delta - RunStepDetailsToolCallsObject: - title: Tool calls - type: object - description: Details of the tool call. - properties: - type: - description: Always `tool_calls`. - type: string - enum: ["tool_calls"] - tool_calls: - type: array - description: | - An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`. - items: - oneOf: - - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsFunctionObject" - x-oaiExpandable: true - required: - - type - - tool_calls + data: + {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" + sunny"}}]}} - RunStepDeltaStepDetailsToolCallsObject: - title: Tool calls - type: object - description: Details of the tool call. - properties: - type: - description: Always `tool_calls`. - type: string - enum: ["tool_calls"] - tool_calls: - type: array - description: | - An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`. - items: - oneOf: - - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeObject" - - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFileSearchObject" - - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFunctionObject" - x-oaiExpandable: true - required: - - type - RunStepDetailsToolCallsCodeObject: - title: Code Interpreter tool call - type: object - description: Details of the Code Interpreter tool call the run step was involved in. - properties: - id: - type: string - description: The ID of the tool call. - type: - type: string - description: The type of tool call. This is always going to be `code_interpreter` for this type of tool call. - enum: ["code_interpreter"] - code_interpreter: - type: object - description: The Code Interpreter tool call definition. - required: - - input - - outputs - properties: - input: - type: string - description: The input to the Code Interpreter tool call. - outputs: - type: array - description: The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. - items: - type: object - oneOf: - - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputLogsObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputImageObject" - x-oaiExpandable: true - required: - - id - - type - - code_interpreter + event: thread.message.delta - RunStepDeltaStepDetailsToolCallsCodeObject: - title: Code interpreter tool call - type: object - description: Details of the Code Interpreter tool call the run step was involved in. - properties: - index: - type: integer - description: The index of the tool call in the tool calls array. - id: - type: string - description: The ID of the tool call. - type: - type: string - description: The type of tool call. This is always going to be `code_interpreter` for this type of tool call. - enum: ["code_interpreter"] - code_interpreter: - type: object - description: The Code Interpreter tool call definition. - properties: - input: - type: string - description: The input to the Code Interpreter tool call. - outputs: - type: array - description: The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. - items: - type: object - oneOf: - - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject" - - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputImageObject" - x-oaiExpandable: true - required: - - index - - type + data: + {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"."}}]}} - RunStepDetailsToolCallsCodeOutputLogsObject: - title: Code Interpreter log output - type: object - description: Text output from the Code Interpreter tool call as part of a run step. - properties: - type: - description: Always `logs`. - type: string - enum: ["logs"] - logs: - type: string - description: The text output from the Code Interpreter tool call. - required: - - type - - logs - RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject: - title: Code interpreter log output - type: object - description: Text output from the Code Interpreter tool call as part of a run step. - properties: - index: - type: integer - description: The index of the output in the outputs array. - type: - description: Always `logs`. - type: string - enum: ["logs"] - logs: - type: string - description: The text output from the Code Interpreter tool call. - required: - - index - - type + event: thread.message.completed - RunStepDetailsToolCallsCodeOutputImageObject: - title: Code Interpreter image output - type: object - properties: - type: - description: Always `image`. - type: string - enum: ["image"] - image: - type: object - properties: - file_id: - description: The [file](/docs/api-reference/files) ID of the image. - type: string - required: - - file_id - required: - - type - - image + data: + {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710352477,"role":"assistant","content":[{"type":"text","text":{"value":"The + current weather in San Francisco, CA is 70 degrees Fahrenheit and + sunny.","annotations":[]}}],"metadata":{}} - RunStepDeltaStepDetailsToolCallsCodeOutputImageObject: - title: Code interpreter image output - type: object - properties: - index: - type: integer - description: The index of the output in the outputs array. - type: - description: Always `image`. - type: string - enum: ["image"] - image: - type: object - properties: - file_id: - description: The [file](/docs/api-reference/files) ID of the image. - type: string - required: - - index - - type - RunStepDetailsToolCallsFileSearchObject: - title: File search tool call - type: object - properties: - id: - type: string - description: The ID of the tool call object. - type: - type: string - description: The type of tool call. This is always going to be `file_search` for this type of tool call. - enum: ["file_search"] - file_search: - type: object - description: For now, this is always going to be an empty object. - x-oaiTypeLabel: map - required: - - id - - type - - file_search + event: thread.run.step.completed - RunStepDeltaStepDetailsToolCallsFileSearchObject: - title: File search tool call - type: object - properties: - index: - type: integer - description: The index of the tool call in the tool calls array. - id: - type: string - description: The ID of the tool call object. - type: - type: string - description: The type of tool call. This is always going to be `file_search` for this type of tool call. - enum: ["file_search"] - file_search: - type: object - description: For now, this is always going to be an empty object. - x-oaiTypeLabel: map - required: - - index - - type - - file_search + data: + {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710352477,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":{"prompt_tokens":329,"completion_tokens":18,"total_tokens":347}} - RunStepDetailsToolCallsFunctionObject: - type: object - title: Function tool call - properties: - id: - type: string - description: The ID of the tool call object. - type: - type: string - description: The type of tool call. This is always going to be `function` for this type of tool call. - enum: ["function"] - function: - type: object - description: The definition of the function that was called. - properties: - name: - type: string - description: The name of the function. - arguments: - type: string - description: The arguments passed to the function. - output: - type: string - description: The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. - nullable: true - required: - - name - - arguments - - output - required: - - id - - type - - function - RunStepDeltaStepDetailsToolCallsFunctionObject: - type: object - title: Function tool call - properties: - index: - type: integer - description: The index of the tool call in the tool calls array. - id: - type: string - description: The ID of the tool call object. - type: - type: string - description: The type of tool call. This is always going to be `function` for this type of tool call. - enum: ["function"] - function: - type: object - description: The definition of the function that was called. - properties: - name: - type: string - description: The name of the function. - arguments: - type: string - description: The arguments passed to the function. - output: - type: string - description: The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. - nullable: true - required: - - index - - type + event: thread.run.completed - VectorStoreExpirationAfter: - type: object - title: Vector store expiration policy - description: The expiration policy for a vector store. - properties: - anchor: - description: "Anchor timestamp after which the expiration policy applies. Supported anchors: `last_active_at`." - type: string - enum: ["last_active_at"] - days: - description: The number of days after the anchor time that the vector store will expire. - type: integer - minimum: 1 - maximum: 365 - required: - - anchor - - days + data: + {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710352475,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710352477,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get + the current weather in a given + location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The + city and state, e.g. San Francisco, + CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} - VectorStoreObject: - type: object - title: Vector store - description: A vector store is a collection of processed files can be used by the `file_search` tool. - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `vector_store`. - type: string - enum: ["vector_store"] - created_at: - description: The Unix timestamp (in seconds) for when the vector store was created. - type: integer - name: - description: The name of the vector store. - type: string - usage_bytes: - description: The total number of bytes used by the files in the vector store. - type: integer - file_counts: - type: object - properties: - in_progress: - description: The number of files that are currently being processed. - type: integer - completed: - description: The number of files that have been successfully processed. - type: integer - failed: - description: The number of files that have failed to process. - type: integer - cancelled: - description: The number of files that were cancelled. - type: integer - total: - description: The total number of files. - type: integer - required: - - in_progress - - completed - - failed - - cancelled - - total - status: - description: The status of the vector store, which can be either `expired`, `in_progress`, or `completed`. A status of `completed` indicates that the vector store is ready for use. - type: string - enum: ["expired", "in_progress", "completed"] - expires_after: - $ref: "#/components/schemas/VectorStoreExpirationAfter" - expires_at: - description: The Unix timestamp (in seconds) for when the vector store will expire. - type: integer - nullable: true - last_active_at: - description: The Unix timestamp (in seconds) for when the vector store was last active. - type: integer - nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - required: - - id - - object - - usage_bytes - - created_at - - status - - last_active_at - - name - - file_counts - - metadata - x-oaiMeta: - name: The vector store object - beta: true - example: | - { - "id": "vs_123", - "object": "vector_store", - "created_at": 1698107661, - "usage_bytes": 123456, - "last_active_at": 1698107661, - "name": "my_vector_store", - "status": "completed", - "file_counts": { - "in_progress": 0, - "completed": 100, - "cancelled": 0, - "failed": 0, - "total": 100 - }, - "metadata": {}, - "last_used_at": 1698107661 - } - CreateVectorStoreRequest: - type: object - additionalProperties: false - properties: + event: done + + data: [DONE] + /uploads: + post: + operationId: createUpload + tags: + - Uploads + summary: > + Creates an intermediate [Upload](/docs/api-reference/uploads/object) + object that you can add [Parts](/docs/api-reference/uploads/part-object) + to. Currently, an Upload can accept at most 8 GB in total and expires + after an hour after you create it. + + + Once you complete the Upload, we will create a + [File](/docs/api-reference/files/object) object that contains all the + parts you uploaded. This File is usable in the rest of our platform as a + regular File object. + + + For certain `purpose`s, the correct `mime_type` must be specified. + Please refer to documentation for the supported MIME types for your use + case: + + - [Assistants](/docs/assistants/tools/file-search#supported-files) + + + For guidance on the proper filename extensions for each purpose, please + follow the documentation on [creating a + File](/docs/api-reference/files/create). + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateUploadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Upload" + x-oaiMeta: + name: Create upload + group: uploads + returns: The [Upload](/docs/api-reference/uploads/object) object with status + `pending`. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "purpose": "fine-tune", + "filename": "training_examples.jsonl", + "bytes": 2147483648, + "mime_type": "text/jsonl" + }' + response: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "pending", + "expires_at": 1719127296 + } + /uploads/{upload_id}/cancel: + post: + operationId: cancelUpload + tags: + - Uploads + summary: | + Cancels the Upload. No Parts may be added after an Upload is cancelled. + parameters: + - in: path + name: upload_id + required: true + schema: + type: string + example: upload_abc123 + description: | + The ID of the Upload. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Upload" + x-oaiMeta: + name: Cancel upload + group: uploads + returns: The [Upload](/docs/api-reference/uploads/object) object with status + `cancelled`. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads/upload_abc123/cancel + response: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "cancelled", + "expires_at": 1719127296 + } + /uploads/{upload_id}/complete: + post: + operationId: completeUpload + tags: + - Uploads + summary: > + Completes the [Upload](/docs/api-reference/uploads/object). + + + Within the returned Upload object, there is a nested + [File](/docs/api-reference/files/object) object that is ready to use in + the rest of the platform. + + + You can specify the order of the Parts by passing in an ordered list of + the Part IDs. + + + The number of bytes uploaded upon completion must match the number of + bytes initially specified when creating the Upload object. No Parts may + be added after an Upload is completed. + parameters: + - in: path + name: upload_id + required: true + schema: + type: string + example: upload_abc123 + description: | + The ID of the Upload. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CompleteUploadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Upload" + x-oaiMeta: + name: Complete upload + group: uploads + returns: The [Upload](/docs/api-reference/uploads/object) object with status + `completed` with an additional `file` property containing the created + usable File object. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads/upload_abc123/complete + -d '{ + "part_ids": ["part_def456", "part_ghi789"] + }' + response: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "completed", + "expires_at": 1719127296, + "file": { + "id": "file-xyz321", + "object": "file", + "bytes": 2147483648, + "created_at": 1719186911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + } + } + /uploads/{upload_id}/parts: + post: + operationId: addUploadPart + tags: + - Uploads + summary: > + Adds a [Part](/docs/api-reference/uploads/part-object) to an + [Upload](/docs/api-reference/uploads/object) object. A Part represents a + chunk of bytes from the file you are trying to upload. + + + Each Part can be at most 64 MB, and you can add Parts until you hit the + Upload maximum of 8 GB. + + + It is possible to add multiple Parts in parallel. You can decide the + intended order of the Parts when you [complete the + Upload](/docs/api-reference/uploads/complete). + parameters: + - in: path + name: upload_id + required: true + schema: + type: string + example: upload_abc123 + description: | + The ID of the Upload. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/AddUploadPartRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/UploadPart" + x-oaiMeta: + name: Add upload part + group: uploads + returns: The upload [Part](/docs/api-reference/uploads/part-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads/upload_abc123/parts + -F data="aHR0cHM6Ly9hcGkub3BlbmFpLmNvbS92MS91cGxvYWRz..." + response: | + { + "id": "part_def456", + "object": "upload.part", + "created_at": 1719185911, + "upload_id": "upload_abc123" + } + /vector_stores: + get: + operationId: listVectorStores + tags: + - Vector stores + summary: Returns a list of vector stores. + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoresResponse" + x-oaiMeta: + name: List vector stores + group: vector_stores + beta: true + returns: A list of [vector store](/docs/api-reference/vector-stores/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_stores = client.beta.vector_stores.list() + print(vector_stores) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStores = await openai.beta.vectorStores.list(); + console.log(vectorStores); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + }, + { + "id": "vs_abc456", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ v2", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + ], + "first_id": "vs_abc123", + "last_id": "vs_abc456", + "has_more": false + } + post: + operationId: createVectorStore + tags: + - Vector stores + summary: Create a vector store. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Create vector store + group: vector_stores + beta: true + returns: A [vector store](/docs/api-reference/vector-stores/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + -d '{ + "name": "Support FAQ" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.beta.vector_stores.create( + name="Support FAQ" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.beta.vectorStores.create({ + name: "Support FAQ" + }); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + /vector_stores/{vector_store_id}: + get: + operationId: getVectorStore + tags: + - Vector stores + summary: Retrieves a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Retrieve vector store + group: vector_stores + beta: true + returns: The [vector store](/docs/api-reference/vector-stores/object) object + matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.beta.vector_stores.retrieve( + vector_store_id="vs_abc123" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.beta.vectorStores.retrieve( + "vs_abc123" + ); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776 + } + post: + operationId: modifyVectorStore + tags: + - Vector stores + summary: Modifies a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/UpdateVectorStoreRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Modify vector store + group: vector_stores + beta: true + returns: The modified [vector store](/docs/api-reference/vector-stores/object) + object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + -d '{ + "name": "Support FAQ" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.beta.vector_stores.update( + vector_store_id="vs_abc123", + name="Support FAQ" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.beta.vectorStores.update( + "vs_abc123", + { + name: "Support FAQ" + } + ); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + delete: + operationId: deleteVectorStore + tags: + - Vector stores + summary: Delete a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteVectorStoreResponse" + x-oaiMeta: + name: Delete vector store + group: vector_stores + beta: true + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + deleted_vector_store = client.beta.vector_stores.delete( + vector_store_id="vs_abc123" + ) + print(deleted_vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const deletedVectorStore = await openai.beta.vectorStores.del( + "vs_abc123" + ); + console.log(deletedVectorStore); + } + + main(); + response: | + { + id: "vs_abc123", + object: "vector_store.deleted", + deleted: true + } + /vector_stores/{vector_store_id}/file_batches: + post: + operationId: createVectorStoreFileBatch + tags: + - Vector stores + summary: Create a vector store file batch. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: | + The ID of the vector store for which to create a File Batch. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreFileBatchRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Create vector store file batch + group: vector_stores + beta: true + returns: A [vector store file + batch](/docs/api-reference/vector-stores-file-batches/batch-object) + object. + examples: + request: + curl: > + curl + https://api.openai.com/v1/vector_stores/vs_abc123/file_batches \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "file_ids": ["file-abc123", "file-abc456"] + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + vector_store_file_batch = + client.beta.vector_stores.file_batches.create( + vector_store_id="vs_abc123", + file_ids=["file-abc123", "file-abc456"] + ) + + print(vector_store_file_batch) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const myVectorStoreFileBatch = await openai.beta.vectorStores.fileBatches.create( + "vs_abc123", + { + file_ids: ["file-abc123", "file-abc456"] + } + ); + console.log(myVectorStoreFileBatch); + } + + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "in_progress", + "file_counts": { + "in_progress": 1, + "completed": 1, + "failed": 0, + "cancelled": 0, + "total": 0, + } + } + /vector_stores/{vector_store_id}/file_batches/{batch_id}: + get: + operationId: getVectorStoreFileBatch + tags: + - Vector stores + summary: Retrieves a vector store file batch. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store that the file batch belongs to. + - in: path + name: batch_id + required: true + schema: + type: string + example: vsfb_abc123 + description: The ID of the file batch being retrieved. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Retrieve vector store file batch + group: vector_stores + beta: true + returns: The [vector store file + batch](/docs/api-reference/vector-stores-file-batches/batch-object) + object. + examples: + request: + curl: > + curl + https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123 + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: > + from openai import OpenAI + + client = OpenAI() + + + vector_store_file_batch = + client.beta.vector_stores.file_batches.retrieve( + vector_store_id="vs_abc123", + batch_id="vsfb_abc123" + ) + + print(vector_store_file_batch) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const vectorStoreFileBatch = await openai.beta.vectorStores.fileBatches.retrieve( + "vs_abc123", + "vsfb_abc123" + ); + console.log(vectorStoreFileBatch); + } + + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "in_progress", + "file_counts": { + "in_progress": 1, + "completed": 1, + "failed": 0, + "cancelled": 0, + "total": 0, + } + } + /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel: + post: + operationId: cancelVectorStoreFileBatch + tags: + - Vector stores + summary: Cancel a vector store file batch. This attempts to cancel the + processing of files in this batch as soon as possible. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store that the file batch belongs to. + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the file batch to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Cancel vector store file batch + group: vector_stores + beta: true + returns: The modified vector store file batch object. + examples: + request: + curl: > + curl + https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/cancel + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X POST + python: > + from openai import OpenAI + + client = OpenAI() + + + deleted_vector_store_file_batch = + client.beta.vector_stores.file_batches.cancel( + vector_store_id="vs_abc123", + file_batch_id="vsfb_abc123" + ) + + print(deleted_vector_store_file_batch) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const deletedVectorStoreFileBatch = await openai.vector_stores.fileBatches.cancel( + "vs_abc123", + "vsfb_abc123" + ); + console.log(deletedVectorStoreFileBatch); + } + + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "cancelling", + "file_counts": { + "in_progress": 12, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 15, + } + } + /vector_stores/{vector_store_id}/file_batches/{batch_id}/files: + get: + operationId: listFilesInVectorStoreBatch + tags: + - Vector stores + summary: Returns a list of vector store files in a batch. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store that the files belong to. + required: true + schema: + type: string + - name: batch_id + in: path + description: The ID of the file batch that the files belong to. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: filter + in: query + description: Filter by file status. One of `in_progress`, `completed`, `failed`, + `cancelled`. + schema: + type: string + enum: + - in_progress + - completed + - failed + - cancelled + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoreFilesResponse" + x-oaiMeta: + name: List vector store files in a batch + group: vector_stores + beta: true + returns: A list of [vector store + file](/docs/api-reference/vector-stores-files/file-object) objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/files + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: > + from openai import OpenAI + + client = OpenAI() + + + vector_store_files = + client.beta.vector_stores.file_batches.list_files( + vector_store_id="vs_abc123", + batch_id="vsfb_abc123" + ) + + print(vector_store_files) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const vectorStoreFiles = await openai.beta.vectorStores.fileBatches.listFiles( + "vs_abc123", + "vsfb_abc123" + ); + console.log(vectorStoreFiles); + } + + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + }, + { + "id": "file-abc456", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + } + ], + "first_id": "file-abc123", + "last_id": "file-abc456", + "has_more": false + } + /vector_stores/{vector_store_id}/files: + get: + operationId: listVectorStoreFiles + tags: + - Vector stores + summary: Returns a list of vector store files. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store that the files belong to. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: filter + in: query + description: Filter by file status. One of `in_progress`, `completed`, `failed`, + `cancelled`. + schema: + type: string + enum: + - in_progress + - completed + - failed + - cancelled + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoreFilesResponse" + x-oaiMeta: + name: List vector store files + group: vector_stores + beta: true + returns: A list of [vector store + file](/docs/api-reference/vector-stores-files/file-object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_files = client.beta.vector_stores.files.list( + vector_store_id="vs_abc123" + ) + print(vector_store_files) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const vectorStoreFiles = await openai.beta.vectorStores.files.list( + "vs_abc123" + ); + console.log(vectorStoreFiles); + } + + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + }, + { + "id": "file-abc456", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + } + ], + "first_id": "file-abc123", + "last_id": "file-abc456", + "has_more": false + } + post: + operationId: createVectorStoreFile + tags: + - Vector stores + summary: Create a vector store file by attaching a + [File](/docs/api-reference/files) to a [vector + store](/docs/api-reference/vector-stores/object). + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: | + The ID of the vector store for which to create a File. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreFileRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileObject" + x-oaiMeta: + name: Create vector store file + group: vector_stores + beta: true + returns: A [vector store + file](/docs/api-reference/vector-stores-files/file-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "file_id": "file-abc123" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file = client.beta.vector_stores.files.create( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(vector_store_file) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const myVectorStoreFile = await openai.beta.vectorStores.files.create( + "vs_abc123", + { + file_id: "file-abc123" + } + ); + console.log(myVectorStoreFile); + } + + + main(); + response: | + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "usage_bytes": 1234, + "vector_store_id": "vs_abcd", + "status": "completed", + "last_error": null + } + /vector_stores/{vector_store_id}/files/{file_id}: + get: + operationId: getVectorStoreFile + tags: + - Vector stores + summary: Retrieves a vector store file. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store that the file belongs to. + - in: path + name: file_id + required: true + schema: + type: string + example: file-abc123 + description: The ID of the file being retrieved. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileObject" + x-oaiMeta: + name: Retrieve vector store file + group: vector_stores + beta: true + returns: The [vector store + file](/docs/api-reference/vector-stores-files/file-object) object. + examples: + request: + curl: > + curl + https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file = client.beta.vector_stores.files.retrieve( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(vector_store_file) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const vectorStoreFile = await openai.beta.vectorStores.files.retrieve( + "vs_abc123", + "file-abc123" + ); + console.log(vectorStoreFile); + } + + + main(); + response: | + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abcd", + "status": "completed", + "last_error": null + } + delete: + operationId: deleteVectorStoreFile + tags: + - Vector stores + summary: Delete a vector store file. This will remove the file from the vector + store but the file itself will not be deleted. To delete the file, use + the [delete file](/docs/api-reference/files/delete) endpoint. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store that the file belongs to. + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteVectorStoreFileResponse" + x-oaiMeta: + name: Delete vector store file + group: vector_stores + beta: true + returns: Deletion status + examples: + request: + curl: > + curl + https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: > + from openai import OpenAI + + client = OpenAI() + + + deleted_vector_store_file = + client.beta.vector_stores.files.delete( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + + print(deleted_vector_store_file) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const deletedVectorStoreFile = await openai.beta.vectorStores.files.del( + "vs_abc123", + "file-abc123" + ); + console.log(deletedVectorStoreFile); + } + + + main(); + response: | + { + id: "file-abc123", + object: "vector_store.file.deleted", + deleted: true + } +components: + schemas: + AddUploadPartRequest: + type: object + additionalProperties: false + properties: + data: + description: | + The chunk of bytes for this Part. + type: string + format: binary + required: + - data + AssistantObject: + type: object + title: Assistant + description: Represents an `assistant` that can call the model and use tools. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `assistant`. + type: string + enum: + - assistant + created_at: + description: The Unix timestamp (in seconds) for when the assistant was created. + type: integer + name: + description: | + The name of the assistant. The maximum length is 256 characters. + type: string + maxLength: 256 + nullable: true + description: + description: > + The description of the assistant. The maximum length is 512 + characters. + type: string + maxLength: 512 + nullable: true + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + type: string + instructions: + description: > + The system instructions that the assistant uses. The maximum length + is 256,000 characters. + type: string + maxLength: 256000 + nullable: true + tools: + description: > + A list of tool enabled on the assistant. There can be a maximum of + 128 tools per assistant. Tools can be of types `code_interpreter`, + `file_search`, or `function`. + default: [] + type: array + maxItems: 128 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: file_ids: - description: A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files. - type: array - maxItems: 500 - items: - type: string + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter`` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The ID of the [vector + store](/docs/api-reference/vector-stores/object) attached to + this assistant. There can be a maximum of 1 vector store + attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - id + - object + - created_at + - name + - description + - model + - instructions + - tools + - metadata + x-oaiMeta: + name: The assistant object + beta: true + example: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698984975, + "name": "Math Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + AssistantStreamEvent: + description: > + Represents an event emitted when streaming a Run. + + + Each event in a server-sent events stream has an `event` and `data` + property: + + + ``` + + event: thread.created + + data: {"id": "thread_123", "object": "thread", ...} + + ``` + + + We emit events whenever a new object is created, transitions to a new + state, or is being + + streamed in parts (deltas). For example, we emit `thread.run.created` + when a new run + + is created, `thread.run.completed` when a run completes, and so on. When + an Assistant chooses + + to create a message during a run, we emit a `thread.message.created + event`, a + + `thread.message.in_progress` event, many `thread.message.delta` events, + and finally a + + `thread.message.completed` event. + + + We may add additional events over time, so we recommend handling unknown + events gracefully + + in your code. See the [Assistants API + quickstart](/docs/assistants/overview) to learn how to + + integrate the Assistants API with streaming. + oneOf: + - $ref: "#/components/schemas/ThreadStreamEvent" + - $ref: "#/components/schemas/RunStreamEvent" + - $ref: "#/components/schemas/RunStepStreamEvent" + - $ref: "#/components/schemas/MessageStreamEvent" + - $ref: "#/components/schemas/ErrorEvent" + - $ref: "#/components/schemas/DoneEvent" + x-oaiMeta: + name: Assistant stream events + beta: true + AssistantToolsCode: + type: object + title: Code interpreter tool + properties: + type: + type: string + description: "The type of tool being defined: `code_interpreter`" + enum: + - code_interpreter + required: + - type + AssistantToolsFileSearch: + type: object + title: FileSearch tool + properties: + type: + type: string + description: "The type of tool being defined: `file_search`" + enum: + - file_search + file_search: + type: object + description: Overrides for the file search tool. + properties: + max_num_results: + type: integer + minimum: 1 + maximum: 50 + description: > + The maximum number of results the file search tool should + output. The default is 20 for `gpt-4*` models and 5 for + `gpt-3.5-turbo`. This number should be between 1 and 50 + inclusive. + + + Note that the file search tool may output fewer than + `max_num_results` results. See the [file search tool + documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) + for more information. + ranking_options: + $ref: "#/components/schemas/FileSearchRankingOptions" + required: + - type + AssistantToolsFileSearchTypeOnly: + type: object + title: FileSearch tool + properties: + type: + type: string + description: "The type of tool being defined: `file_search`" + enum: + - file_search + required: + - type + AssistantToolsFunction: + type: object + title: Function tool + properties: + type: + type: string + description: "The type of tool being defined: `function`" + enum: + - function + function: + $ref: "#/components/schemas/FunctionObject" + required: + - type + - function + AssistantsApiResponseFormatOption: + description: > + Specifies the format that the model must output. Compatible with + [GPT-4o](/docs/models#gpt-4o), [GPT-4 + Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models + since `gpt-3.5-turbo-1106`. + + + Setting to `{ "type": "json_schema", "json_schema": {...} }` enables + Structured Outputs which ensures the model will match your supplied JSON + schema. Learn more in the [Structured Outputs + guide](/docs/guides/structured-outputs). + + + Setting to `{ "type": "json_object" }` enables JSON mode, which ensures + the message the model generates is valid JSON. + + + **Important:** when using JSON mode, you **must** also instruct the + model to produce JSON yourself via a system or user message. Without + this, the model may generate an unending stream of whitespace until the + generation reaches the token limit, resulting in a long-running and + seemingly "stuck" request. Also note that the message content may be + partially cut off if `finish_reason="length"`, which indicates the + generation exceeded `max_tokens` or the conversation exceeded the max + context length. + oneOf: + - type: string + description: | + `auto` is the default value + enum: + - auto + - $ref: "#/components/schemas/ResponseFormatText" + - $ref: "#/components/schemas/ResponseFormatJsonObject" + - $ref: "#/components/schemas/ResponseFormatJsonSchema" + x-oaiExpandable: true + AssistantsApiToolChoiceOption: + description: > + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tools and instead generates a + message. + + `auto` is the default value and means the model can pick between + generating a message or calling one or more tools. + + `required` means the model must call one or more tools before responding + to the user. + + Specifying a particular tool like `{"type": "file_search"}` or `{"type": + "function", "function": {"name": "my_function"}}` forces the model to + call that tool. + oneOf: + - type: string + description: > + `none` means the model will not call any tools and instead generates + a message. `auto` means the model can pick between generating a + message or calling one or more tools. `required` means the model + must call one or more tools before responding to the user. + enum: + - none + - auto + - required + - $ref: "#/components/schemas/AssistantsNamedToolChoice" + x-oaiExpandable: true + AssistantsNamedToolChoice: + type: object + description: Specifies a tool the model should use. Use to force the model to + call a specific tool. + properties: + type: + type: string + enum: + - function + - code_interpreter + - file_search + description: The type of the tool. If type is `function`, the function name must + be set + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + required: + - name + required: + - type + AudioResponseFormat: + description: > + The format of the output, in one of these options: `json`, `text`, + `srt`, `verbose_json`, or `vtt`. + type: string + enum: + - json + - text + - srt + - verbose_json + - vtt + default: json + AuditLog: + type: object + description: A log of a user action or configuration change within this organization. + properties: + id: + type: string + description: The ID of this log. + type: + $ref: "#/components/schemas/AuditLogEventType" + effective_at: + type: integer + description: The Unix timestamp (in seconds) of the event. + project: + type: object + description: The project that the action was scoped to. Absent for actions not + scoped to projects. + properties: + id: + type: string + description: The project ID. + name: + type: string + description: The project title. + actor: + $ref: "#/components/schemas/AuditLogActor" + api_key.created: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The tracking ID of the API key. + data: + type: object + description: The payload used to create the API key. + properties: + scopes: + type: array + items: + type: string + description: A list of scopes allowed for the API key, e.g. + `["api.model.request"]` + api_key.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The tracking ID of the API key. + changes_requested: + type: object + description: The payload used to update the API key. + properties: + scopes: + type: array + items: + type: string + description: A list of scopes allowed for the API key, e.g. + `["api.model.request"]` + api_key.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The tracking ID of the API key. + invite.sent: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The ID of the invite. + data: + type: object + description: The payload used to create the invite. + properties: + email: + type: string + description: The email invited to the organization. + role: + type: string + description: The role the email was invited to be. Is either `owner` or + `member`. + invite.accepted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The ID of the invite. + invite.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The ID of the invite. + login.failed: + type: object + description: The details for events with this `type`. + properties: + error_code: + type: string + description: The error code of the failure. + error_message: + type: string + description: The error message of the failure. + logout.failed: + type: object + description: The details for events with this `type`. + properties: + error_code: + type: string + description: The error code of the failure. + error_message: + type: string + description: The error message of the failure. + organization.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The organization ID. + changes_requested: + type: object + description: The payload used to update the organization settings. + properties: + title: + type: string + description: The organization title. + description: + type: string + description: The organization description. name: - description: The name of the vector store. - type: string - expires_after: - $ref: "#/components/schemas/VectorStoreExpirationAfter" - chunking_strategy: - type: object - description: The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty. - oneOf: - - $ref: "#/components/schemas/AutoChunkingStrategyRequestParam" - - $ref: "#/components/schemas/StaticChunkingStrategyRequestParam" - x-oaiExpandable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - - UpdateVectorStoreRequest: - type: object - additionalProperties: false - properties: + type: string + description: The organization name. + settings: + type: object + properties: + threads_ui_visibility: + type: string + description: Visibility of the threads page which shows messages created with + the Assistants API and Playground. One of `ANY_ROLE`, + `OWNERS`, or `NONE`. + usage_dashboard_visibility: + type: string + description: Visibility of the usage dashboard which shows activity and costs + for your organization. One of `ANY_ROLE` or `OWNERS`. + project.created: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + data: + type: object + description: The payload used to create the project. + properties: name: - description: The name of the vector store. - type: string - nullable: true - expires_after: - $ref: "#/components/schemas/VectorStoreExpirationAfter" + type: string + description: The project name. + title: + type: string + description: The title of the project as seen on the dashboard. + project.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + changes_requested: + type: object + description: The payload used to update the project. + properties: + title: + type: string + description: The title of the project as seen on the dashboard. + project.archived: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + rate_limit.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The rate limit ID + changes_requested: + type: object + description: The payload used to update the rate limits. + properties: + max_requests_per_1_minute: + type: integer + description: The maximum requests per minute. + max_tokens_per_1_minute: + type: integer + description: The maximum tokens per minute. + max_images_per_1_minute: + type: integer + description: The maximum images per minute. Only relevant for certain models. + max_audio_megabytes_per_1_minute: + type: integer + description: The maximum audio megabytes per minute. Only relevant for certain + models. + max_requests_per_1_day: + type: integer + description: The maximum requests per day. Only relevant for certain models. + batch_1_day_max_input_tokens: + type: integer + description: The maximum batch input tokens per day. Only relevant for certain + models. + rate_limit.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The rate limit ID + service_account.created: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The service account ID. + data: + type: object + description: The payload used to create the service account. + properties: + role: + type: string + description: The role of the service account. Is either `owner` or `member`. + service_account.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The service account ID. + changes_requested: + type: object + description: The payload used to updated the service account. + properties: + role: + type: string + description: The role of the service account. Is either `owner` or `member`. + service_account.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The service account ID. + user.added: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The user ID. + data: + type: object + description: The payload used to add the user to the project. + properties: + role: + type: string + description: The role of the user. Is either `owner` or `member`. + user.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + changes_requested: + type: object + description: The payload used to update the user. + properties: + role: + type: string + description: The role of the user. Is either `owner` or `member`. + user.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The user ID. + required: + - id + - type + - effective_at + - actor + x-oaiMeta: + name: The audit log object + example: > + { + "id": "req_xxx_20240101", + "type": "api_key.created", + "effective_at": 1720804090, + "actor": { + "type": "session", + "session": { + "user": { + "id": "user-xxx", + "email": "user@example.com" + }, + "ip_address": "127.0.0.1", + "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36" + } + }, + "api_key.created": { + "id": "key_xxxx", + "data": { + "scopes": ["resource.operation"] + } + } + } + AuditLogActor: + type: object + description: The actor who performed the audit logged action. + properties: + type: + type: string + description: The type of actor. Is either `session` or `api_key`. + enum: + - session + - api_key + session: + type: object + $ref: "#/components/schemas/AuditLogActorSession" + api_key: + type: object + $ref: "#/components/schemas/AuditLogActorApiKey" + AuditLogActorApiKey: + type: object + description: The API Key used to perform the audit logged action. + properties: + id: + type: string + description: The tracking id of the API key. + type: + type: string + description: The type of API key. Can be either `user` or `service_account`. + enum: + - user + - service_account + user: + $ref: "#/components/schemas/AuditLogActorUser" + service_account: + $ref: "#/components/schemas/AuditLogActorServiceAccount" + AuditLogActorServiceAccount: + type: object + description: The service account that performed the audit logged action. + properties: + id: + type: string + description: The service account id. + AuditLogActorSession: + type: object + description: The session in which the audit logged action was performed. + properties: + user: + $ref: "#/components/schemas/AuditLogActorUser" + ip_address: + type: string + description: The IP address from which the action was performed. + AuditLogActorUser: + type: object + description: The user who performed the audit logged action. + properties: + id: + type: string + description: The user id. + email: + type: string + description: The user email. + AuditLogEventType: + type: string + description: The event type. + x-oaiExpandable: true + enum: + - api_key.created + - api_key.updated + - api_key.deleted + - invite.sent + - invite.accepted + - invite.deleted + - login.succeeded + - login.failed + - logout.succeeded + - logout.failed + - organization.updated + - project.created + - project.updated + - project.archived + - service_account.created + - service_account.updated + - service_account.deleted + - rate_limit.updated + - rate_limit.deleted + - user.added + - user.updated + - user.deleted + AutoChunkingStrategyRequestParam: + type: object + title: Auto Chunking Strategy + description: The default strategy. This strategy currently uses a + `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. + additionalProperties: false + properties: + type: + type: string + description: Always `auto`. + enum: + - auto + required: + - type + Batch: + type: object + properties: + id: + type: string + object: + type: string + enum: + - batch + description: The object type, which is always `batch`. + endpoint: + type: string + description: The OpenAI API endpoint used by the batch. + errors: + type: object + properties: + object: + type: string + description: The object type, which is always `list`. + data: + type: array + items: + type: object + properties: + code: + type: string + description: An error code identifying the error type. + message: + type: string + description: A human-readable message providing more details about the error. + param: + type: string + description: The name of the parameter that caused the error, if applicable. nullable: true - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map + line: + type: integer + description: The line number of the input file where the error occurred, if + applicable. nullable: true - - ListVectorStoresResponse: - properties: - object: - type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/VectorStoreObject" - first_id: - type: string - example: "vs_abc123" - last_id: - type: string - example: "vs_abc456" - has_more: - type: boolean - example: false - required: - - object - - data - - first_id - - last_id - - has_more - - DeleteVectorStoreResponse: + input_file_id: + type: string + description: The ID of the input file for the batch. + completion_window: + type: string + description: The time frame within which the batch should be processed. + status: + type: string + description: The current status of the batch. + enum: + - validating + - failed + - in_progress + - finalizing + - completed + - expired + - cancelling + - cancelled + output_file_id: + type: string + description: The ID of the file containing the outputs of successfully executed + requests. + error_file_id: + type: string + description: The ID of the file containing the outputs of requests with errors. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was created. + in_progress_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started + processing. + expires_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch will expire. + finalizing_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started + finalizing. + completed_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was completed. + failed_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch failed. + expired_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch expired. + cancelling_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started + cancelling. + cancelled_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was cancelled. + request_counts: + type: object + properties: + total: + type: integer + description: Total number of requests in the batch. + completed: + type: integer + description: Number of requests that have been completed successfully. + failed: + type: integer + description: Number of requests that have failed. + required: + - total + - completed + - failed + description: The request counts for different statuses within the batch. + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + required: + - id + - object + - endpoint + - input_file_id + - completion_window + - status + - created_at + x-oaiMeta: + name: The batch object + example: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + BatchRequestInput: + type: object + description: The per-line object of the batch input file + properties: + custom_id: + type: string + description: A developer-provided per-request id that will be used to match + outputs to inputs. Must be unique for each request in a batch. + method: + type: string + enum: + - POST + description: The HTTP method to be used for the request. Currently only `POST` + is supported. + url: + type: string + description: The OpenAI API relative URL to be used for the request. Currently + `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are + supported. + x-oaiMeta: + name: The request input object + example: > + {"custom_id": "request-1", "method": "POST", "url": + "/v1/chat/completions", "body": {"model": "gpt-4o-mini", "messages": + [{"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": "What is 2+2?"}]}} + BatchRequestOutput: + type: object + description: The per-line object of the batch output and error files + properties: + id: + type: string + custom_id: + type: string + description: A developer-provided per-request id that will be used to match + outputs to inputs. + response: + type: object + nullable: true + properties: + status_code: + type: integer + description: The HTTP status code of the response + request_id: + type: string + description: An unique identifier for the OpenAI API request. Please include + this request ID when contacting support. + body: + type: object + x-oaiTypeLabel: map + description: The JSON body of the response + error: + type: object + nullable: true + description: For requests that failed with a non-HTTP error, this will contain + more information on the cause of the failure. + properties: + code: + type: string + description: A machine-readable error code. + message: + type: string + description: A human-readable error message. + x-oaiMeta: + name: The request output object + example: > + {"id": "batch_req_wnaDys", "custom_id": "request-2", "response": + {"status_code": 200, "request_id": "req_c187b3", "body": {"id": + "chatcmpl-9758Iw", "object": "chat.completion", "created": 1711475054, + "model": "gpt-4o-mini", "choices": [{"index": 0, "message": {"role": + "assistant", "content": "2 + 2 equals 4."}, "finish_reason": "stop"}], + "usage": {"prompt_tokens": 24, "completion_tokens": 15, + "total_tokens": 39}, "system_fingerprint": null}}, "error": null} + CancelUploadRequest: + type: object + additionalProperties: false + ChatCompletionFunctionCallOption: + type: object + description: > + Specifying a particular function via `{"name": "my_function"}` forces + the model to call that function. + properties: + name: + type: string + description: The name of the function to call. + required: + - name + ChatCompletionFunctions: + type: object + deprecated: true + properties: + description: + type: string + description: A description of what the function does, used by the model to + choose when and how to call the function. + name: + type: string + description: The name of the function to be called. Must be a-z, A-Z, 0-9, or + contain underscores and dashes, with a maximum length of 64. + parameters: + $ref: "#/components/schemas/FunctionParameters" + required: + - name + ChatCompletionMessageToolCall: + type: object + properties: + id: + type: string + description: The ID of the tool call. + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + function: + type: object + description: The function that the model called. + properties: + name: + type: string + description: The name of the function to call. + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + required: + - name + - arguments + required: + - id + - type + - function + ChatCompletionMessageToolCallChunk: + type: object + properties: + index: + type: integer + id: + type: string + description: The ID of the tool call. + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + required: + - index + ChatCompletionMessageToolCalls: + type: array + description: The tool calls generated by the model, such as function calls. + items: + $ref: "#/components/schemas/ChatCompletionMessageToolCall" + ChatCompletionModalities: + type: array + nullable: true + description: > + Output types that you would like the model to generate for this request. + + Most models are capable of generating text, which is the default: + + + `["text"]` + + + The `gpt-4o-audio-preview` model can also be used to [generate + audio](/docs/guides/audio). To + + request that this model generate both text and audio responses, you can + + use: + + + `["text", "audio"]` + items: + type: string + enum: + - text + - audio + ChatCompletionNamedToolChoice: + type: object + description: Specifies a tool the model should use. Use to force the model to + call a specific function. + properties: + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + required: + - name + required: + - type + - function + ChatCompletionRequestAssistantMessage: + type: object + title: Assistant message + properties: + content: + x-oaiExpandable: true + nullable: true + oneOf: + - type: string + description: The contents of the assistant message. + title: Text content + - type: array + description: An array of content parts with a defined type. Can be one or more + of type `text`, or exactly one of type `refusal`. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestAssistantMessageContentPart" + minItems: 1 + description: > + The contents of the assistant message. Required unless `tool_calls` + or `function_call` is specified. + refusal: + nullable: true + type: string + description: The refusal message by the assistant. + role: + type: string + enum: + - assistant + description: The role of the messages author, in this case `assistant`. + name: + type: string + description: An optional name for the participant. Provides the model + information to differentiate between participants of the same role. + audio: + type: object + nullable: true + x-oaiExpandable: true + description: | + Data about a previous audio response from the model. + [Learn more](/docs/guides/audio). + required: + - id + properties: + id: + type: string + description: | + Unique identifier for a previous audio response from the model. + tool_calls: + $ref: "#/components/schemas/ChatCompletionMessageToolCalls" + function_call: + type: object + deprecated: true + description: Deprecated and replaced by `tool_calls`. The name and arguments of + a function that should be called, as generated by the model. + nullable: true + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + name: + type: string + description: The name of the function to call. + required: + - arguments + - name + required: + - role + ChatCompletionRequestAssistantMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartRefusal" + x-oaiExpandable: true + ChatCompletionRequestFunctionMessage: + type: object + title: Function message + deprecated: true + properties: + role: + type: string + enum: + - function + description: The role of the messages author, in this case `function`. + content: + nullable: true + type: string + description: The contents of the function message. + name: + type: string + description: The name of the function to call. + required: + - role + - content + - name + ChatCompletionRequestMessage: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" + - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" + - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" + - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" + - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" + x-oaiExpandable: true + ChatCompletionRequestMessageContentPartAudio: + type: object + title: Audio content part + description: | + Learn about [audio inputs](/docs/guides/audio). + properties: + type: + type: string + enum: + - input_audio + description: The type of the content part. Always `input_audio`. + input_audio: + type: object + properties: + data: + type: string + description: Base64 encoded audio data. + format: + type: string + enum: + - wav + - mp3 + description: > + The format of the encoded audio data. Currently supports "wav" + and "mp3". + required: + - data + - format + required: + - type + - input_audio + ChatCompletionRequestMessageContentPartImage: + type: object + title: Image content part + description: | + Learn about [image inputs](/docs/guides/vision). + properties: + type: + type: string + enum: + - image_url + description: The type of the content part. + image_url: + type: object + properties: + url: + type: string + description: Either a URL of the image or the base64 encoded image data. + format: uri + detail: + type: string + description: Specifies the detail level of the image. Learn more in the [Vision + guide](/docs/guides/vision#low-or-high-fidelity-image-understanding). + enum: + - auto + - low + - high + default: auto + required: + - url + required: + - type + - image_url + ChatCompletionRequestMessageContentPartRefusal: + type: object + title: Refusal content part + properties: + type: + type: string + enum: + - refusal + description: The type of the content part. + refusal: + type: string + description: The refusal message generated by the model. + required: + - type + - refusal + ChatCompletionRequestMessageContentPartText: + type: object + title: Text content part + description: | + Learn about [text inputs](/docs/guides/text-generation). + properties: + type: + type: string + enum: + - text + description: The type of the content part. + text: + type: string + description: The text content. + required: + - type + - text + ChatCompletionRequestSystemMessage: + type: object + title: System message + properties: + content: + description: The contents of the system message. + oneOf: + - type: string + description: The contents of the system message. + title: Text content + - type: array + description: An array of content parts with a defined type. For system messages, + only type `text` is supported. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestSystemMessageContentPart" + minItems: 1 + role: + type: string + enum: + - system + description: The role of the messages author, in this case `system`. + name: + type: string + description: An optional name for the participant. Provides the model + information to differentiate between participants of the same role. + required: + - content + - role + ChatCompletionRequestSystemMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + x-oaiExpandable: true + ChatCompletionRequestToolMessage: + type: object + title: Tool message + properties: + role: + type: string + enum: + - tool + description: The role of the messages author, in this case `tool`. + content: + oneOf: + - type: string + description: The contents of the tool message. + title: Text content + - type: array + description: An array of content parts with a defined type. For tool messages, + only type `text` is supported. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestToolMessageContentPart" + minItems: 1 + description: The contents of the tool message. + tool_call_id: + type: string + description: Tool call that this message is responding to. + required: + - role + - content + - tool_call_id + ChatCompletionRequestToolMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + x-oaiExpandable: true + ChatCompletionRequestUserMessage: + type: object + title: User message + properties: + content: + description: | + The contents of the user message. + oneOf: + - type: string + description: The text contents of the message. + title: Text content + - type: array + description: An array of content parts with a defined type. Supported options + differ based on the [model](/docs/models) being used to generate + the response. Can contain text, image, or audio inputs. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestUserMessageContentPart" + minItems: 1 + x-oaiExpandable: true + role: + type: string + enum: + - user + description: The role of the messages author, in this case `user`. + name: + type: string + description: An optional name for the participant. Provides the model + information to differentiate between participants of the same role. + required: + - content + - role + ChatCompletionRequestUserMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartImage" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartAudio" + x-oaiExpandable: true + ChatCompletionResponseMessage: + type: object + description: A chat completion message generated by the model. + properties: + content: + type: string + description: The contents of the message. + nullable: true + refusal: + type: string + description: The refusal message generated by the model. + nullable: true + tool_calls: + $ref: "#/components/schemas/ChatCompletionMessageToolCalls" + role: + type: string + enum: + - assistant + description: The role of the author of this message. + function_call: + type: object + deprecated: true + description: Deprecated and replaced by `tool_calls`. The name and arguments of + a function that should be called, as generated by the model. + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + name: + type: string + description: The name of the function to call. + required: + - name + - arguments + audio: + type: object + nullable: true + description: > + If the audio output modality is requested, this object contains data + + about the audio response from the model. [Learn + more](/docs/guides/audio). + x-oaiExpandable: true + required: + - id + - expires_at + - data + - transcript + properties: + id: + type: string + description: Unique identifier for this audio response. + expires_at: + type: integer + description: > + The Unix timestamp (in seconds) for when this audio response + will + + no longer be accessible on the server for use in multi-turn + + conversations. + data: + type: string + description: | + Base64 encoded audio bytes generated by the model, in the format + specified in the request. + transcript: + type: string + description: Transcript of the audio generated by the model. + required: + - role + - content + - refusal + ChatCompletionRole: + type: string + description: The role of the author of a message + enum: + - system + - user + - assistant + - tool + - function + ChatCompletionStreamOptions: + description: > + Options for streaming response. Only set this when you set `stream: + true`. + type: object + nullable: true + # default: null + properties: + include_usage: + type: boolean + description: > + If set, an additional chunk will be streamed before the `data: + [DONE]` message. The `usage` field on this chunk shows the token + usage statistics for the entire request, and the `choices` field + will always be an empty array. All other chunks will also include a + `usage` field, but with a null value. + ChatCompletionStreamResponseDelta: + type: object + description: A chat completion delta generated by streamed model responses. + properties: + content: + type: string + description: The contents of the chunk message. + nullable: true + function_call: + deprecated: true + type: object + description: Deprecated and replaced by `tool_calls`. The name and arguments of + a function that should be called, as generated by the model. + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + name: + type: string + description: The name of the function to call. + tool_calls: + type: array + items: + $ref: "#/components/schemas/ChatCompletionMessageToolCallChunk" + role: + type: string + enum: + - system + - user + - assistant + - tool + description: The role of the author of this message. + refusal: + type: string + description: The refusal message generated by the model. + nullable: true + ChatCompletionTokenLogprob: + type: object + properties: + token: &a1 + description: The token. + type: string + logprob: &a2 + description: The log probability of this token, if it is within the top 20 most + likely tokens. Otherwise, the value `-9999.0` is used to signify + that the token is very unlikely. + type: number + bytes: &a3 + description: A list of integers representing the UTF-8 bytes representation of + the token. Useful in instances where characters are represented by + multiple tokens and their byte representations must be combined to + generate the correct text representation. Can be `null` if there is + no bytes representation for the token. + type: array + items: + type: integer + nullable: true + top_logprobs: + description: List of the most likely tokens and their log probability, at this + token position. In rare cases, there may be fewer than the number of + requested `top_logprobs` returned. + type: array + items: type: object properties: - id: - type: string - deleted: - type: boolean - object: - type: string - enum: [vector_store.deleted] + token: *a1 + logprob: *a2 + bytes: *a3 required: - - id - - object - - deleted - - VectorStoreFileObject: - type: object - title: Vector store files - description: A list of files attached to a vector store. - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `vector_store.file`. - type: string - enum: ["vector_store.file"] - usage_bytes: - description: The total vector store usage in bytes. Note that this may be different from the original file size. - type: integer - created_at: - description: The Unix timestamp (in seconds) for when the vector store file was created. - type: integer - vector_store_id: - description: The ID of the [vector store](/docs/api-reference/vector-stores/object) that the [File](/docs/api-reference/files) is attached to. - type: string - status: - description: The status of the vector store file, which can be either `in_progress`, `completed`, `cancelled`, or `failed`. The status `completed` indicates that the vector store file is ready for use. - type: string - enum: ["in_progress", "completed", "cancelled", "failed"] - last_error: + - token + - logprob + - bytes + required: + - token + - logprob + - bytes + - top_logprobs + ChatCompletionTool: + type: object + properties: + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + function: + $ref: "#/components/schemas/FunctionObject" + required: + - type + - function + ChatCompletionToolChoiceOption: + description: > + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a + message. + + `auto` means the model can pick between generating a message or calling + one or more tools. + + `required` means the model must call one or more tools. + + Specifying a particular tool via `{"type": "function", "function": + {"name": "my_function"}}` forces the model to call that tool. + + + `none` is the default when no tools are present. `auto` is the default + if tools are present. + oneOf: + - type: string + description: > + `none` means the model will not call any tool and instead generates + a message. `auto` means the model can pick between generating a + message or calling one or more tools. `required` means the model + must call one or more tools. + enum: + - none + - auto + - required + - $ref: "#/components/schemas/ChatCompletionNamedToolChoice" + x-oaiExpandable: true + ChunkingStrategyRequestParam: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. + oneOf: + - $ref: "#/components/schemas/AutoChunkingStrategyRequestParam" + - $ref: "#/components/schemas/StaticChunkingStrategyRequestParam" + x-oaiExpandable: true + CompleteUploadRequest: + type: object + additionalProperties: false + properties: + part_ids: + type: array + description: | + The ordered list of Part IDs. + items: + type: string + md5: + description: > + The optional md5 checksum for the file contents to verify if the + bytes uploaded matches what you expect. + type: string + required: + - part_ids + CompletionUsage: + type: object + description: Usage statistics for the completion request. + properties: + completion_tokens: + type: integer + description: Number of tokens in the generated completion. + prompt_tokens: + type: integer + description: Number of tokens in the prompt. + total_tokens: + type: integer + description: Total number of tokens used in the request (prompt + completion). + completion_tokens_details: + type: object + description: Breakdown of tokens used in a completion. + properties: + accepted_prediction_tokens: + type: integer + description: | + When using Predicted Outputs, the number of tokens in the + prediction that appeared in the completion. + audio_tokens: + type: integer + description: Audio input tokens generated by the model. + reasoning_tokens: + type: integer + description: Tokens generated by the model for reasoning. + rejected_prediction_tokens: + type: integer + description: > + When using Predicted Outputs, the number of tokens in the + + prediction that did not appear in the completion. However, like + + reasoning tokens, these tokens are still counted in the total + + completion tokens for purposes of billing, output, and context + window + + limits. + prompt_tokens_details: + type: object + description: Breakdown of tokens used in the prompt. + properties: + audio_tokens: + type: integer + description: Audio input tokens present in the prompt. + cached_tokens: + type: integer + description: Cached tokens present in the prompt. + required: + - prompt_tokens + - completion_tokens + - total_tokens + CostsResult: + type: object + description: The aggregated costs details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.costs.result + amount: + type: object + description: The monetary value in its associated currency. + properties: + value: + type: number + description: The numeric value of the cost. + currency: + type: string + description: Lowercase ISO-4217 currency e.g. "usd" + line_item: + type: string + nullable: true + description: When `group_by=line_item`, this field provides the line item of the + grouped costs result. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped costs result. + required: + - object + - sessions + x-oaiMeta: + name: Costs object + example: | + { + "object": "organization.costs.result", + "amount": { + "value": 0.06, + "currency": "usd" + }, + "line_item": "Image models", + "project_id": "proj_abc" + } + CreateAssistantRequest: + type: object + additionalProperties: false + properties: + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + example: gpt-4o + anyOf: + - type: string + - type: string + enum: + - gpt-4o + - gpt-4o-2024-11-20 + - gpt-4o-2024-08-06 + - gpt-4o-2024-05-13 + - gpt-4o-mini + - gpt-4o-mini-2024-07-18 + - gpt-4-turbo + - gpt-4-turbo-2024-04-09 + - gpt-4-0125-preview + - gpt-4-turbo-preview + - gpt-4-1106-preview + - gpt-4-vision-preview + - gpt-4 + - gpt-4-0314 + - gpt-4-0613 + - gpt-4-32k + - gpt-4-32k-0314 + - gpt-4-32k-0613 + - gpt-3.5-turbo + - gpt-3.5-turbo-16k + - gpt-3.5-turbo-0613 + - gpt-3.5-turbo-1106 + - gpt-3.5-turbo-0125 + - gpt-3.5-turbo-16k-0613 + x-oaiTypeLabel: string + name: + description: | + The name of the assistant. The maximum length is 256 characters. + type: string + nullable: true + maxLength: 256 + description: + description: > + The description of the assistant. The maximum length is 512 + characters. + type: string + nullable: true + maxLength: 512 + instructions: + description: > + The system instructions that the assistant uses. The maximum length + is 256,000 characters. + type: string + nullable: true + maxLength: 256000 + tools: + description: > + A list of tool enabled on the assistant. There can be a maximum of + 128 tools per assistant. Tools can be of types `code_interpreter`, + `file_search`, or `function`. + default: [] + type: array + maxItems: 128 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this assistant. There can be a maximum of 1 + vector store attached to the assistant. + maxItems: 1 + items: + type: string + vector_stores: + type: array + description: > + A helper to create a [vector + store](/docs/api-reference/vector-stores/object) with + file_ids and attach it to this assistant. There can be a + maximum of 1 vector store attached to the assistant. + maxItems: 1 + items: type: object - description: The last error associated with this vector store file. Will be `null` if there are no errors. - nullable: true properties: - code: - type: string - description: One of `server_error` or `rate_limit_exceeded`. - enum: - [ - "internal_error", - "file_not_found", - "parsing_error", - "unhandled_mime_type", - ] - message: - type: string - description: A human-readable description of the error. - required: - - code - - message - chunking_strategy: - type: object - description: The strategy used to chunk the file. - oneOf: - - $ref: "#/components/schemas/StaticChunkingStrategyResponseParam" - - $ref: "#/components/schemas/OtherChunkingStrategyResponseParam" - x-oaiExpandable: true + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs to add + to the vector store. There can be a maximum of 10000 + files in a vector store. + maxItems: 10000 + items: + type: string + chunking_strategy: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. + oneOf: + - type: object + title: Auto Chunking Strategy + description: The default strategy. This strategy currently uses a + `max_chunk_size_tokens` of `800` and + `chunk_overlap_tokens` of `400`. + additionalProperties: false + properties: + type: + type: string + description: Always `auto`. + enum: + - auto + required: + - type + - type: object + title: Static Chunking Strategy + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + static: + type: object + additionalProperties: false + properties: + max_chunk_size_tokens: + type: integer + minimum: 100 + maximum: 4096 + description: The maximum number of tokens in each chunk. The default value is + `800`. The minimum value is `100` and the + maximum value is `4096`. + chunk_overlap_tokens: + type: integer + description: > + The number of tokens that overlap between + chunks. The default value is `400`. + + + Note that the overlap must not exceed half + of `max_chunk_size_tokens`. + required: + - max_chunk_size_tokens + - chunk_overlap_tokens + required: + - type + - static + x-oaiExpandable: true + metadata: + type: object + description: > + Set of 16 key-value pairs that can be attached to a + vector store. This can be useful for storing + additional information about the vector store in a + structured format. Keys can be a maximum of 64 + characters long and values can be a maximum of 512 + characters long. + x-oaiTypeLabel: map + oneOf: + - required: + - vector_store_ids + - required: + - vector_stores + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - model + CreateChatCompletionFunctionResponse: + type: object + description: Represents a chat completion response returned by model, based on + the provided input. + properties: + id: + type: string + description: A unique identifier for the chat completion. + choices: + type: array + description: A list of chat completion choices. Can be more than one if `n` is + greater than 1. + items: + type: object required: - - id - - object - - usage_bytes - - created_at - - vector_store_id - - status - - last_error - x-oaiMeta: - name: The vector store file object - beta: true - example: | + - finish_reason + - index + - message + - logprobs + properties: + finish_reason: + type: string + description: > + The reason the model stopped generating tokens. This will be + `stop` if the model hit a natural stop point or a provided + stop sequence, `length` if the maximum number of tokens + specified in the request was reached, `content_filter` if + content was omitted due to a flag from our content filters, or + `function_call` if the model called a function. + enum: + - stop + - length + - function_call + - content_filter + index: + type: integer + description: The index of the choice in the list of choices. + message: + $ref: "#/components/schemas/ChatCompletionResponseMessage" + created: + type: integer + description: The Unix timestamp (in seconds) of when the chat completion was + created. + model: + type: string + description: The model used for the chat completion. + system_fingerprint: + type: string + description: > + This fingerprint represents the backend configuration that the model + runs with. + + + Can be used in conjunction with the `seed` request parameter to + understand when backend changes have been made that might impact + determinism. + object: + type: string + description: The object type, which is always `chat.completion`. + enum: + - chat.completion + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion object + group: chat + example: | + { + "id": "chatcmpl-abc123", + "object": "chat.completion", + "created": 1699896916, + "model": "gpt-4o-mini", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": null, + "tool_calls": [ { - "id": "file-abc123", - "object": "vector_store.file", - "usage_bytes": 1234, - "created_at": 1698107661, - "vector_store_id": "vs_abc123", - "status": "completed", - "last_error": null, - "chunking_strategy": { - "type": "static", - "static": { - "max_chunk_size_tokens": 800, - "chunk_overlap_tokens": 400 - } + "id": "call_abc123", + "type": "function", + "function": { + "name": "get_current_weather", + "arguments": "{\n\"location\": \"Boston, MA\"\n}" } } - - OtherChunkingStrategyResponseParam: - type: object - title: Other Chunking Strategy - description: This is returned when the chunking strategy is unknown. Typically, this is because the file was indexed before the `chunking_strategy` concept was introduced in the API. - additionalProperties: false - properties: - type: - type: string - description: Always `other`. - enum: ["other"] - required: - - type - - StaticChunkingStrategyResponseParam: - type: object - title: Static Chunking Strategy - additionalProperties: false - properties: - type: - type: string - description: Always `static`. - enum: ["static"] - static: - $ref: "#/components/schemas/StaticChunkingStrategy" - required: - - type - - static - - StaticChunkingStrategy: - type: object - additionalProperties: false - properties: - max_chunk_size_tokens: - type: integer - minimum: 100 - maximum: 4096 - description: The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`. - chunk_overlap_tokens: - type: integer - description: | - The number of tokens that overlap between chunks. The default value is `400`. - - Note that the overlap must not exceed half of `max_chunk_size_tokens`. - required: - - max_chunk_size_tokens - - chunk_overlap_tokens - - AutoChunkingStrategyRequestParam: - type: object - title: Auto Chunking Strategy - description: The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. - additionalProperties: false - properties: - type: - type: string - description: Always `auto`. - enum: ["auto"] - required: - - type - - StaticChunkingStrategyRequestParam: - type: object - title: Static Chunking Strategy - additionalProperties: false - properties: - type: - type: string - description: Always `static`. - enum: ["static"] - static: - $ref: "#/components/schemas/StaticChunkingStrategy" - required: - - type - - static - - ChunkingStrategyRequestParam: - type: object - description: The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. - oneOf: - - $ref: "#/components/schemas/AutoChunkingStrategyRequestParam" - - $ref: "#/components/schemas/StaticChunkingStrategyRequestParam" - x-oaiExpandable: true - - CreateVectorStoreFileRequest: + ] + }, + "logprobs": null, + "finish_reason": "tool_calls" + } + ], + "usage": { + "prompt_tokens": 82, + "completion_tokens": 17, + "total_tokens": 99, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } + } + CreateChatCompletionImageResponse: + type: object + description: Represents a streamed chunk of a chat completion response returned + by model, based on the provided input. + x-oaiMeta: + name: The chat completion chunk object + group: chat + example: > + { + "id": "chatcmpl-123", + "object": "chat.completion", + "created": 1677652288, + "model": "gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices": [{ + "index": 0, + "message": { + "role": "assistant", + "content": "\n\nThis image shows a wooden boardwalk extending through a lush green marshland.", + }, + "logprobs": null, + "finish_reason": "stop" + }], + "usage": { + "prompt_tokens": 9, + "completion_tokens": 12, + "total_tokens": 21, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } + } + CreateChatCompletionRequest: + type: object + properties: + messages: + description: > + A list of messages comprising the conversation so far. Depending on + the + + [model](/docs/models) you use, different message types (modalities) + are + + supported, like [text](/docs/guides/text-generation), + + [images](/docs/guides/vision), and [audio](/docs/guides/audio). + type: array + minItems: 1 + items: + $ref: "#/components/schemas/ChatCompletionRequestMessage" + model: + description: ID of the model to use. See the [model endpoint + compatibility](/docs/models#model-endpoint-compatibility) table for + details on which models work with the Chat API. + example: gpt-4o + anyOf: + - type: string + - type: string + enum: + - o1-preview + - o1-preview-2024-09-12 + - o1-mini + - o1-mini-2024-09-12 + - gpt-4o + - gpt-4o-2024-11-20 + - gpt-4o-2024-08-06 + - gpt-4o-2024-05-13 + - gpt-4o-realtime-preview + - gpt-4o-realtime-preview-2024-10-01 + - gpt-4o-audio-preview + - gpt-4o-audio-preview-2024-10-01 + - chatgpt-4o-latest + - gpt-4o-mini + - gpt-4o-mini-2024-07-18 + - gpt-4-turbo + - gpt-4-turbo-2024-04-09 + - gpt-4-0125-preview + - gpt-4-turbo-preview + - gpt-4-1106-preview + - gpt-4-vision-preview + - gpt-4 + - gpt-4-0314 + - gpt-4-0613 + - gpt-4-32k + - gpt-4-32k-0314 + - gpt-4-32k-0613 + - gpt-3.5-turbo + - gpt-3.5-turbo-16k + - gpt-3.5-turbo-0301 + - gpt-3.5-turbo-0613 + - gpt-3.5-turbo-1106 + - gpt-3.5-turbo-0125 + - gpt-3.5-turbo-16k-0613 + x-oaiTypeLabel: string + store: + type: boolean + default: false + nullable: true + description: > + Whether or not to store the output of this chat completion request + + for use in our [model distillation](/docs/guides/distillation) or + [evals](/docs/guides/evals) products. + metadata: + type: object + nullable: true + description: | + Developer-defined tags and values used for filtering completions + in the [dashboard](https://platform.openai.com/chat-completions). + additionalProperties: + type: string + frequency_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on their existing frequency in the text so far, decreasing the + model's likelihood to repeat the same line verbatim. + + + [See more information about frequency and presence + penalties.](/docs/guides/text-generation) + logit_bias: + type: object + x-oaiTypeLabel: map + # default: null + nullable: true + additionalProperties: + type: integer + description: > + Modify the likelihood of specified tokens appearing in the + completion. + + + Accepts a JSON object that maps tokens (specified by their token ID + in the tokenizer) to an associated bias value from -100 to 100. + Mathematically, the bias is added to the logits generated by the + model prior to sampling. The exact effect will vary per model, but + values between -1 and 1 should decrease or increase likelihood of + selection; values like -100 or 100 should result in a ban or + exclusive selection of the relevant token. + logprobs: + description: Whether to return log probabilities of the output tokens or not. If + true, returns the log probabilities of each output token returned in + the `content` of `message`. + type: boolean + default: false + nullable: true + top_logprobs: + description: An integer between 0 and 20 specifying the number of most likely + tokens to return at each token position, each with an associated log + probability. `logprobs` must be set to `true` if this parameter is + used. + type: integer + minimum: 0 + maximum: 20 + nullable: true + max_tokens: + description: > + The maximum number of [tokens](/tokenizer) that can be generated in + the chat completion. This value can be used to control + [costs](https://openai.com/api/pricing/) for text generated via API. + + + This value is now deprecated in favor of `max_completion_tokens`, + and is not compatible with [o1 series + models](/docs/guides/reasoning). + type: integer + nullable: true + deprecated: true + max_completion_tokens: + description: > + An upper bound for the number of tokens that can be generated for a + completion, including visible output tokens and [reasoning + tokens](/docs/guides/reasoning). + type: integer + nullable: true + n: + type: integer + minimum: 1 + maximum: 128 + default: 1 + example: 1 + nullable: true + description: How many chat completion choices to generate for each input + message. Note that you will be charged based on the number of + generated tokens across all of the choices. Keep `n` as `1` to + minimize costs. + modalities: + $ref: "#/components/schemas/ChatCompletionModalities" + prediction: + nullable: true + x-oaiExpandable: true + description: > + Configuration for a [Predicted + Output](/docs/guides/predicted-outputs), + + which can greatly improve response times when large parts of the + model + + response are known ahead of time. This is most common when you are + + regenerating a file with only minor changes to most of the content. + oneOf: + - $ref: "#/components/schemas/PredictionContent" + audio: + type: object + nullable: true + description: > + Parameters for audio output. Required when audio output is requested + with + + `modalities: ["audio"]`. [Learn more](/docs/guides/audio). + required: + - voice + - format + x-oaiExpandable: true + properties: + voice: + type: string + enum: + - alloy + - ash + - ballad + - coral + - echo + - sage + - shimmer + - verse + description: > + The voice the model uses to respond. Supported voices are `ash`, + `ballad`, `coral`, `sage`, and `verse` (also supported but not + recommended are `alloy`, `echo`, and `shimmer`; these voices are + less expressive). + format: + type: string + enum: + - wav + - mp3 + - flac + - opus + - pcm16 + description: > + Specifies the output audio format. Must be one of `wav`, `mp3`, + `flac`, + + `opus`, or `pcm16`. + presence_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on whether they appear in the text so far, increasing the + model's likelihood to talk about new topics. + + + [See more information about frequency and presence + penalties.](/docs/guides/text-generation) + response_format: + description: > + An object specifying the format that the model must output. + Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4o + mini](/docs/models#gpt-4o-mini), [GPT-4 + Turbo](/docs/models#gpt-4-turbo-and-gpt-4) and all GPT-3.5 Turbo + models newer than `gpt-3.5-turbo-1106`. + + + Setting to `{ "type": "json_schema", "json_schema": {...} }` enables + Structured Outputs which ensures the model will match your supplied + JSON schema. Learn more in the [Structured Outputs + guide](/docs/guides/structured-outputs). + + + Setting to `{ "type": "json_object" }` enables JSON mode, which + ensures the message the model generates is valid JSON. + + + **Important:** when using JSON mode, you **must** also instruct the + model to produce JSON yourself via a system or user message. Without + this, the model may generate an unending stream of whitespace until + the generation reaches the token limit, resulting in a long-running + and seemingly "stuck" request. Also note that the message content + may be partially cut off if `finish_reason="length"`, which + indicates the generation exceeded `max_tokens` or the conversation + exceeded the max context length. + oneOf: + - $ref: "#/components/schemas/ResponseFormatText" + - $ref: "#/components/schemas/ResponseFormatJsonObject" + - $ref: "#/components/schemas/ResponseFormatJsonSchema" + x-oaiExpandable: true + seed: + type: integer + minimum: -9223372036854776000 + maximum: 9223372036854776000 + nullable: true + description: > + This feature is in Beta. + + If specified, our system will make a best effort to sample + deterministically, such that repeated requests with the same `seed` + and parameters should return the same result. + + Determinism is not guaranteed, and you should refer to the + `system_fingerprint` response parameter to monitor changes in the + backend. + x-oaiMeta: + beta: true + service_tier: + description: > + Specifies the latency tier to use for processing the request. This + parameter is relevant for customers subscribed to the scale tier + service: + - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. + - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. + - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. + - When not set, the default behavior is 'auto'. + + When this parameter is set, the response body will include the `service_tier` utilized. + type: string + enum: + - auto + - default + nullable: true + default: auto + stop: + description: | + Up to 4 sequences where the API will stop generating further tokens. + # default: null + oneOf: + - type: string + nullable: true + - type: array + minItems: 1 + maxItems: 4 + items: + type: string + stream: + description: > + If set, partial message deltas will be sent, like in ChatGPT. Tokens + will be sent as data-only [server-sent + events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) + as they become available, with the stream terminated by a `data: + [DONE]` message. [Example Python + code](https://cookbook.openai.com/examples/how_to_stream_completions). + type: boolean + nullable: true + default: false + stream_options: + $ref: "#/components/schemas/ChatCompletionStreamOptions" + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + + + We generally recommend altering this or `top_p` but not both. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or `temperature` but not both. + tools: + type: array + description: > + A list of tools the model may call. Currently, only functions are + supported as a tool. Use this to provide a list of functions the + model may generate JSON inputs for. A max of 128 functions are + supported. + items: + $ref: "#/components/schemas/ChatCompletionTool" + tool_choice: + $ref: "#/components/schemas/ChatCompletionToolChoiceOption" + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + function_call: + deprecated: true + description: > + Deprecated in favor of `tool_choice`. + + + Controls which (if any) function is called by the model. + + `none` means the model will not call a function and instead + generates a message. + + `auto` means the model can pick between generating a message or + calling a function. + + Specifying a particular function via `{"name": "my_function"}` + forces the model to call that function. + + + `none` is the default when no functions are present. `auto` is the + default if functions are present. + oneOf: + - type: string + description: > + `none` means the model will not call a function and instead + generates a message. `auto` means the model can pick between + generating a message or calling a function. + enum: + - none + - auto + - $ref: "#/components/schemas/ChatCompletionFunctionCallOption" + x-oaiExpandable: true + functions: + deprecated: true + description: | + Deprecated in favor of `tools`. + + A list of functions the model may generate JSON inputs for. + type: array + minItems: 1 + maxItems: 128 + items: + $ref: "#/components/schemas/ChatCompletionFunctions" + required: + - model + - messages + CreateChatCompletionResponse: + type: object + description: Represents a chat completion response returned by model, based on + the provided input. + properties: + id: + type: string + description: A unique identifier for the chat completion. + choices: + type: array + description: A list of chat completion choices. Can be more than one if `n` is + greater than 1. + items: type: object - additionalProperties: false - properties: - file_id: - description: A [File](/docs/api-reference/files) ID that the vector store should use. Useful for tools like `file_search` that can access files. - type: string - chunking_strategy: - $ref: "#/components/schemas/ChunkingStrategyRequestParam" required: - - file_id - - ListVectorStoreFilesResponse: + - finish_reason + - index + - message + - logprobs properties: - object: - type: string - example: "list" - data: + finish_reason: + type: string + description: > + The reason the model stopped generating tokens. This will be + `stop` if the model hit a natural stop point or a provided + stop sequence, + + `length` if the maximum number of tokens specified in the + request was reached, + + `content_filter` if content was omitted due to a flag from our + content filters, + + `tool_calls` if the model called a tool, or `function_call` + (deprecated) if the model called a function. + enum: + - stop + - length + - tool_calls + - content_filter + - function_call + index: + type: integer + description: The index of the choice in the list of choices. + message: + $ref: "#/components/schemas/ChatCompletionResponseMessage" + logprobs: + description: Log probability information for the choice. + type: object + nullable: true + properties: + content: + description: A list of message content tokens with log probability information. type: array items: - $ref: "#/components/schemas/VectorStoreFileObject" - first_id: - type: string - example: "file-abc123" - last_id: - type: string - example: "file-abc456" - has_more: - type: boolean - example: false - required: - - object - - data - - first_id - - last_id - - has_more - - DeleteVectorStoreFileResponse: - type: object - properties: - id: - type: string - deleted: - type: boolean - object: - type: string - enum: [vector_store.file.deleted] - required: - - id - - object - - deleted - - VectorStoreFileBatchObject: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + refusal: + description: A list of message refusal tokens with log probability information. + type: array + items: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + required: + - content + - refusal + created: + type: integer + description: The Unix timestamp (in seconds) of when the chat completion was + created. + model: + type: string + description: The model used for the chat completion. + service_tier: + description: The service tier used for processing the request. This field is + only included if the `service_tier` parameter is specified in the + request. + type: string + enum: + - scale + - default + example: scale + nullable: true + system_fingerprint: + type: string + description: > + This fingerprint represents the backend configuration that the model + runs with. + + + Can be used in conjunction with the `seed` request parameter to + understand when backend changes have been made that might impact + determinism. + object: + type: string + description: The object type, which is always `chat.completion`. + enum: + - chat.completion + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion object + group: chat + example: | + { + "id": "chatcmpl-123456", + "object": "chat.completion", + "created": 1728933352, + "model": "gpt-4o-2024-08-06", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "Hi there! How can I assist you today?", + "refusal": null + }, + "logprobs": null, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 19, + "completion_tokens": 10, + "total_tokens": 29, + "prompt_tokens_details": { + "cached_tokens": 0 + }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + }, + "system_fingerprint": "fp_6b68a8204b" + } + CreateChatCompletionStreamResponse: + type: object + description: Represents a streamed chunk of a chat completion response returned + by model, based on the provided input. + properties: + id: + type: string + description: A unique identifier for the chat completion. Each chunk has the + same ID. + choices: + type: array + description: > + A list of chat completion choices. Can contain more than one + elements if `n` is greater than 1. Can also be empty for the + + last chunk if you set `stream_options: {"include_usage": true}`. + items: type: object - title: Vector store file batch - description: A batch of files attached to a vector store. - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `vector_store.file_batch`. - type: string - enum: ["vector_store.files_batch"] - created_at: - description: The Unix timestamp (in seconds) for when the vector store files batch was created. - type: integer - vector_store_id: - description: The ID of the [vector store](/docs/api-reference/vector-stores/object) that the [File](/docs/api-reference/files) is attached to. - type: string - status: - description: The status of the vector store files batch, which can be either `in_progress`, `completed`, `cancelled` or `failed`. - type: string - enum: ["in_progress", "completed", "cancelled", "failed"] - file_counts: - type: object - properties: - in_progress: - description: The number of files that are currently being processed. - type: integer - completed: - description: The number of files that have been processed. - type: integer - failed: - description: The number of files that have failed to process. - type: integer - cancelled: - description: The number of files that where cancelled. - type: integer - total: - description: The total number of files. - type: integer - required: - - in_progress - - completed - - cancelled - - failed - - total required: - - id - - object - - created_at - - vector_store_id - - status - - file_counts - x-oaiMeta: - name: The vector store files batch object - beta: true - example: | - { - "id": "vsfb_123", - "object": "vector_store.files_batch", - "created_at": 1698107661, - "vector_store_id": "vs_abc123", - "status": "completed", - "file_counts": { - "in_progress": 0, - "completed": 100, - "failed": 0, - "cancelled": 0, - "total": 100 - } - } - - CreateVectorStoreFileBatchRequest: - type: object - additionalProperties: false + - delta + - finish_reason + - index properties: - file_ids: - description: A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files. + delta: + $ref: "#/components/schemas/ChatCompletionStreamResponseDelta" + logprobs: + description: Log probability information for the choice. + type: object + nullable: true + properties: + content: + description: A list of message content tokens with log probability information. type: array - minItems: 1 - maxItems: 500 items: - type: string - chunking_strategy: - $ref: "#/components/schemas/ChunkingStrategyRequestParam" - required: - - file_ids - - AssistantStreamEvent: - description: | - Represents an event emitted when streaming a Run. - - Each event in a server-sent events stream has an `event` and `data` property: - - ``` - event: thread.created - data: {"id": "thread_123", "object": "thread", ...} - ``` - - We emit events whenever a new object is created, transitions to a new state, or is being - streamed in parts (deltas). For example, we emit `thread.run.created` when a new run - is created, `thread.run.completed` when a run completes, and so on. When an Assistant chooses - to create a message during a run, we emit a `thread.message.created event`, a - `thread.message.in_progress` event, many `thread.message.delta` events, and finally a - `thread.message.completed` event. - - We may add additional events over time, so we recommend handling unknown events gracefully - in your code. See the [Assistants API quickstart](/docs/assistants/overview) to learn how to - integrate the Assistants API with streaming. - oneOf: - - $ref: "#/components/schemas/ThreadStreamEvent" - - $ref: "#/components/schemas/RunStreamEvent" - - $ref: "#/components/schemas/RunStepStreamEvent" - - $ref: "#/components/schemas/MessageStreamEvent" - - $ref: "#/components/schemas/ErrorEvent" - - $ref: "#/components/schemas/DoneEvent" - x-oaiMeta: - name: Assistant stream events - beta: true - - ThreadStreamEvent: - oneOf: - - type: object - properties: - event: - type: string - enum: ["thread.created"] - data: - $ref: "#/components/schemas/ThreadObject" - required: - - event - - data - description: Occurs when a new [thread](/docs/api-reference/threads/object) is created. - x-oaiMeta: - dataDescription: "`data` is a [thread](/docs/api-reference/threads/object)" - - RunStreamEvent: - oneOf: - - type: object - properties: - event: - type: string - enum: ["thread.run.created"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a new [run](/docs/api-reference/runs/object) is created. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.queued"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) moves to a `queued` status. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.in_progress"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) moves to an `in_progress` status. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.requires_action"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) moves to a `requires_action` status. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.completed"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) is completed. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: [ "thread.run.incomplete" ] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) ends with status `incomplete`. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.failed"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) fails. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.cancelling"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) moves to a `cancelling` status. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.cancelled"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) is cancelled. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.expired"] - data: - $ref: "#/components/schemas/RunObject" - required: - - event - - data - description: Occurs when a [run](/docs/api-reference/runs/object) expires. - x-oaiMeta: - dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" - - RunStepStreamEvent: - oneOf: - - type: object - properties: - event: - type: string - enum: ["thread.run.step.created"] - data: - $ref: "#/components/schemas/RunStepObject" - required: - - event - - data - description: Occurs when a [run step](/docs/api-reference/runs/step-object) is created. - x-oaiMeta: - dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.step.in_progress"] - data: - $ref: "#/components/schemas/RunStepObject" - required: - - event - - data - description: Occurs when a [run step](/docs/api-reference/runs/step-object) moves to an `in_progress` state. - x-oaiMeta: - dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.step.delta"] - data: - $ref: "#/components/schemas/RunStepDeltaObject" - required: - - event - - data - description: Occurs when parts of a [run step](/docs/api-reference/runs/step-object) are being streamed. - x-oaiMeta: - dataDescription: "`data` is a [run step delta](/docs/api-reference/assistants-streaming/run-step-delta-object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.step.completed"] - data: - $ref: "#/components/schemas/RunStepObject" - required: - - event - - data - description: Occurs when a [run step](/docs/api-reference/runs/step-object) is completed. - x-oaiMeta: - dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.step.failed"] - data: - $ref: "#/components/schemas/RunStepObject" - required: - - event - - data - description: Occurs when a [run step](/docs/api-reference/runs/step-object) fails. - x-oaiMeta: - dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.step.cancelled"] - data: - $ref: "#/components/schemas/RunStepObject" - required: - - event - - data - description: Occurs when a [run step](/docs/api-reference/runs/step-object) is cancelled. - x-oaiMeta: - dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" - - type: object - properties: - event: - type: string - enum: ["thread.run.step.expired"] - data: - $ref: "#/components/schemas/RunStepObject" - required: - - event - - data - description: Occurs when a [run step](/docs/api-reference/runs/step-object) expires. - x-oaiMeta: - dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" - - MessageStreamEvent: - oneOf: - - type: object - properties: - event: - type: string - enum: ["thread.message.created"] - data: - $ref: "#/components/schemas/MessageObject" - required: - - event - - data - description: Occurs when a [message](/docs/api-reference/messages/object) is created. - x-oaiMeta: - dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" - - type: object - properties: - event: - type: string - enum: ["thread.message.in_progress"] - data: - $ref: "#/components/schemas/MessageObject" - required: - - event - - data - description: Occurs when a [message](/docs/api-reference/messages/object) moves to an `in_progress` state. - x-oaiMeta: - dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" - - type: object - properties: - event: - type: string - enum: ["thread.message.delta"] - data: - $ref: "#/components/schemas/MessageDeltaObject" - required: - - event - - data - description: Occurs when parts of a [Message](/docs/api-reference/messages/object) are being streamed. - x-oaiMeta: - dataDescription: "`data` is a [message delta](/docs/api-reference/assistants-streaming/message-delta-object)" - - type: object - properties: - event: - type: string - enum: ["thread.message.completed"] - data: - $ref: "#/components/schemas/MessageObject" - required: - - event - - data - description: Occurs when a [message](/docs/api-reference/messages/object) is completed. - x-oaiMeta: - dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" - - type: object - properties: - event: - type: string - enum: ["thread.message.incomplete"] - data: - $ref: "#/components/schemas/MessageObject" - required: - - event - - data - description: Occurs when a [message](/docs/api-reference/messages/object) ends before it is completed. - x-oaiMeta: - dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" - - ErrorEvent: - type: object - properties: - event: - type: string - enum: ["error"] - data: - $ref: "#/components/schemas/Error" - required: - - event - - data - description: Occurs when an [error](/docs/guides/error-codes/api-errors) occurs. This can happen due to an internal server error or a timeout. - x-oaiMeta: - dataDescription: "`data` is an [error](/docs/guides/error-codes/api-errors)" - - DoneEvent: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + refusal: + description: A list of message refusal tokens with log probability information. + type: array + items: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + required: + - content + - refusal + finish_reason: + type: string + description: > + The reason the model stopped generating tokens. This will be + `stop` if the model hit a natural stop point or a provided + stop sequence, + + `length` if the maximum number of tokens specified in the + request was reached, + + `content_filter` if content was omitted due to a flag from our + content filters, + + `tool_calls` if the model called a tool, or `function_call` + (deprecated) if the model called a function. + enum: + - stop + - length + - tool_calls + - content_filter + - function_call + nullable: true + index: + type: integer + description: The index of the choice in the list of choices. + created: + type: integer + description: The Unix timestamp (in seconds) of when the chat completion was + created. Each chunk has the same timestamp. + model: + type: string + description: The model to generate the completion. + service_tier: + description: The service tier used for processing the request. This field is + only included if the `service_tier` parameter is specified in the + request. + type: string + enum: + - scale + - default + example: scale + nullable: true + system_fingerprint: + type: string + description: > + This fingerprint represents the backend configuration that the model + runs with. + + Can be used in conjunction with the `seed` request parameter to + understand when backend changes have been made that might impact + determinism. + object: + type: string + description: The object type, which is always `chat.completion.chunk`. + enum: + - chat.completion.chunk + usage: + type: object + nullable: true + description: > + An optional field that will only be present when you set + `stream_options: {"include_usage": true}` in your request. + + When present, it contains a null value except for the last chunk + which contains the token usage statistics for the entire request. + properties: + completion_tokens: + type: integer + description: Number of tokens in the generated completion. + prompt_tokens: + type: integer + description: Number of tokens in the prompt. + total_tokens: + type: integer + description: Total number of tokens used in the request (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion chunk object + group: chat + example: > + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} + + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} + + + .... + + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", + "system_fingerprint": "fp_44709d6fcb", + "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} + CreateCompletionRequest: + type: object + properties: + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + anyOf: + - type: string + - type: string + enum: + - gpt-3.5-turbo-instruct + - davinci-002 + - babbage-002 + x-oaiTypeLabel: string + prompt: + description: > + The prompt(s) to generate completions for, encoded as a string, + array of strings, array of tokens, or array of token arrays. + + + Note that <|endoftext|> is the document separator that the model + sees during training, so if a prompt is not specified the model will + generate as if from the beginning of a new document. + default: <|endoftext|> + nullable: true + oneOf: + - type: string + default: "" + example: This is a test. + - type: array + items: + type: string + default: "" + example: This is a test. + - type: array + minItems: 1 + items: + type: integer + example: "[1212, 318, 257, 1332, 13]" + - type: array + minItems: 1 + items: + type: array + minItems: 1 + items: + type: integer + example: "[[1212, 318, 257, 1332, 13]]" + best_of: + type: integer + default: 1 + minimum: 0 + maximum: 20 + nullable: true + description: > + Generates `best_of` completions server-side and returns the "best" + (the one with the highest log probability per token). Results cannot + be streamed. + + + When used with `n`, `best_of` controls the number of candidate + completions and `n` specifies how many to return – `best_of` must be + greater than `n`. + + + **Note:** Because this parameter generates many completions, it can + quickly consume your token quota. Use carefully and ensure that you + have reasonable settings for `max_tokens` and `stop`. + echo: + type: boolean + default: false + nullable: true + description: | + Echo back the prompt in addition to the completion + frequency_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on their existing frequency in the text so far, decreasing the + model's likelihood to repeat the same line verbatim. + + + [See more information about frequency and presence + penalties.](/docs/guides/text-generation) + logit_bias: + type: object + x-oaiTypeLabel: map + # default: null + nullable: true + additionalProperties: + type: integer + description: > + Modify the likelihood of specified tokens appearing in the + completion. + + + Accepts a JSON object that maps tokens (specified by their token ID + in the GPT tokenizer) to an associated bias value from -100 to 100. + You can use this [tokenizer tool](/tokenizer?view=bpe) to convert + text to token IDs. Mathematically, the bias is added to the logits + generated by the model prior to sampling. The exact effect will vary + per model, but values between -1 and 1 should decrease or increase + likelihood of selection; values like -100 or 100 should result in a + ban or exclusive selection of the relevant token. + + + As an example, you can pass `{"50256": -100}` to prevent the + <|endoftext|> token from being generated. + logprobs: + type: integer + minimum: 0 + maximum: 5 + # default: null + nullable: true + description: > + Include the log probabilities on the `logprobs` most likely output + tokens, as well the chosen tokens. For example, if `logprobs` is 5, + the API will return a list of the 5 most likely tokens. The API will + always return the `logprob` of the sampled token, so there may be up + to `logprobs+1` elements in the response. + + + The maximum value for `logprobs` is 5. + max_tokens: + type: integer + minimum: 0 + default: 16 + example: 16 + nullable: true + description: > + The maximum number of [tokens](/tokenizer) that can be generated in + the completion. + + + The token count of your prompt plus `max_tokens` cannot exceed the + model's context length. [Example Python + code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) + for counting tokens. + n: + type: integer + minimum: 1 + maximum: 128 + default: 1 + example: 1 + nullable: true + description: > + How many completions to generate for each prompt. + + + **Note:** Because this parameter generates many completions, it can + quickly consume your token quota. Use carefully and ensure that you + have reasonable settings for `max_tokens` and `stop`. + presence_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on whether they appear in the text so far, increasing the + model's likelihood to talk about new topics. + + + [See more information about frequency and presence + penalties.](/docs/guides/text-generation) + seed: + type: integer + minimum: -9223372036854776000 + maximum: 9223372036854776000 + nullable: true + description: > + If specified, our system will make a best effort to sample + deterministically, such that repeated requests with the same `seed` + and parameters should return the same result. + + + Determinism is not guaranteed, and you should refer to the + `system_fingerprint` response parameter to monitor changes in the + backend. + stop: + description: > + Up to 4 sequences where the API will stop generating further tokens. + The returned text will not contain the stop sequence. + # default: null + nullable: true + oneOf: + - type: string + default: <|endoftext|> + example: "\n" + nullable: true + - type: array + minItems: 1 + maxItems: 4 + items: + type: string + example: '["\n"]' + stream: + description: > + Whether to stream back partial progress. If set, tokens will be sent + as data-only [server-sent + events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) + as they become available, with the stream terminated by a `data: + [DONE]` message. [Example Python + code](https://cookbook.openai.com/examples/how_to_stream_completions). + type: boolean + nullable: true + default: false + stream_options: + $ref: "#/components/schemas/ChatCompletionStreamOptions" + suffix: + description: | + The suffix that comes after a completion of inserted text. + + This parameter is only supported for `gpt-3.5-turbo-instruct`. + # default: null + nullable: true + type: string + example: test. + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + + + We generally recommend altering this or `top_p` but not both. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or `temperature` but not both. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - model + - prompt + CreateCompletionResponse: + type: object + description: > + Represents a completion response from the API. Note: both the streamed + and non-streamed response objects share the same shape (unlike the chat + endpoint). + properties: + id: + type: string + description: A unique identifier for the completion. + choices: + type: array + description: The list of completion choices the model generated for the input + prompt. + items: type: object - properties: - event: - type: string - enum: ["done"] - data: - type: string - enum: ["[DONE]"] required: - - event - - data - description: Occurs when a stream ends. - x-oaiMeta: - dataDescription: "`data` is `[DONE]`" - - Batch: - type: object + - finish_reason + - index + - logprobs + - text properties: - id: - type: string - object: - type: string - enum: [batch] - description: The object type, which is always `batch`. - endpoint: - type: string - description: The OpenAI API endpoint used by the batch. - - errors: - type: object - properties: - object: - type: string - description: The object type, which is always `list`. - data: - type: array - items: - type: object - properties: - code: - type: string - description: An error code identifying the error type. - message: - type: string - description: A human-readable message providing more details about the error. - param: - type: string - description: The name of the parameter that caused the error, if applicable. - nullable: true - line: - type: integer - description: The line number of the input file where the error occurred, if applicable. - nullable: true - input_file_id: - type: string - description: The ID of the input file for the batch. - completion_window: - type: string - description: The time frame within which the batch should be processed. - status: - type: string - description: The current status of the batch. - enum: - - validating - - failed - - in_progress - - finalizing - - completed - - expired - - cancelling - - cancelled - output_file_id: - type: string - description: The ID of the file containing the outputs of successfully executed requests. - error_file_id: - type: string - description: The ID of the file containing the outputs of requests with errors. - created_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch was created. - in_progress_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch started processing. - expires_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch will expire. - finalizing_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch started finalizing. - completed_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch was completed. - failed_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch failed. - expired_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch expired. - cancelling_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch started cancelling. - cancelled_at: - type: integer - description: The Unix timestamp (in seconds) for when the batch was cancelled. - request_counts: - type: object - properties: - total: - type: integer - description: Total number of requests in the batch. - completed: - type: integer - description: Number of requests that have been completed successfully. - failed: - type: integer - description: Number of requests that have failed. - required: - - total - - completed - - failed - description: The request counts for different statuses within the batch. - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - required: - - id - - object - - endpoint - - input_file_id - - completion_window - - status - - created_at - x-oaiMeta: - name: The batch object - example: *batch_object - - BatchRequestInput: + finish_reason: + type: string + description: > + The reason the model stopped generating tokens. This will be + `stop` if the model hit a natural stop point or a provided + stop sequence, + + `length` if the maximum number of tokens specified in the + request was reached, + + or `content_filter` if content was omitted due to a flag from + our content filters. + enum: + - stop + - length + - content_filter + index: + type: integer + logprobs: + type: object + nullable: true + properties: + text_offset: + type: array + items: + type: integer + token_logprobs: + type: array + items: + type: number + tokens: + type: array + items: + type: string + top_logprobs: + type: array + items: + type: object + additionalProperties: + type: number + text: + type: string + created: + type: integer + description: The Unix timestamp (in seconds) of when the completion was created. + model: + type: string + description: The model used for completion. + system_fingerprint: + type: string + description: > + This fingerprint represents the backend configuration that the model + runs with. + + + Can be used in conjunction with the `seed` request parameter to + understand when backend changes have been made that might impact + determinism. + object: + type: string + description: The object type, which is always "text_completion" + enum: + - text_completion + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - id + - object + - created + - model + - choices + x-oaiMeta: + name: The completion object + legacy: true + example: | + { + "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", + "object": "text_completion", + "created": 1589478378, + "model": "gpt-4-turbo", + "choices": [ + { + "text": "\n\nThis is indeed a test", + "index": 0, + "logprobs": null, + "finish_reason": "length" + } + ], + "usage": { + "prompt_tokens": 5, + "completion_tokens": 7, + "total_tokens": 12 + } + } + CreateEmbeddingRequest: + type: object + additionalProperties: false + properties: + input: + description: > + Input text to embed, encoded as a string or array of tokens. To + embed multiple inputs in a single request, pass an array of strings + or array of token arrays. The input must not exceed the max input + tokens for the model (8192 tokens for `text-embedding-ada-002`), + cannot be an empty string, and any array must be 2048 dimensions or + less. [Example Python + code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) + for counting tokens. + example: The quick brown fox jumped over the lazy dog + oneOf: + - type: string + title: string + description: The string that will be turned into an embedding. + default: "" + example: This is a test. + - type: array + title: array + description: The array of strings that will be turned into an embedding. + minItems: 1 + maxItems: 2048 + items: + type: string + default: "" + example: "['This is a test.']" + - type: array + title: array + description: The array of integers that will be turned into an embedding. + minItems: 1 + maxItems: 2048 + items: + type: integer + example: "[1212, 318, 257, 1332, 13]" + - type: array + title: array + description: The array of arrays containing integers that will be turned into an + embedding. + minItems: 1 + maxItems: 2048 + items: + type: array + minItems: 1 + items: + type: integer + example: "[[1212, 318, 257, 1332, 13]]" + x-oaiExpandable: true + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + example: text-embedding-3-small + anyOf: + - type: string + - type: string + enum: + - text-embedding-ada-002 + - text-embedding-3-small + - text-embedding-3-large + x-oaiTypeLabel: string + encoding_format: + description: The format to return the embeddings in. Can be either `float` or + [`base64`](https://pypi.org/project/pybase64/). + example: float + default: float + type: string + enum: + - float + - base64 + dimensions: + description: > + The number of dimensions the resulting output embeddings should + have. Only supported in `text-embedding-3` and later models. + type: integer + minimum: 1 + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - model + - input + CreateEmbeddingResponse: + type: object + properties: + data: + type: array + description: The list of embeddings generated by the model. + items: + $ref: "#/components/schemas/Embedding" + model: + type: string + description: The name of the model used to generate the embedding. + object: + type: string + description: The object type, which is always "list". + enum: + - list + usage: + type: object + description: The usage information for the request. + properties: + prompt_tokens: + type: integer + description: The number of tokens used by the prompt. + total_tokens: + type: integer + description: The total number of tokens used by the request. + required: + - prompt_tokens + - total_tokens + required: + - object + - model + - data + - usage + CreateFileRequest: + type: object + additionalProperties: false + properties: + file: + description: | + The File object (not file name) to be uploaded. + type: string + format: binary + purpose: + description: > + The intended purpose of the uploaded file. + + + Use "assistants" for [Assistants](/docs/api-reference/assistants) + and [Message](/docs/api-reference/messages) files, "vision" for + Assistants image file inputs, "batch" for [Batch + API](/docs/guides/batch), and "fine-tune" for + [Fine-tuning](/docs/api-reference/fine-tuning). + type: string + enum: + - assistants + - batch + - fine-tune + - vision + required: + - file + - purpose + CreateFineTuningJobRequest: + type: object + properties: + model: + description: > + The name of the model to fine-tune. You can select one of the + + [supported + models](/docs/guides/fine-tuning#which-models-can-be-fine-tuned). + example: gpt-4o-mini + anyOf: + - type: string + - type: string + enum: + - babbage-002 + - davinci-002 + - gpt-3.5-turbo + - gpt-4o-mini + x-oaiTypeLabel: string + training_file: + description: > + The ID of an uploaded file that contains training data. + + + See [upload file](/docs/api-reference/files/create) for how to + upload a file. + + + Your dataset must be formatted as a JSONL file. Additionally, you + must upload your file with the purpose `fine-tune`. + + + The contents of the file should differ depending on if the model + uses the [chat](/docs/api-reference/fine-tuning/chat-input) or + [completions](/docs/api-reference/fine-tuning/completions-input) + format. + + + See the [fine-tuning guide](/docs/guides/fine-tuning) for more + details. + type: string + example: file-abc123 + hyperparameters: + type: object + description: The hyperparameters used for the fine-tuning job. + properties: + batch_size: + description: > + Number of examples in each batch. A larger batch size means that + model parameters + + are updated less frequently, but with lower variance. + oneOf: + - type: string + enum: + - auto + - type: integer + minimum: 1 + maximum: 256 + default: auto + learning_rate_multiplier: + description: > + Scaling factor for the learning rate. A smaller learning rate + may be useful to avoid + + overfitting. + oneOf: + - type: string + enum: + - auto + - type: number + minimum: 0 + exclusiveMinimum: true + default: auto + n_epochs: + description: > + The number of epochs to train the model for. An epoch refers to + one full cycle + + through the training dataset. + oneOf: + - type: string + enum: + - auto + - type: integer + minimum: 1 + maximum: 50 + default: auto + suffix: + description: > + A string of up to 64 characters that will be added to your + fine-tuned model name. + + + For example, a `suffix` of "custom-model-name" would produce a model + name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`. + type: string + minLength: 1 + maxLength: 64 + # default: null + nullable: true + validation_file: + description: > + The ID of an uploaded file that contains validation data. + + + If you provide this file, the data is used to generate validation + + metrics periodically during fine-tuning. These metrics can be viewed + in + + the fine-tuning results file. + + The same data should not be present in both train and validation + files. + + + Your dataset must be formatted as a JSONL file. You must upload your + file with the purpose `fine-tune`. + + + See the [fine-tuning guide](/docs/guides/fine-tuning) for more + details. + type: string + nullable: true + example: file-abc123 + integrations: + type: array + description: A list of integrations to enable for your fine-tuning job. + nullable: true + items: type: object - description: The per-line object of the batch input file + required: + - type + - wandb properties: - custom_id: + type: + description: > + The type of integration to enable. Currently, only "wandb" + (Weights and Biases) is supported. + oneOf: + - type: string + enum: + - wandb + wandb: + type: object + description: > + The settings for your integration with Weights and Biases. + This payload specifies the project that + + metrics will be sent to. Optionally, you can set an explicit + display name for your run, add tags + + to your run, and set a default entity (team, username, etc) to + be associated with your run. + required: + - project + properties: + project: + description: > + The name of the project that the new run will be created + under. type: string - description: A developer-provided per-request id that will be used to match outputs to inputs. Must be unique for each request in a batch. - method: + example: my-wandb-project + name: + description: > + A display name to set for the run. If not set, we will use + the Job ID as the name. + nullable: true type: string - enum: ["POST"] - description: The HTTP method to be used for the request. Currently only `POST` is supported. - url: + entity: + description: > + The entity to use for the run. This allows you to set the + team or username of the WandB user that you would + + like associated with the run. If not set, the default + entity for the registered WandB API key is used. + nullable: true type: string - description: The OpenAI API relative URL to be used for the request. Currently `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. - x-oaiMeta: - name: The request input object - example: | - {"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is 2+2?"}]}} + tags: + description: > + A list of tags to be attached to the newly created run. + These tags are passed through directly to WandB. Some - BatchRequestOutput: + default tags are generated by OpenAI: "openai/finetune", + "openai/{base-model}", "openai/{ftjob-abcdef}". + type: array + items: + type: string + example: custom-tag + seed: + description: > + The seed controls the reproducibility of the job. Passing in the + same seed and job parameters should produce the same results, but + may differ in rare cases. + + If a seed is not specified, one will be generated for you. + type: integer + nullable: true + minimum: 0 + maximum: 2147483647 + example: 42 + required: + - model + - training_file + CreateImageEditRequest: + type: object + properties: + image: + description: The image to edit. Must be a valid PNG file, less than 4MB, and + square. If mask is not provided, image must have transparency, which + will be used as the mask. + type: string + format: binary + prompt: + description: A text description of the desired image(s). The maximum length is + 1000 characters. + type: string + example: A cute baby sea otter wearing a beret + mask: + description: An additional image whose fully transparent areas (e.g. where alpha + is zero) indicate where `image` should be edited. Must be a valid + PNG file, less than 4MB, and have the same dimensions as `image`. + type: string + format: binary + model: + anyOf: + - type: string + - type: string + enum: + - dall-e-2 + x-oaiTypeLabel: string + default: dall-e-2 + example: dall-e-2 + nullable: true + description: The model to use for image generation. Only `dall-e-2` is supported + at this time. + n: + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. + size: + type: string + enum: + - 256x256 + - 512x512 + - 1024x1024 + default: 1024x1024 + example: 1024x1024 + nullable: true + description: The size of the generated images. Must be one of `256x256`, + `512x512`, or `1024x1024`. + response_format: + type: string + enum: + - url + - b64_json + default: url + example: url + nullable: true + description: The format in which the generated images are returned. Must be one + of `url` or `b64_json`. URLs are only valid for 60 minutes after the + image has been generated. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - prompt + - image + CreateImageRequest: + type: object + properties: + prompt: + description: A text description of the desired image(s). The maximum length is + 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`. + type: string + example: A cute baby sea otter + model: + anyOf: + - type: string + - type: string + enum: + - dall-e-2 + - dall-e-3 + x-oaiTypeLabel: string + default: dall-e-2 + example: dall-e-3 + nullable: true + description: The model to use for image generation. + n: + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. For + `dall-e-3`, only `n=1` is supported. + quality: + type: string + enum: + - standard + - hd + default: standard + example: standard + description: The quality of the image that will be generated. `hd` creates + images with finer details and greater consistency across the image. + This param is only supported for `dall-e-3`. + response_format: + type: string + enum: + - url + - b64_json + default: url + example: url + nullable: true + description: The format in which the generated images are returned. Must be one + of `url` or `b64_json`. URLs are only valid for 60 minutes after the + image has been generated. + size: + type: string + enum: + - 256x256 + - 512x512 + - 1024x1024 + - 1792x1024 + - 1024x1792 + default: 1024x1024 + example: 1024x1024 + nullable: true + description: The size of the generated images. Must be one of `256x256`, + `512x512`, or `1024x1024` for `dall-e-2`. Must be one of + `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3` models. + style: + type: string + enum: + - vivid + - natural + default: vivid + example: vivid + nullable: true + description: The style of the generated images. Must be one of `vivid` or + `natural`. Vivid causes the model to lean towards generating + hyper-real and dramatic images. Natural causes the model to produce + more natural, less hyper-real looking images. This param is only + supported for `dall-e-3`. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - prompt + CreateImageVariationRequest: + type: object + properties: + image: + description: The image to use as the basis for the variation(s). Must be a valid + PNG file, less than 4MB, and square. + type: string + format: binary + model: + anyOf: + - type: string + - type: string + enum: + - dall-e-2 + x-oaiTypeLabel: string + default: dall-e-2 + example: dall-e-2 + nullable: true + description: The model to use for image generation. Only `dall-e-2` is supported + at this time. + n: + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. For + `dall-e-3`, only `n=1` is supported. + response_format: + type: string + enum: + - url + - b64_json + default: url + example: url + nullable: true + description: The format in which the generated images are returned. Must be one + of `url` or `b64_json`. URLs are only valid for 60 minutes after the + image has been generated. + size: + type: string + enum: + - 256x256 + - 512x512 + - 1024x1024 + default: 1024x1024 + example: 1024x1024 + nullable: true + description: The size of the generated images. Must be one of `256x256`, + `512x512`, or `1024x1024`. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - image + CreateMessageRequest: + type: object + additionalProperties: false + required: + - role + - content + properties: + role: + type: string + enum: + - user + - assistant + description: > + The role of the entity that is creating the message. Allowed values + include: + + - `user`: Indicates the message is sent by an actual user and should + be used in most cases to represent user-generated messages. + + - `assistant`: Indicates the message is generated by the assistant. + Use this value to insert messages from the assistant into the + conversation. + content: + oneOf: + - type: string + description: The text contents of the message. + title: Text content + - type: array + description: An array of content parts with a defined type, each can be of type + `text` or images can be passed with `image_url` or `image_file`. + Image types are only supported on [Vision-compatible + models](/docs/models). + title: Array of content parts + items: + oneOf: + - $ref: "#/components/schemas/MessageContentImageFileObject" + - $ref: "#/components/schemas/MessageContentImageUrlObject" + - $ref: "#/components/schemas/MessageRequestContentTextObject" + x-oaiExpandable: true + minItems: 1 + x-oaiExpandable: true + attachments: + type: array + items: type: object - description: The per-line object of the batch output and error files properties: - id: - type: string - custom_id: - type: string - description: A developer-provided per-request id that will be used to match outputs to inputs. - response: - type: object - nullable: true + file_id: + type: string + description: The ID of the file to attach to the message. + tools: + description: The tools to add this file to. + type: array + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearchTypeOnly" + x-oaiExpandable: true + description: A list of files attached to the message, and the tools they should + be added to. + required: + - file_id + - tools + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + CreateModerationRequest: + type: object + properties: + input: + description: > + Input (or inputs) to classify. Can be a single string, an array of + strings, or + + an array of multi-modal input objects similar to other models. + oneOf: + - type: string + description: A string of text to classify for moderation. + default: "" + example: I want to kill them. + - type: array + description: An array of strings to classify for moderation. + items: + type: string + default: "" + example: I want to kill them. + - type: array + description: An array of multi-modal inputs to the moderation model. + items: + x-oaiExpandable: true + oneOf: + - type: object + description: An object describing an image to classify. properties: - status_code: - type: integer - description: The HTTP status code of the response - request_id: + type: + description: Always `image_url`. + type: string + enum: + - image_url + image_url: + type: object + description: Contains either an image URL or a data URL for a base64 encoded + image. + properties: + url: type: string - description: An unique identifier for the OpenAI API request. Please include this request ID when contacting support. - body: - type: object - x-oaiTypeLabel: map - description: The JSON body of the response - error: - type: object - nullable: true - description: For requests that failed with a non-HTTP error, this will contain more information on the cause of the failure. + description: Either a URL of the image or the base64 encoded image data. + format: uri + example: https://example.com/image.jpg + required: + - url + required: + - type + - image_url + - type: object + description: An object describing text to classify. properties: - code: - type: string - description: A machine-readable error code. - message: - type: string - description: A human-readable error message. - x-oaiMeta: - name: The request output object - example: | - {"id": "batch_req_wnaDys", "custom_id": "request-2", "response": {"status_code": 200, "request_id": "req_c187b3", "body": {"id": "chatcmpl-9758Iw", "object": "chat.completion", "created": 1711475054, "model": "gpt-3.5-turbo", "choices": [{"index": 0, "message": {"role": "assistant", "content": "2 + 2 equals 4."}, "finish_reason": "stop"}], "usage": {"prompt_tokens": 24, "completion_tokens": 15, "total_tokens": 39}, "system_fingerprint": null}}, "error": null} - - ListBatchesResponse: + type: + description: Always `text`. + type: string + enum: + - text + text: + description: A string of text to classify. + type: string + example: I want to kill them + required: + - type + - text + x-oaiExpandable: true + model: + description: | + The content moderation model you would like to use. Learn more in + [the moderation guide](/docs/guides/moderation), and learn about + available models [here](/docs/models#moderation). + nullable: false + default: omni-moderation-latest + example: omni-moderation-2024-09-26 + anyOf: + - type: string + - type: string + enum: + - omni-moderation-latest + - omni-moderation-2024-09-26 + - text-moderation-latest + - text-moderation-stable + x-oaiTypeLabel: string + required: + - input + CreateModerationResponse: + type: object + description: Represents if a given text input is potentially harmful. + properties: + id: + type: string + description: The unique identifier for the moderation request. + model: + type: string + description: The model used to generate the moderation results. + results: + type: array + description: A list of moderation objects. + items: type: object properties: - data: + flagged: + type: boolean + description: Whether any of the below categories are flagged. + categories: + type: object + description: A list of the categories, and whether they are flagged or not. + properties: + hate: + type: boolean + description: Content that expresses, incites, or promotes hate based on race, + gender, ethnicity, religion, nationality, sexual + orientation, disability status, or caste. Hateful content + aimed at non-protected groups (e.g., chess players) is + harassment. + hate/threatening: + type: boolean + description: Hateful content that also includes violence or serious harm towards + the targeted group based on race, gender, ethnicity, + religion, nationality, sexual orientation, disability + status, or caste. + harassment: + type: boolean + description: Content that expresses, incites, or promotes harassing language + towards any target. + harassment/threatening: + type: boolean + description: Harassment content that also includes violence or serious harm + towards any target. + illicit: + type: boolean + description: Content that includes instructions or advice that facilitate the + planning or execution of wrongdoing, or that gives advice + or instruction on how to commit illicit acts. For example, + "how to shoplift" would fit this category. + illicit/violent: + type: boolean + description: Content that includes instructions or advice that facilitate the + planning or execution of wrongdoing that also includes + violence, or that gives advice or instruction on the + procurement of any weapon. + self-harm: + type: boolean + description: Content that promotes, encourages, or depicts acts of self-harm, + such as suicide, cutting, and eating disorders. + self-harm/intent: + type: boolean + description: Content where the speaker expresses that they are engaging or + intend to engage in acts of self-harm, such as suicide, + cutting, and eating disorders. + self-harm/instructions: + type: boolean + description: Content that encourages performing acts of self-harm, such as + suicide, cutting, and eating disorders, or that gives + instructions or advice on how to commit such acts. + sexual: + type: boolean + description: Content meant to arouse sexual excitement, such as the description + of sexual activity, or that promotes sexual services + (excluding sex education and wellness). + sexual/minors: + type: boolean + description: Sexual content that includes an individual who is under 18 years + old. + violence: + type: boolean + description: Content that depicts death, violence, or physical injury. + violence/graphic: + type: boolean + description: Content that depicts death, violence, or physical injury in graphic + detail. + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - illicit + - illicit/violent + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic + category_scores: + type: object + description: A list of the categories along with their scores as predicted by + model. + properties: + hate: + type: number + description: The score for the category 'hate'. + hate/threatening: + type: number + description: The score for the category 'hate/threatening'. + harassment: + type: number + description: The score for the category 'harassment'. + harassment/threatening: + type: number + description: The score for the category 'harassment/threatening'. + illicit: + type: number + description: The score for the category 'illicit'. + illicit/violent: + type: number + description: The score for the category 'illicit/violent'. + self-harm: + type: number + description: The score for the category 'self-harm'. + self-harm/intent: + type: number + description: The score for the category 'self-harm/intent'. + self-harm/instructions: + type: number + description: The score for the category 'self-harm/instructions'. + sexual: + type: number + description: The score for the category 'sexual'. + sexual/minors: + type: number + description: The score for the category 'sexual/minors'. + violence: + type: number + description: The score for the category 'violence'. + violence/graphic: + type: number + description: The score for the category 'violence/graphic'. + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - illicit + - illicit/violent + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic + category_applied_input_types: + type: object + description: A list of the categories along with the input type(s) that the + score applies to. + properties: + hate: type: array + description: The applied input type(s) for the category 'hate'. items: - $ref: "#/components/schemas/Batch" - first_id: - type: string - example: "batch_abc123" - last_id: - type: string - example: "batch_abc456" - has_more: - type: boolean - object: - type: string - enum: [list] + type: string + enum: + - text + hate/threatening: + type: array + description: The applied input type(s) for the category 'hate/threatening'. + items: + type: string + enum: + - text + harassment: + type: array + description: The applied input type(s) for the category 'harassment'. + items: + type: string + enum: + - text + harassment/threatening: + type: array + description: The applied input type(s) for the category + 'harassment/threatening'. + items: + type: string + enum: + - text + illicit: + type: array + description: The applied input type(s) for the category 'illicit'. + items: + type: string + enum: + - text + illicit/violent: + type: array + description: The applied input type(s) for the category 'illicit/violent'. + items: + type: string + enum: + - text + self-harm: + type: array + description: The applied input type(s) for the category 'self-harm'. + items: + type: string + enum: + - text + - image + self-harm/intent: + type: array + description: The applied input type(s) for the category 'self-harm/intent'. + items: + type: string + enum: + - text + - image + self-harm/instructions: + type: array + description: The applied input type(s) for the category + 'self-harm/instructions'. + items: + type: string + enum: + - text + - image + sexual: + type: array + description: The applied input type(s) for the category 'sexual'. + items: + type: string + enum: + - text + - image + sexual/minors: + type: array + description: The applied input type(s) for the category 'sexual/minors'. + items: + type: string + enum: + - text + violence: + type: array + description: The applied input type(s) for the category 'violence'. + items: + type: string + enum: + - text + - image + violence/graphic: + type: array + description: The applied input type(s) for the category 'violence/graphic'. + items: + type: string + enum: + - text + - image + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - illicit + - illicit/violent + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic required: - - object - - data - - has_more - -security: - - ApiKeyAuth: [] - -x-oaiMeta: - navigationGroups: - - id: endpoints - title: Endpoints - - id: assistants - title: Assistants - - id: legacy - title: Legacy - groups: - # > General Notes - # The `groups` section is used to generate the API reference pages and navigation, in the same - # order listed below. Additionally, each `group` can have a list of `sections`, each of which - # will become a navigation subroute and subsection under the group. Each section has: - # - `type`: Currently, either an `endpoint` or `object`, depending on how the section needs to - # be rendered - # - `key`: The reference key that can be used to lookup the section definition - # - `path`: The path (url) of the section, which is used to generate the navigation link. - # - # > The `object` sections maps to a schema component and the following fields are read for rendering - # - `x-oaiMeta.name`: The name of the object, which will become the section title - # - `x-oaiMeta.example`: The example object, which will be used to generate the example sample (always JSON) - # - `description`: The description of the object, which will be used to generate the section description - # - # > The `endpoint` section maps to an operation path and the following fields are read for rendering: - # - `x-oaiMeta.name`: The name of the endpoint, which will become the section title - # - `x-oaiMeta.examples`: The endpoint examples, which can be an object (meaning a single variation, most - # endpoints, or an array of objects, meaning multiple variations, e.g. the - # chat completion and completion endpoints, with streamed and non-streamed examples. - # - `x-oaiMeta.returns`: text describing what the endpoint returns. - # - `summary`: The summary of the endpoint, which will be used to generate the section description - - id: audio - title: Audio - description: | - Learn how to turn audio into text or text into audio. - - Related guide: [Speech to text](/docs/guides/speech-to-text) - navigationGroup: endpoints - sections: - - type: endpoint - key: createSpeech - path: createSpeech - - type: endpoint - key: createTranscription - path: createTranscription - - type: endpoint - key: createTranslation - path: createTranslation - - type: object - key: CreateTranscriptionResponseJson - path: json-object - - type: object - key: CreateTranscriptionResponseVerboseJson - path: verbose-json-object - - id: chat - title: Chat - description: | - Given a list of messages comprising a conversation, the model will return a response. - - Related guide: [Chat Completions](/docs/guides/text-generation) - navigationGroup: endpoints - sections: - - type: endpoint - key: createChatCompletion - path: create - - type: object - key: CreateChatCompletionResponse - path: object - - type: object - key: CreateChatCompletionStreamResponse - path: streaming - - id: embeddings - title: Embeddings - description: | - Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. - - Related guide: [Embeddings](/docs/guides/embeddings) - navigationGroup: endpoints - sections: - - type: endpoint - key: createEmbedding - path: create - - type: object - key: Embedding - path: object - - id: fine-tuning - title: Fine-tuning - description: | - Manage fine-tuning jobs to tailor a model to your specific training data. - - Related guide: [Fine-tune models](/docs/guides/fine-tuning) - navigationGroup: endpoints - sections: - - type: endpoint - key: createFineTuningJob - path: create - - type: endpoint - key: listPaginatedFineTuningJobs - path: list - - type: endpoint - key: listFineTuningEvents - path: list-events - - type: endpoint - key: listFineTuningJobCheckpoints - path: list-checkpoints - - type: endpoint - key: retrieveFineTuningJob - path: retrieve - - type: endpoint - key: cancelFineTuningJob - path: cancel - - type: object - key: FinetuneChatRequestInput - path: chat-input - - type: object - key: FinetuneCompletionRequestInput - path: completions-input - - type: object - key: FineTuningJob - path: object - - type: object - key: FineTuningJobEvent - path: event-object - - type: object - key: FineTuningJobCheckpoint - path: checkpoint-object - - id: batch - title: Batch - description: | - Create large batches of API requests for asynchronous processing. The Batch API returns completions within 24 hours for a 50% discount. - - Related guide: [Batch](/docs/guides/batch) - navigationGroup: endpoints - sections: - - type: endpoint - key: createBatch - path: create - - type: endpoint - key: retrieveBatch - path: retrieve - - type: endpoint - key: cancelBatch - path: cancel - - type: endpoint - key: listBatches - path: list - - type: object - key: Batch - path: object - - type: object - key: BatchRequestInput - path: request-input - - type: object - key: BatchRequestOutput - path: request-output - - id: files - title: Files - description: | - Files are used to upload documents that can be used with features like [Assistants](/docs/api-reference/assistants), [Fine-tuning](/docs/api-reference/fine-tuning), and [Batch API](/docs/guides/batch). - navigationGroup: endpoints - sections: - - type: endpoint - key: createFile - path: create - - type: endpoint - key: listFiles - path: list - - type: endpoint - key: retrieveFile - path: retrieve - - type: endpoint - key: deleteFile - path: delete - - type: endpoint - key: downloadFile - path: retrieve-contents - - type: object - key: OpenAIFile - path: object - - id: uploads - title: Uploads + - flagged + - categories + - category_scores + - category_applied_input_types + required: + - id + - model + - results + x-oaiMeta: + name: The moderation object + example: | + { + "id": "modr-0d9740456c391e43c445bf0f010940c7", + "model": "omni-moderation-latest", + "results": [ + { + "flagged": true, + "categories": { + "harassment": true, + "harassment/threatening": true, + "sexual": false, + "hate": false, + "hate/threatening": false, + "illicit": false, + "illicit/violent": false, + "self-harm/intent": false, + "self-harm/instructions": false, + "self-harm": false, + "sexual/minors": false, + "violence": true, + "violence/graphic": true + }, + "category_scores": { + "harassment": 0.8189693396524255, + "harassment/threatening": 0.804985420696006, + "sexual": 1.573112165348997e-6, + "hate": 0.007562942636942845, + "hate/threatening": 0.004208854591835476, + "illicit": 0.030535955153511665, + "illicit/violent": 0.008925306722380033, + "self-harm/intent": 0.00023023930975076432, + "self-harm/instructions": 0.0002293869201073356, + "self-harm": 0.012598046106750154, + "sexual/minors": 2.212566909570261e-8, + "violence": 0.9999992735124786, + "violence/graphic": 0.843064871157054 + }, + "category_applied_input_types": { + "harassment": [ + "text" + ], + "harassment/threatening": [ + "text" + ], + "sexual": [ + "text", + "image" + ], + "hate": [ + "text" + ], + "hate/threatening": [ + "text" + ], + "illicit": [ + "text" + ], + "illicit/violent": [ + "text" + ], + "self-harm/intent": [ + "text", + "image" + ], + "self-harm/instructions": [ + "text", + "image" + ], + "self-harm": [ + "text", + "image" + ], + "sexual/minors": [ + "text" + ], + "violence": [ + "text", + "image" + ], + "violence/graphic": [ + "text", + "image" + ] + } + } + ] + } + CreateRunRequest: + type: object + additionalProperties: false + properties: + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) to use to + execute this run. + type: string + model: + description: The ID of the [Model](/docs/api-reference/models) to be used to + execute this run. If a value is provided here, it will override the + model associated with the assistant. If not, the model associated + with the assistant will be used. + example: gpt-4o + anyOf: + - type: string + - type: string + enum: + - gpt-4o + - gpt-4o-2024-11-20 + - gpt-4o-2024-08-06 + - gpt-4o-2024-05-13 + - gpt-4o-mini + - gpt-4o-mini-2024-07-18 + - gpt-4-turbo + - gpt-4-turbo-2024-04-09 + - gpt-4-0125-preview + - gpt-4-turbo-preview + - gpt-4-1106-preview + - gpt-4-vision-preview + - gpt-4 + - gpt-4-0314 + - gpt-4-0613 + - gpt-4-32k + - gpt-4-32k-0314 + - gpt-4-32k-0613 + - gpt-3.5-turbo + - gpt-3.5-turbo-16k + - gpt-3.5-turbo-0613 + - gpt-3.5-turbo-1106 + - gpt-3.5-turbo-0125 + - gpt-3.5-turbo-16k-0613 + x-oaiTypeLabel: string + nullable: true + instructions: + description: Overrides the + [instructions](/docs/api-reference/assistants/createAssistant) of + the assistant. This is useful for modifying the behavior on a + per-run basis. + type: string + nullable: true + additional_instructions: + description: Appends additional instructions at the end of the instructions for + the run. This is useful for modifying the behavior on a per-run + basis without overriding other instructions. + type: string + nullable: true + additional_messages: + description: Adds additional messages to the thread before creating the run. + type: array + items: + $ref: "#/components/schemas/CreateMessageRequest" + nullable: true + tools: + description: Override the tools the assistant can use for this run. This is + useful for modifying the behavior on a per-run basis. + nullable: true + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + stream: + type: boolean + nullable: true + description: > + If `true`, returns a stream of events that happen during the Run as + server-sent events, terminating when the Run enters a terminal state + with a `data: [DONE]` message. + max_prompt_tokens: + type: integer + nullable: true + description: > + The maximum number of prompt tokens that may be used over the course + of the run. The run will make a best effort to use only the number + of prompt tokens specified, across multiple turns of the run. If the + run exceeds the number of prompt tokens specified, the run will end + with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + max_completion_tokens: + type: integer + nullable: true + description: > + The maximum number of completion tokens that may be used over the + course of the run. The run will make a best effort to use only the + number of completion tokens specified, across multiple turns of the + run. If the run exceeds the number of completion tokens specified, + the run will end with status `incomplete`. See `incomplete_details` + for more info. + minimum: 256 + truncation_strategy: + $ref: "#/components/schemas/TruncationObject" + nullable: true + tool_choice: + $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + nullable: true + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - assistant_id + CreateSpeechRequest: + type: object + additionalProperties: false + properties: + model: + description: > + One of the available [TTS models](/docs/models#tts): `tts-1` or + `tts-1-hd` + anyOf: + - type: string + - type: string + enum: + - tts-1 + - tts-1-hd + x-oaiTypeLabel: string + input: + type: string + description: The text to generate audio for. The maximum length is 4096 + characters. + maxLength: 4096 + voice: + description: The voice to use when generating the audio. Supported voices are + `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of + the voices are available in the [Text to speech + guide](/docs/guides/text-to-speech#voice-options). + type: string + enum: + - alloy + - echo + - fable + - onyx + - nova + - shimmer + response_format: + description: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, + `flac`, `wav`, and `pcm`. + default: mp3 + type: string + enum: + - mp3 + - opus + - aac + - flac + - wav + - pcm + speed: + description: The speed of the generated audio. Select a value from `0.25` to + `4.0`. `1.0` is the default. + type: number + default: 1 + minimum: 0.25 + maximum: 4 + required: + - model + - input + - voice + CreateThreadAndRunRequest: + type: object + additionalProperties: false + properties: + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) to use to + execute this run. + type: string + thread: + $ref: "#/components/schemas/CreateThreadRequest" + description: If no thread is provided, an empty thread will be created. + model: + description: The ID of the [Model](/docs/api-reference/models) to be used to + execute this run. If a value is provided here, it will override the + model associated with the assistant. If not, the model associated + with the assistant will be used. + example: gpt-4o + anyOf: + - type: string + - type: string + enum: + - gpt-4o + - gpt-4o-2024-11-20 + - gpt-4o-2024-08-06 + - gpt-4o-2024-05-13 + - gpt-4o-mini + - gpt-4o-mini-2024-07-18 + - gpt-4-turbo + - gpt-4-turbo-2024-04-09 + - gpt-4-0125-preview + - gpt-4-turbo-preview + - gpt-4-1106-preview + - gpt-4-vision-preview + - gpt-4 + - gpt-4-0314 + - gpt-4-0613 + - gpt-4-32k + - gpt-4-32k-0314 + - gpt-4-32k-0613 + - gpt-3.5-turbo + - gpt-3.5-turbo-16k + - gpt-3.5-turbo-0613 + - gpt-3.5-turbo-1106 + - gpt-3.5-turbo-0125 + - gpt-3.5-turbo-16k-0613 + x-oaiTypeLabel: string + nullable: true + instructions: + description: Override the default system message of the assistant. This is + useful for modifying the behavior on a per-run basis. + type: string + nullable: true + tools: + description: Override the tools the assistant can use for this run. This is + useful for modifying the behavior on a per-run basis. + nullable: true + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The ID of the [vector + store](/docs/api-reference/vector-stores/object) attached to + this assistant. There can be a maximum of 1 vector store + attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + stream: + type: boolean + nullable: true + description: > + If `true`, returns a stream of events that happen during the Run as + server-sent events, terminating when the Run enters a terminal state + with a `data: [DONE]` message. + max_prompt_tokens: + type: integer + nullable: true + description: > + The maximum number of prompt tokens that may be used over the course + of the run. The run will make a best effort to use only the number + of prompt tokens specified, across multiple turns of the run. If the + run exceeds the number of prompt tokens specified, the run will end + with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + max_completion_tokens: + type: integer + nullable: true + description: > + The maximum number of completion tokens that may be used over the + course of the run. The run will make a best effort to use only the + number of completion tokens specified, across multiple turns of the + run. If the run exceeds the number of completion tokens specified, + the run will end with status `incomplete`. See `incomplete_details` + for more info. + minimum: 256 + truncation_strategy: + $ref: "#/components/schemas/TruncationObject" + nullable: true + tool_choice: + $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + nullable: true + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - assistant_id + CreateThreadRequest: + type: object + additionalProperties: false + properties: + messages: + description: A list of [messages](/docs/api-reference/messages) to start the + thread with. + type: array + items: + $ref: "#/components/schemas/CreateMessageRequest" + tool_resources: + type: object + description: > + A set of resources that are made available to the assistant's tools + in this thread. The resources are specific to the type of tool. For + example, the `code_interpreter` tool requires a list of file IDs, + while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this thread. There can be a maximum of 1 vector + store attached to the thread. + maxItems: 1 + items: + type: string + vector_stores: + type: array + description: > + A helper to create a [vector + store](/docs/api-reference/vector-stores/object) with + file_ids and attach it to this thread. There can be a + maximum of 1 vector store attached to the thread. + maxItems: 1 + items: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs to add + to the vector store. There can be a maximum of 10000 + files in a vector store. + maxItems: 10000 + items: + type: string + chunking_strategy: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. + oneOf: + - type: object + title: Auto Chunking Strategy + description: The default strategy. This strategy currently uses a + `max_chunk_size_tokens` of `800` and + `chunk_overlap_tokens` of `400`. + additionalProperties: false + properties: + type: + type: string + description: Always `auto`. + enum: + - auto + required: + - type + - type: object + title: Static Chunking Strategy + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + static: + type: object + additionalProperties: false + properties: + max_chunk_size_tokens: + type: integer + minimum: 100 + maximum: 4096 + description: The maximum number of tokens in each chunk. The default value is + `800`. The minimum value is `100` and the + maximum value is `4096`. + chunk_overlap_tokens: + type: integer + description: > + The number of tokens that overlap between + chunks. The default value is `400`. + + + Note that the overlap must not exceed half + of `max_chunk_size_tokens`. + required: + - max_chunk_size_tokens + - chunk_overlap_tokens + required: + - type + - static + x-oaiExpandable: true + metadata: + type: object + description: > + Set of 16 key-value pairs that can be attached to a + vector store. This can be useful for storing + additional information about the vector store in a + structured format. Keys can be a maximum of 64 + characters long and values can be a maximum of 512 + characters long. + x-oaiTypeLabel: map + x-oaiExpandable: true + oneOf: + - required: + - vector_store_ids + - required: + - vector_stores + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + CreateTranscriptionRequest: + type: object + additionalProperties: false + properties: + file: + description: > + The audio file object (not file name) to transcribe, in one of these + formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + type: string + x-oaiTypeLabel: file + format: binary + model: + description: > + ID of the model to use. Only `whisper-1` (which is powered by our + open source Whisper V2 model) is currently available. + example: whisper-1 + anyOf: + - type: string + - type: string + enum: + - whisper-1 + x-oaiTypeLabel: string + language: + description: > + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) + format will improve accuracy and latency. + type: string + prompt: + description: > + An optional text to guide the model's style or continue a previous + audio segment. The [prompt](/docs/guides/speech-to-text#prompting) + should match the audio language. + type: string + response_format: + $ref: "#/components/schemas/AudioResponseFormat" + temperature: + description: > + The sampling temperature, between 0 and 1. Higher values like 0.8 + will make the output more random, while lower values like 0.2 will + make it more focused and deterministic. If set to 0, the model will + use [log probability](https://en.wikipedia.org/wiki/Log_probability) + to automatically increase the temperature until certain thresholds + are hit. + type: number + default: 0 + timestamp_granularities[]: + description: > + The timestamp granularities to populate for this transcription. + `response_format` must be set `verbose_json` to use timestamp + granularities. Either or both of these options are supported: + `word`, or `segment`. Note: There is no additional latency for + segment timestamps, but generating word timestamps incurs additional + latency. + type: array + items: + type: string + enum: + - word + - segment + default: + - segment + required: + - file + - model + CreateTranscriptionResponseJson: + type: object + description: Represents a transcription response returned by model, based on the + provided input. + properties: + text: + type: string + description: The transcribed text. + required: + - text + x-oaiMeta: + name: The transcription object (JSON) + group: audio + example: > + { + "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that." + } + CreateTranscriptionResponseVerboseJson: + type: object + description: Represents a verbose json transcription response returned by model, + based on the provided input. + properties: + language: + type: string + description: The language of the input audio. + duration: + type: string + description: The duration of the input audio. + text: + type: string + description: The transcribed text. + words: + type: array + description: Extracted words and their corresponding timestamps. + items: + $ref: "#/components/schemas/TranscriptionWord" + segments: + type: array + description: Segments of the transcribed text and their corresponding details. + items: + $ref: "#/components/schemas/TranscriptionSegment" + required: + - language + - duration + - text + x-oaiMeta: + name: The transcription object (Verbose JSON) + group: audio + example: > + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "segments": [ + { + "id": 0, + "seek": 0, + "start": 0.0, + "end": 3.319999933242798, + "text": " The beach was a popular spot on a hot summer day.", + "tokens": [ + 50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530 + ], + "temperature": 0.0, + "avg_logprob": -0.2860786020755768, + "compression_ratio": 1.2363636493682861, + "no_speech_prob": 0.00985979475080967 + }, + ... + ] + } + CreateTranslationRequest: + type: object + additionalProperties: false + properties: + file: + description: > + The audio file object (not file name) translate, in one of these + formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + type: string + x-oaiTypeLabel: file + format: binary + model: + description: > + ID of the model to use. Only `whisper-1` (which is powered by our + open source Whisper V2 model) is currently available. + example: whisper-1 + anyOf: + - type: string + - type: string + enum: + - whisper-1 + x-oaiTypeLabel: string + prompt: + description: > + An optional text to guide the model's style or continue a previous + audio segment. The [prompt](/docs/guides/speech-to-text#prompting) + should be in English. + type: string + response_format: + $ref: "#/components/schemas/AudioResponseFormat" + temperature: + description: > + The sampling temperature, between 0 and 1. Higher values like 0.8 + will make the output more random, while lower values like 0.2 will + make it more focused and deterministic. If set to 0, the model will + use [log probability](https://en.wikipedia.org/wiki/Log_probability) + to automatically increase the temperature until certain thresholds + are hit. + type: number + default: 0 + required: + - file + - model + CreateTranslationResponseJson: + type: object + properties: + text: + type: string + required: + - text + CreateTranslationResponseVerboseJson: + type: object + properties: + language: + type: string + description: The language of the output translation (always `english`). + duration: + type: string + description: The duration of the input audio. + text: + type: string + description: The translated text. + segments: + type: array + description: Segments of the translated text and their corresponding details. + items: + $ref: "#/components/schemas/TranscriptionSegment" + required: + - language + - duration + - text + CreateUploadRequest: + type: object + additionalProperties: false + properties: + filename: description: | - Allows you to upload large files in multiple parts. - navigationGroup: endpoints - sections: - - type: endpoint - key: createUpload - path: create - - type: endpoint - key: addUploadPart - path: add-part - - type: endpoint - key: completeUpload - path: complete - - type: endpoint - key: cancelUpload - path: cancel - - type: object - key: Upload - path: object - - type: object - key: UploadPart - path: part-object - - id: images - title: Images + The name of the file to upload. + type: string + purpose: + description: > + The intended purpose of the uploaded file. + + + See the [documentation on File + purposes](/docs/api-reference/files/create#files-create-purpose). + type: string + enum: + - assistants + - batch + - fine-tune + - vision + bytes: description: | - Given a prompt and/or an input image, the model will generate a new image. - - Related guide: [Image generation](/docs/guides/images) - navigationGroup: endpoints - sections: - - type: endpoint - key: createImage - path: create - - type: endpoint - key: createImageEdit - path: createEdit - - type: endpoint - key: createImageVariation - path: createVariation - - type: object - key: Image - path: object - - id: models - title: Models + The number of bytes in the file you are uploading. + type: integer + mime_type: + description: > + The MIME type of the file. + + + This must fall within the supported MIME types for your file + purpose. See the supported MIME types for assistants and vision. + type: string + required: + - filename + - purpose + - bytes + - mime_type + CreateVectorStoreFileBatchRequest: + type: object + additionalProperties: false + properties: + file_ids: + description: A list of [File](/docs/api-reference/files) IDs that the vector + store should use. Useful for tools like `file_search` that can + access files. + type: array + minItems: 1 + maxItems: 500 + items: + type: string + chunking_strategy: + $ref: "#/components/schemas/ChunkingStrategyRequestParam" + required: + - file_ids + CreateVectorStoreFileRequest: + type: object + additionalProperties: false + properties: + file_id: + description: A [File](/docs/api-reference/files) ID that the vector store should + use. Useful for tools like `file_search` that can access files. + type: string + chunking_strategy: + $ref: "#/components/schemas/ChunkingStrategyRequestParam" + required: + - file_id + CreateVectorStoreRequest: + type: object + additionalProperties: false + properties: + file_ids: + description: A list of [File](/docs/api-reference/files) IDs that the vector + store should use. Useful for tools like `file_search` that can + access files. + type: array + maxItems: 500 + items: + type: string + name: + description: The name of the vector store. + type: string + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + chunking_strategy: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. Only applicable if `file_ids` is non-empty. + oneOf: + - $ref: "#/components/schemas/AutoChunkingStrategyRequestParam" + - $ref: "#/components/schemas/StaticChunkingStrategyRequestParam" + x-oaiExpandable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + DefaultProjectErrorResponse: + type: object + properties: + code: + type: integer + message: + type: string + required: + - code + - message + DeleteAssistantResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - assistant.deleted + required: + - id + - object + - deleted + DeleteFileResponse: + type: object + properties: + id: + type: string + object: + type: string + enum: + - file + deleted: + type: boolean + required: + - id + - object + - deleted + DeleteMessageResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - thread.message.deleted + required: + - id + - object + - deleted + DeleteModelResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + required: + - id + - object + - deleted + DeleteThreadResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - thread.deleted + required: + - id + - object + - deleted + DeleteVectorStoreFileResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - vector_store.file.deleted + required: + - id + - object + - deleted + DeleteVectorStoreResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - vector_store.deleted + required: + - id + - object + - deleted + DoneEvent: + type: object + properties: + event: + type: string + enum: + - done + data: + type: string + enum: + - "[DONE]" + required: + - event + - data + description: Occurs when a stream ends. + x-oaiMeta: + dataDescription: "`data` is `[DONE]`" + Embedding: + type: object + description: | + Represents an embedding vector returned by embedding endpoint. + properties: + index: + type: integer + description: The index of the embedding in the list of embeddings. + embedding: + type: array + description: > + The embedding vector, which is a list of floats. The length of + vector depends on the model as listed in the [embedding + guide](/docs/guides/embeddings). + items: + type: number + object: + type: string + description: The object type, which is always "embedding". + enum: + - embedding + required: + - index + - object + - embedding + x-oaiMeta: + name: The embedding object + example: | + { + "object": "embedding", + "embedding": [ + 0.0023064255, + -0.009327292, + .... (1536 floats total for ada-002) + -0.0028842222, + ], + "index": 0 + } + Error: + type: object + properties: + code: + type: string + nullable: true + message: + type: string + nullable: false + param: + type: string + nullable: true + type: + type: string + nullable: false + required: + - type + - message + - param + - code + ErrorEvent: + type: object + properties: + event: + type: string + enum: + - error + data: + $ref: "#/components/schemas/Error" + required: + - event + - data + description: Occurs when an [error](/docs/guides/error-codes#api-errors) occurs. + This can happen due to an internal server error or a timeout. + x-oaiMeta: + dataDescription: "`data` is an [error](/docs/guides/error-codes#api-errors)" + ErrorResponse: + type: object + properties: + error: + $ref: "#/components/schemas/Error" + required: + - error + FileSearchRankingOptions: + title: File search tool call ranking options + type: object + description: > + The ranking options for the file search. If not specified, the file + search tool will use the `auto` ranker and a score_threshold of 0. + + + See the [file search tool + documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) + for more information. + properties: + ranker: + type: string + description: The ranker to use for the file search. If not specified will use + the `auto` ranker. + enum: + - auto + - default_2024_08_21 + score_threshold: + type: number + description: The score threshold for the file search. All values must be a + floating point number between 0 and 1. + minimum: 0 + maximum: 1 + required: + - score_threshold + FineTuneChatCompletionRequestAssistantMessage: + allOf: + - type: object + title: Assistant message + deprecated: false + properties: + weight: + type: integer + enum: + - 0 + - 1 + description: Controls whether the assistant message is trained against (0 or 1) + - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" + required: + - role + FineTuningIntegration: + type: object + title: Fine-Tuning Job Integration + required: + - type + - wandb + properties: + type: + type: string + description: The type of the integration being enabled for the fine-tuning job + enum: + - wandb + wandb: + type: object + description: > + The settings for your integration with Weights and Biases. This + payload specifies the project that + + metrics will be sent to. Optionally, you can set an explicit display + name for your run, add tags + + to your run, and set a default entity (team, username, etc) to be + associated with your run. + required: + - project + properties: + project: + description: | + The name of the project that the new run will be created under. + type: string + example: my-wandb-project + name: + description: > + A display name to set for the run. If not set, we will use the + Job ID as the name. + nullable: true + type: string + entity: + description: > + The entity to use for the run. This allows you to set the team + or username of the WandB user that you would + + like associated with the run. If not set, the default entity for + the registered WandB API key is used. + nullable: true + type: string + tags: + description: > + A list of tags to be attached to the newly created run. These + tags are passed through directly to WandB. Some + + default tags are generated by OpenAI: "openai/finetune", + "openai/{base-model}", "openai/{ftjob-abcdef}". + type: array + items: + type: string + example: custom-tag + FineTuningJob: + type: object + title: FineTuningJob + description: > + The `fine_tuning.job` object represents a fine-tuning job that has been + created through the API. + properties: + id: + type: string + description: The object identifier, which can be referenced in the API endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the fine-tuning job was + created. + error: + type: object + nullable: true + description: For fine-tuning jobs that have `failed`, this will contain more + information on the cause of the failure. + properties: + code: + type: string + description: A machine-readable error code. + message: + type: string + description: A human-readable error message. + param: + type: string + description: The parameter that was invalid, usually `training_file` or + `validation_file`. This field will be null if the failure was + not parameter-specific. + nullable: true + required: + - code + - message + - param + fine_tuned_model: + type: string + nullable: true + description: The name of the fine-tuned model that is being created. The value + will be null if the fine-tuning job is still running. + finished_at: + type: integer + nullable: true + description: The Unix timestamp (in seconds) for when the fine-tuning job was + finished. The value will be null if the fine-tuning job is still + running. + hyperparameters: + type: object + description: The hyperparameters used for the fine-tuning job. See the + [fine-tuning guide](/docs/guides/fine-tuning) for more details. + properties: + n_epochs: + oneOf: + - type: string + enum: + - auto + - type: integer + minimum: 1 + maximum: 50 + default: auto + description: >- + The number of epochs to train the model for. An epoch refers to + one full cycle through the training dataset. + + "auto" decides the optimal number of epochs based on the size of + the dataset. If setting the number manually, we support any + number between 1 and 50 epochs. + required: + - n_epochs + model: + type: string + description: The base model that is being fine-tuned. + object: + type: string + description: The object type, which is always "fine_tuning.job". + enum: + - fine_tuning.job + organization_id: + type: string + description: The organization that owns the fine-tuning job. + result_files: + type: array + description: The compiled results file ID(s) for the fine-tuning job. You can + retrieve the results with the [Files + API](/docs/api-reference/files/retrieve-contents). + items: + type: string + example: file-abc123 + status: + type: string + description: The current status of the fine-tuning job, which can be either + `validating_files`, `queued`, `running`, `succeeded`, `failed`, or + `cancelled`. + enum: + - validating_files + - queued + - running + - succeeded + - failed + - cancelled + trained_tokens: + type: integer + nullable: true + description: The total number of billable tokens processed by this fine-tuning + job. The value will be null if the fine-tuning job is still running. + training_file: + type: string + description: The file ID used for training. You can retrieve the training data + with the [Files API](/docs/api-reference/files/retrieve-contents). + validation_file: + type: string + nullable: true + description: The file ID used for validation. You can retrieve the validation + results with the [Files + API](/docs/api-reference/files/retrieve-contents). + integrations: + type: array + nullable: true + description: A list of integrations to enable for this fine-tuning job. + maxItems: 5 + items: + oneOf: + - $ref: "#/components/schemas/FineTuningIntegration" + x-oaiExpandable: true + seed: + type: integer + description: The seed used for the fine-tuning job. + estimated_finish: + type: integer + nullable: true + description: The Unix timestamp (in seconds) for when the fine-tuning job is + estimated to finish. The value will be null if the fine-tuning job + is not running. + required: + - created_at + - error + - finished_at + - fine_tuned_model + - hyperparameters + - id + - model + - object + - organization_id + - result_files + - status + - trained_tokens + - training_file + - validation_file + - seed + x-oaiMeta: + name: The fine-tuning job object + example: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "davinci-002", + "created_at": 1692661014, + "finished_at": 1692661190, + "fine_tuned_model": "ft:davinci-002:my-org:custom_suffix:7q8mpxmy", + "organization_id": "org-123", + "result_files": [ + "file-abc123" + ], + "status": "succeeded", + "validation_file": null, + "training_file": "file-abc123", + "hyperparameters": { + "n_epochs": 4, + "batch_size": 1, + "learning_rate_multiplier": 1.0 + }, + "trained_tokens": 5768, + "integrations": [], + "seed": 0, + "estimated_finish": 0 + } + FineTuningJobCheckpoint: + type: object + title: FineTuningJobCheckpoint + description: > + The `fine_tuning.job.checkpoint` object represents a model checkpoint + for a fine-tuning job that is ready to use. + properties: + id: + type: string + description: The checkpoint identifier, which can be referenced in the API + endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the checkpoint was created. + fine_tuned_model_checkpoint: + type: string + description: The name of the fine-tuned checkpoint model that is created. + step_number: + type: integer + description: The step number that the checkpoint was created at. + metrics: + type: object + description: Metrics at the step number during the fine-tuning job. + properties: + step: + type: number + train_loss: + type: number + train_mean_token_accuracy: + type: number + valid_loss: + type: number + valid_mean_token_accuracy: + type: number + full_valid_loss: + type: number + full_valid_mean_token_accuracy: + type: number + fine_tuning_job_id: + type: string + description: The name of the fine-tuning job that this checkpoint was created + from. + object: + type: string + description: The object type, which is always "fine_tuning.job.checkpoint". + enum: + - fine_tuning.job.checkpoint + required: + - created_at + - fine_tuning_job_id + - fine_tuned_model_checkpoint + - id + - metrics + - object + - step_number + x-oaiMeta: + name: The fine-tuning job checkpoint object + example: > + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_qtZ5Gyk4BLq1SfLFWp3RtO3P", + "created_at": 1712211699, + "fine_tuned_model_checkpoint": "ft:gpt-4o-mini-2024-07-18:my-org:custom_suffix:9ABel2dg:ckpt-step-88", + "fine_tuning_job_id": "ftjob-fpbNQ3H1GrMehXRf8cO97xTN", + "metrics": { + "step": 88, + "train_loss": 0.478, + "train_mean_token_accuracy": 0.924, + "valid_loss": 10.112, + "valid_mean_token_accuracy": 0.145, + "full_valid_loss": 0.567, + "full_valid_mean_token_accuracy": 0.944 + }, + "step_number": 88 + } + FineTuningJobEvent: + type: object + description: Fine-tuning job event object + properties: + id: + type: string + created_at: + type: integer + level: + type: string + enum: + - info + - warn + - error + message: + type: string + object: + type: string + enum: + - fine_tuning.job.event + required: + - id + - object + - created_at + - level + - message + x-oaiMeta: + name: The fine-tuning job event object + example: | + { + "object": "fine_tuning.job.event", + "id": "ftevent-abc123" + "created_at": 1677610602, + "level": "info", + "message": "Created fine-tuning job" + } + FinetuneChatRequestInput: + type: object + description: The per-line training example of a fine-tuning input file for chat models + properties: + messages: + type: array + minItems: 1 + items: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" + - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" + - $ref: "#/components/schemas/FineTuneChatCompletionRequestAssistantMessage" + - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" + - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" + x-oaiExpandable: true + tools: + type: array + description: A list of tools the model may generate JSON inputs for. + items: + $ref: "#/components/schemas/ChatCompletionTool" + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + functions: + deprecated: true + description: A list of functions the model may generate JSON inputs for. + type: array + minItems: 1 + maxItems: 128 + items: + $ref: "#/components/schemas/ChatCompletionFunctions" + x-oaiMeta: + name: Training format for chat models + example: > + { + "messages": [ + { "role": "user", "content": "What is the weather in San Francisco?" }, + { + "role": "assistant", + "tool_calls": [ + { + "id": "call_id", + "type": "function", + "function": { + "name": "get_current_weather", + "arguments": "{\"location\": \"San Francisco, USA\", \"format\": \"celsius\"}" + } + } + ] + } + ], + "parallel_tool_calls": false, + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and country, eg. San Francisco, USA" + }, + "format": { "type": "string", "enum": ["celsius", "fahrenheit"] } + }, + "required": ["location", "format"] + } + } + } + ] + } + FinetuneCompletionRequestInput: + type: object + description: The per-line training example of a fine-tuning input file for + completions models + properties: + prompt: + type: string + description: The input prompt for this training example. + completion: + type: string + description: The desired completion for this training example. + x-oaiMeta: + name: Training format for completions models + example: | + { + "prompt": "What is the answer to 2+2", + "completion": "4" + } + FunctionObject: + type: object + properties: + description: + type: string + description: A description of what the function does, used by the model to + choose when and how to call the function. + name: + type: string + description: The name of the function to be called. Must be a-z, A-Z, 0-9, or + contain underscores and dashes, with a maximum length of 64. + parameters: + $ref: "#/components/schemas/FunctionParameters" + strict: + type: boolean + nullable: true + default: false + description: Whether to enable strict schema adherence when generating the + function call. If set to true, the model will follow the exact + schema defined in the `parameters` field. Only a subset of JSON + Schema is supported when `strict` is `true`. Learn more about + Structured Outputs in the [function calling + guide](docs/guides/function-calling). + required: + - name + FunctionParameters: + type: object + description: >- + The parameters the functions accepts, described as a JSON Schema object. + See the [guide](/docs/guides/function-calling) for examples, and the + [JSON Schema + reference](https://json-schema.org/understanding-json-schema/) for + documentation about the format. + + + Omitting `parameters` defines a function with an empty parameter list. + additionalProperties: true + Image: + type: object + description: Represents the url or the content of an image generated by the + OpenAI API. + properties: + b64_json: + type: string + description: The base64-encoded JSON of the generated image, if + `response_format` is `b64_json`. + url: + type: string + description: The URL of the generated image, if `response_format` is `url` + (default). + revised_prompt: + type: string + description: The prompt that was used to generate the image, if there was any + revision to the prompt. + x-oaiMeta: + name: The image object + example: | + { + "url": "...", + "revised_prompt": "..." + } + ImagesResponse: + properties: + created: + type: integer + data: + type: array + items: + $ref: "#/components/schemas/Image" + required: + - created + - data + Invite: + type: object + description: Represents an individual `invite` to the organization. + properties: + object: + type: string + enum: + - organization.invite + description: The object type, which is always `organization.invite` + id: + type: string + description: The identifier, which can be referenced in API endpoints + email: + type: string + description: The email address of the individual to whom the invite was sent + role: + type: string + enum: + - owner + - reader + description: "`owner` or `reader`" + status: + type: string + enum: + - accepted + - expired + - pending + description: "`accepted`,`expired`, or `pending`" + invited_at: + type: integer + description: The Unix timestamp (in seconds) of when the invite was sent. + expires_at: + type: integer + description: The Unix timestamp (in seconds) of when the invite expires. + accepted_at: + type: integer + description: The Unix timestamp (in seconds) of when the invite was accepted. + required: + - object + - id + - email + - role + - status + - invited_at + - expires_at + x-oaiMeta: + name: The invite object + example: | + { + "object": "organization.invite", + "id": "invite-abc", + "email": "user@example.com", + "role": "owner", + "status": "accepted", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": 1711471533 + } + InviteDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.invite.deleted + description: The object type, which is always `organization.invite.deleted` + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + InviteListResponse: + type: object + properties: + object: + type: string + enum: + - list + description: The object type, which is always `list` + data: + type: array + items: + $ref: "#/components/schemas/Invite" + first_id: + type: string + description: The first `invite_id` in the retrieved `list` + last_id: + type: string + description: The last `invite_id` in the retrieved `list` + has_more: + type: boolean + description: The `has_more` property is used for pagination to indicate there + are additional results. + required: + - object + - data + InviteRequest: + type: object + properties: + email: + type: string + description: Send an email to this address + role: + type: string + enum: + - reader + - owner + description: "`owner` or `reader`" + required: + - email + - role + ListAssistantsResponse: + type: object + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/AssistantObject" + first_id: + type: string + example: asst_abc123 + last_id: + type: string + example: asst_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: List assistants response object + group: chat + example: > + { + "object": "list", + "data": [ + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698982736, + "name": "Coding Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc456", + "object": "assistant", + "created_at": 1698982718, + "name": "My Assistant", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc789", + "object": "assistant", + "created_at": 1698982643, + "name": null, + "description": null, + "model": "gpt-4o", + "instructions": null, + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + ], + "first_id": "asst_abc123", + "last_id": "asst_abc789", + "has_more": false + } + ListAuditLogsResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: "#/components/schemas/AuditLog" + first_id: + type: string + example: audit_log-defb456h8dks + last_id: + type: string + example: audit_log-hnbkd8s93s + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ListBatchesResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/Batch" + first_id: + type: string + example: batch_abc123 + last_id: + type: string + example: batch_abc456 + has_more: + type: boolean + object: + type: string + enum: + - list + required: + - object + - data + - has_more + ListFilesResponse: + type: object + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/OpenAIFile" + first_id: + type: string + example: file-abc123 + last_id: + type: string + example: file-abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListFineTuningJobCheckpointsResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJobCheckpoint" + object: + type: string + enum: + - list + first_id: + type: string + nullable: true + last_id: + type: string + nullable: true + has_more: + type: boolean + required: + - object + - data + - has_more + ListFineTuningJobEventsResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJobEvent" + object: + type: string + enum: + - list + required: + - object + - data + ListMessagesResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/MessageObject" + first_id: + type: string + example: msg_abc123 + last_id: + type: string + example: msg_abc123 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListModelsResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: "#/components/schemas/Model" + required: + - object + - data + ListPaginatedFineTuningJobsResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJob" + has_more: + type: boolean + object: + type: string + enum: + - list + required: + - object + - data + - has_more + ListRunStepsResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/RunStepObject" + first_id: + type: string + example: step_abc123 + last_id: + type: string + example: step_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListRunsResponse: + type: object + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/RunObject" + first_id: + type: string + example: run_abc123 + last_id: + type: string + example: run_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListThreadsResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/ThreadObject" + first_id: + type: string + example: asst_abc123 + last_id: + type: string + example: asst_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListVectorStoreFilesResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/VectorStoreFileObject" + first_id: + type: string + example: file-abc123 + last_id: + type: string + example: file-abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListVectorStoresResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/VectorStoreObject" + first_id: + type: string + example: vs_abc123 + last_id: + type: string + example: vs_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + MessageContentImageFileObject: + title: Image file + type: object + description: References an image [File](/docs/api-reference/files) in the + content of a message. + properties: + type: + description: Always `image_file`. + type: string + enum: + - image_file + image_file: + type: object + properties: + file_id: + description: The [File](/docs/api-reference/files) ID of the image in the + message content. Set `purpose="vision"` when uploading the File + if you need to later display the file content. + type: string + detail: + type: string + description: Specifies the detail level of the image if specified by the user. + `low` uses fewer tokens, you can opt in to high resolution using + `high`. + enum: + - auto + - low + - high + default: auto + required: + - file_id + required: + - type + - image_file + MessageContentImageUrlObject: + title: Image URL + type: object + description: References an image URL in the content of a message. + properties: + type: + type: string + enum: + - image_url + description: The type of the content part. + image_url: + type: object + properties: + url: + type: string + description: "The external URL of the image, must be a supported image types: + jpeg, jpg, png, gif, webp." + format: uri + detail: + type: string + description: Specifies the detail level of the image. `low` uses fewer tokens, + you can opt in to high resolution using `high`. Default value is + `auto` + enum: + - auto + - low + - high + default: auto + required: + - url + required: + - type + - image_url + MessageContentRefusalObject: + title: Refusal + type: object + description: The refusal content generated by the assistant. + properties: + type: + description: Always `refusal`. + type: string + enum: + - refusal + refusal: + type: string + nullable: false + required: + - type + - refusal + MessageContentTextAnnotationsFileCitationObject: + title: File citation + type: object + description: A citation within the message that points to a specific quote from + a specific File associated with the assistant or the message. Generated + when the assistant uses the "file_search" tool to search files. + properties: + type: + description: Always `file_citation`. + type: string + enum: + - file_citation + text: + description: The text in the message content that needs to be replaced. + type: string + file_citation: + type: object + properties: + file_id: + description: The ID of the specific File the citation is from. + type: string + required: + - file_id + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - type + - text + - file_citation + - start_index + - end_index + MessageContentTextAnnotationsFilePathObject: + title: File path + type: object + description: A URL for the file that's generated when the assistant used the + `code_interpreter` tool to generate a file. + properties: + type: + description: Always `file_path`. + type: string + enum: + - file_path + text: + description: The text in the message content that needs to be replaced. + type: string + file_path: + type: object + properties: + file_id: + description: The ID of the file that was generated. + type: string + required: + - file_id + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - type + - text + - file_path + - start_index + - end_index + MessageContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + type: + description: Always `text`. + type: string + enum: + - text + text: + type: object + properties: + value: + description: The data that makes up the text. + type: string + annotations: + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageContentTextAnnotationsFileCitationObject" + - $ref: "#/components/schemas/MessageContentTextAnnotationsFilePathObject" + x-oaiExpandable: true + required: + - value + - annotations + required: + - type + - text + MessageDeltaContentImageFileObject: + title: Image file + type: object + description: References an image [File](/docs/api-reference/files) in the + content of a message. + properties: + index: + type: integer + description: The index of the content part in the message. + type: + description: Always `image_file`. + type: string + enum: + - image_file + image_file: + type: object + properties: + file_id: + description: The [File](/docs/api-reference/files) ID of the image in the + message content. Set `purpose="vision"` when uploading the File + if you need to later display the file content. + type: string + detail: + type: string + description: Specifies the detail level of the image if specified by the user. + `low` uses fewer tokens, you can opt in to high resolution using + `high`. + enum: + - auto + - low + - high + default: auto + required: + - index + - type + MessageDeltaContentImageUrlObject: + title: Image URL + type: object + description: References an image URL in the content of a message. + properties: + index: + type: integer + description: The index of the content part in the message. + type: + description: Always `image_url`. + type: string + enum: + - image_url + image_url: + type: object + properties: + url: + description: "The URL of the image, must be a supported image types: jpeg, jpg, + png, gif, webp." + type: string + detail: + type: string + description: Specifies the detail level of the image. `low` uses fewer tokens, + you can opt in to high resolution using `high`. + enum: + - auto + - low + - high + default: auto + required: + - index + - type + MessageDeltaContentRefusalObject: + title: Refusal + type: object + description: The refusal content that is part of a message. + properties: + index: + type: integer + description: The index of the refusal part in the message. + type: + description: Always `refusal`. + type: string + enum: + - refusal + refusal: + type: string + required: + - index + - type + MessageDeltaContentTextAnnotationsFileCitationObject: + title: File citation + type: object + description: A citation within the message that points to a specific quote from + a specific File associated with the assistant or the message. Generated + when the assistant uses the "file_search" tool to search files. + properties: + index: + type: integer + description: The index of the annotation in the text content part. + type: + description: Always `file_citation`. + type: string + enum: + - file_citation + text: + description: The text in the message content that needs to be replaced. + type: string + file_citation: + type: object + properties: + file_id: + description: The ID of the specific File the citation is from. + type: string + quote: + description: The specific quote in the file. + type: string + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - index + - type + MessageDeltaContentTextAnnotationsFilePathObject: + title: File path + type: object + description: A URL for the file that's generated when the assistant used the + `code_interpreter` tool to generate a file. + properties: + index: + type: integer + description: The index of the annotation in the text content part. + type: + description: Always `file_path`. + type: string + enum: + - file_path + text: + description: The text in the message content that needs to be replaced. + type: string + file_path: + type: object + properties: + file_id: + description: The ID of the file that was generated. + type: string + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - index + - type + MessageDeltaContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + index: + type: integer + description: The index of the content part in the message. + type: + description: Always `text`. + type: string + enum: + - text + text: + type: object + properties: + value: + description: The data that makes up the text. + type: string + annotations: + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFileCitationObjec\ + t" + - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFilePathObject" + x-oaiExpandable: true + required: + - index + - type + MessageDeltaObject: + type: object + title: Message delta object + description: > + Represents a message delta i.e. any changed fields on a message during + streaming. + properties: + id: + description: The identifier of the message, which can be referenced in API + endpoints. + type: string + object: + description: The object type, which is always `thread.message.delta`. + type: string + enum: + - thread.message.delta + delta: + description: The delta containing the fields that have changed on the Message. + type: object + properties: + role: + description: The entity that produced the message. One of `user` or `assistant`. + type: string + enum: + - user + - assistant + content: + description: The content of the message in array of text and/or images. + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageDeltaContentImageFileObject" + - $ref: "#/components/schemas/MessageDeltaContentTextObject" + - $ref: "#/components/schemas/MessageDeltaContentRefusalObject" + - $ref: "#/components/schemas/MessageDeltaContentImageUrlObject" + x-oaiExpandable: true + required: + - id + - object + - delta + x-oaiMeta: + name: The message delta object + beta: true + example: | + { + "id": "msg_123", + "object": "thread.message.delta", + "delta": { + "content": [ + { + "index": 0, + "type": "text", + "text": { "value": "Hello", "annotations": [] } + } + ] + } + } + MessageObject: + type: object + title: The message object + description: Represents a message within a [thread](/docs/api-reference/threads). + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `thread.message`. + type: string + enum: + - thread.message + created_at: + description: The Unix timestamp (in seconds) for when the message was created. + type: integer + thread_id: + description: The [thread](/docs/api-reference/threads) ID that this message + belongs to. + type: string + status: + description: The status of the message, which can be either `in_progress`, + `incomplete`, or `completed`. + type: string + enum: + - in_progress + - incomplete + - completed + incomplete_details: + description: On an incomplete message, details about why the message is + incomplete. + type: object + properties: + reason: + type: string + description: The reason the message is incomplete. + enum: + - content_filter + - max_tokens + - run_cancelled + - run_expired + - run_failed + nullable: true + required: + - reason + completed_at: + description: The Unix timestamp (in seconds) for when the message was completed. + type: integer + nullable: true + incomplete_at: + description: The Unix timestamp (in seconds) for when the message was marked as + incomplete. + type: integer + nullable: true + role: + description: The entity that produced the message. One of `user` or `assistant`. + type: string + enum: + - user + - assistant + content: + description: The content of the message in array of text and/or images. + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageContentImageFileObject" + - $ref: "#/components/schemas/MessageContentImageUrlObject" + - $ref: "#/components/schemas/MessageContentTextObject" + - $ref: "#/components/schemas/MessageContentRefusalObject" + x-oaiExpandable: true + assistant_id: + description: If applicable, the ID of the + [assistant](/docs/api-reference/assistants) that authored this + message. + type: string + nullable: true + run_id: + description: The ID of the [run](/docs/api-reference/runs) associated with the + creation of this message. Value is `null` when messages are created + manually using the create message or create thread endpoints. + type: string + nullable: true + attachments: + type: array + items: + type: object + properties: + file_id: + type: string + description: The ID of the file to attach to the message. + tools: + description: The tools to add this file to. + type: array + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearchTypeOnly" + x-oaiExpandable: true + description: A list of files attached to the message, and the tools they were + added to. + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + required: + - id + - object + - created_at + - thread_id + - status + - incomplete_details + - completed_at + - incomplete_at + - role + - content + - assistant_id + - run_id + - attachments + - metadata + x-oaiMeta: + name: The message object + beta: true + example: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1698983503, + "thread_id": "thread_abc123", + "role": "assistant", + "content": [ + { + "type": "text", + "text": { + "value": "Hi! How can I help you today?", + "annotations": [] + } + } + ], + "assistant_id": "asst_abc123", + "run_id": "run_abc123", + "attachments": [], + "metadata": {} + } + MessageRequestContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + type: + description: Always `text`. + type: string + enum: + - text + text: + type: string + description: Text content to be sent to the model + required: + - type + - text + MessageStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: + - thread.message.created + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) is + created. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: + type: string + enum: + - thread.message.in_progress + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) moves + to an `in_progress` state. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: + type: string + enum: + - thread.message.delta + data: + $ref: "#/components/schemas/MessageDeltaObject" + required: + - event + - data + description: Occurs when parts of a + [Message](/docs/api-reference/messages/object) are being streamed. + x-oaiMeta: + dataDescription: "`data` is a [message + delta](/docs/api-reference/assistants-streaming/message-delta-obj\ + ect)" + - type: object + properties: + event: + type: string + enum: + - thread.message.completed + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) is + completed. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: + type: string + enum: + - thread.message.incomplete + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) ends + before it is completed. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + Model: + title: Model + description: Describes an OpenAI model offering that can be used with the API. + properties: + id: + type: string + description: The model identifier, which can be referenced in the API endpoints. + created: + type: integer + description: The Unix timestamp (in seconds) when the model was created. + object: + type: string + description: The object type, which is always "model". + enum: + - model + owned_by: + type: string + description: The organization that owns the model. + required: + - id + - object + - created + - owned_by + x-oaiMeta: + name: The model object + example: | + { + "id": "VAR_chat_model_id", + "object": "model", + "created": 1686935002, + "owned_by": "openai" + } + ModifyAssistantRequest: + type: object + additionalProperties: false + properties: + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + anyOf: + - type: string + name: description: | - List and describe the various models available in the API. You can refer to the [Models](/docs/models) documentation to understand what models are available and the differences between them. - navigationGroup: endpoints - sections: - - type: endpoint - key: listModels - path: list - - type: endpoint - key: retrieveModel - path: retrieve - - type: endpoint - key: deleteModel - path: delete - - type: object - key: Model - path: object - - id: moderations - title: Moderations + The name of the assistant. The maximum length is 256 characters. + type: string + nullable: true + maxLength: 256 + description: + description: > + The description of the assistant. The maximum length is 512 + characters. + type: string + nullable: true + maxLength: 512 + instructions: + description: > + The system instructions that the assistant uses. The maximum length + is 256,000 characters. + type: string + nullable: true + maxLength: 256000 + tools: + description: > + A list of tool enabled on the assistant. There can be a maximum of + 128 tools per assistant. Tools can be of types `code_interpreter`, + `file_search`, or `function`. + default: [] + type: array + maxItems: 128 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + Overrides the list of [file](/docs/api-reference/files) IDs + made available to the `code_interpreter` tool. There can be + a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + Overrides the [vector + store](/docs/api-reference/vector-stores/object) attached to + this assistant. There can be a maximum of 1 vector store + attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + ModifyMessageRequest: + type: object + additionalProperties: false + properties: + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + ModifyRunRequest: + type: object + additionalProperties: false + properties: + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + ModifyThreadRequest: + type: object + additionalProperties: false + properties: + tool_resources: + type: object + description: > + A set of resources that are made available to the assistant's tools + in this thread. The resources are specific to the type of tool. For + example, the `code_interpreter` tool requires a list of file IDs, + while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this thread. There can be a maximum of 1 vector + store attached to the thread. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + OpenAIFile: + title: OpenAIFile + description: The `File` object represents a document that has been uploaded to OpenAI. + properties: + id: + type: string + description: The file identifier, which can be referenced in the API endpoints. + bytes: + type: integer + description: The size of the file, in bytes. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the file was created. + filename: + type: string + description: The name of the file. + object: + type: string + description: The object type, which is always `file`. + enum: + - file + purpose: + type: string + description: The intended purpose of the file. Supported values are + `assistants`, `assistants_output`, `batch`, `batch_output`, + `fine-tune`, `fine-tune-results` and `vision`. + enum: + - assistants + - assistants_output + - batch + - batch_output + - fine-tune + - fine-tune-results + - vision + status: + type: string + deprecated: true + description: Deprecated. The current status of the file, which can be either + `uploaded`, `processed`, or `error`. + enum: + - uploaded + - processed + - error + status_details: + type: string + deprecated: true + description: Deprecated. For details on why a fine-tuning training file failed + validation, see the `error` field on `fine_tuning.job`. + required: + - id + - object + - bytes + - created_at + - filename + - purpose + - status + x-oaiMeta: + name: The file object + example: | + { + "id": "file-abc123", + "object": "file", + "bytes": 120000, + "created_at": 1677610602, + "filename": "salesOverview.pdf", + "purpose": "assistants", + } + OtherChunkingStrategyResponseParam: + type: object + title: Other Chunking Strategy + description: This is returned when the chunking strategy is unknown. Typically, + this is because the file was indexed before the `chunking_strategy` + concept was introduced in the API. + additionalProperties: false + properties: + type: + type: string + description: Always `other`. + enum: + - other + required: + - type + ParallelToolCalls: + description: Whether to enable [parallel function + calling](/docs/guides/function-calling#configuring-parallel-function-calling) + during tool use. + type: boolean + default: true + PredictionContent: + type: object + title: Static Content + description: > + Static predicted output content, such as the content of a text file that + is + + being regenerated. + required: + - type + - content + properties: + type: + type: string + enum: + - content description: | - Given some input text, outputs if the model classifies it as potentially harmful across several categories. - - Related guide: [Moderations](/docs/guides/moderation) - navigationGroup: endpoints - sections: - - type: endpoint - key: createModeration - path: create - - type: object - key: CreateModerationResponse - path: object - - id: assistants - title: Assistants - beta: true + The type of the predicted content you want to provide. This type is + currently always `content`. + content: + x-oaiExpandable: true + description: > + The content that should be matched when generating a model response. + + If generated tokens would match this content, the entire model + response + + can be returned much more quickly. + oneOf: + - type: string + title: Text content + description: | + The content used for a Predicted Output. This is often the + text of a file you are regenerating with minor changes. + - type: array + description: An array of content parts with a defined type. Supported options + differ based on the [model](/docs/models) being used to generate + the response. Can contain text inputs. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + minItems: 1 + Project: + type: object + description: Represents an individual project. + properties: + id: + type: string + description: The identifier, which can be referenced in API endpoints + object: + type: string + enum: + - organization.project + description: The object type, which is always `organization.project` + name: + type: string + description: The name of the project. This appears in reporting. + created_at: + type: integer + description: The Unix timestamp (in seconds) of when the project was created. + archived_at: + type: integer + nullable: true + description: The Unix timestamp (in seconds) of when the project was archived or + `null`. + status: + type: string + enum: + - active + - archived + description: "`active` or `archived`" + required: + - id + - object + - name + - created_at + - status + x-oaiMeta: + name: The project object + example: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project example", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + ProjectApiKey: + type: object + description: Represents an individual API key in a project. + properties: + object: + type: string + enum: + - organization.project.api_key + description: The object type, which is always `organization.project.api_key` + redacted_value: + type: string + description: The redacted value of the API key + name: + type: string + description: The name of the API key + created_at: + type: integer + description: The Unix timestamp (in seconds) of when the API key was created + id: + type: string + description: The identifier, which can be referenced in API endpoints + owner: + type: object + properties: + type: + type: string + enum: + - user + - service_account + description: "`user` or `service_account`" + user: + $ref: "#/components/schemas/ProjectUser" + service_account: + $ref: "#/components/schemas/ProjectServiceAccount" + required: + - object + - redacted_value + - name + - created_at + - id + - owner + x-oaiMeta: + name: The project API key object + example: | + { + "object": "organization.project.api_key", + "redacted_value": "sk-abc...def", + "name": "My API Key", + "created_at": 1711471533, + "id": "key_abc", + "owner": { + "type": "user", + "user": { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "created_at": 1711471533 + } + } + } + ProjectApiKeyDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.api_key.deleted + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + ProjectApiKeyListResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: "#/components/schemas/ProjectApiKey" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectCreateRequest: + type: object + properties: + name: + type: string + description: The friendly name of the project, this name appears in reports. + required: + - name + ProjectListResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: "#/components/schemas/Project" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectRateLimit: + type: object + description: Represents a project rate limit config. + properties: + object: + type: string + enum: + - project.rate_limit + description: The object type, which is always `project.rate_limit` + id: + type: string + description: The identifier, which can be referenced in API endpoints. + model: + type: string + description: The model this rate limit applies to. + max_requests_per_1_minute: + type: integer + description: The maximum requests per minute. + max_tokens_per_1_minute: + type: integer + description: The maximum tokens per minute. + max_images_per_1_minute: + type: integer + description: The maximum images per minute. Only present for relevant models. + max_audio_megabytes_per_1_minute: + type: integer + description: The maximum audio megabytes per minute. Only present for relevant + models. + max_requests_per_1_day: + type: integer + description: The maximum requests per day. Only present for relevant models. + batch_1_day_max_input_tokens: + type: integer + description: The maximum batch input tokens per day. Only present for relevant + models. + required: + - object + - id + - model + - max_requests_per_1_minute + - max_tokens_per_1_minute + x-oaiMeta: + name: The project rate limit object + example: | + { + "object": "project.rate_limit", + "id": "rl_ada", + "model": "ada", + "max_requests_per_1_minute": 600, + "max_tokens_per_1_minute": 150000, + "max_images_per_1_minute": 10 + } + ProjectRateLimitListResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: "#/components/schemas/ProjectRateLimit" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectRateLimitUpdateRequest: + type: object + properties: + max_requests_per_1_minute: + type: integer + description: The maximum requests per minute. + max_tokens_per_1_minute: + type: integer + description: The maximum tokens per minute. + max_images_per_1_minute: + type: integer + description: The maximum images per minute. Only relevant for certain models. + max_audio_megabytes_per_1_minute: + type: integer + description: The maximum audio megabytes per minute. Only relevant for certain + models. + max_requests_per_1_day: + type: integer + description: The maximum requests per day. Only relevant for certain models. + batch_1_day_max_input_tokens: + type: integer + description: The maximum batch input tokens per day. Only relevant for certain + models. + ProjectServiceAccount: + type: object + description: Represents an individual service account in a project. + properties: + object: + type: string + enum: + - organization.project.service_account + description: The object type, which is always + `organization.project.service_account` + id: + type: string + description: The identifier, which can be referenced in API endpoints + name: + type: string + description: The name of the service account + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + created_at: + type: integer + description: The Unix timestamp (in seconds) of when the service account was + created + required: + - object + - id + - name + - role + - created_at + x-oaiMeta: + name: The project service account object + example: | + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Service Account", + "role": "owner", + "created_at": 1711471533 + } + ProjectServiceAccountApiKey: + type: object + properties: + object: + type: string + enum: + - organization.project.service_account.api_key + description: The object type, which is always + `organization.project.service_account.api_key` + value: + type: string + name: + type: string + created_at: + type: integer + id: + type: string + required: + - object + - value + - name + - created_at + - id + ProjectServiceAccountCreateRequest: + type: object + properties: + name: + type: string + description: The name of the service account being created. + required: + - name + ProjectServiceAccountCreateResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.service_account + id: + type: string + name: + type: string + role: + type: string + enum: + - member + description: Service accounts can only have one role of type `member` + created_at: + type: integer + api_key: + $ref: "#/components/schemas/ProjectServiceAccountApiKey" + required: + - object + - id + - name + - role + - created_at + - api_key + ProjectServiceAccountDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.service_account.deleted + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + ProjectServiceAccountListResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: "#/components/schemas/ProjectServiceAccount" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectUpdateRequest: + type: object + properties: + name: + type: string + description: The updated name of the project, this name appears in reports. + required: + - name + ProjectUser: + type: object + description: Represents an individual user in a project. + properties: + object: + type: string + enum: + - organization.project.user + description: The object type, which is always `organization.project.user` + id: + type: string + description: The identifier, which can be referenced in API endpoints + name: + type: string + description: The name of the user + email: + type: string + description: The email address of the user + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + added_at: + type: integer + description: The Unix timestamp (in seconds) of when the project was added. + required: + - object + - id + - name + - email + - role + - added_at + x-oaiMeta: + name: The project user object + example: | + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + ProjectUserCreateRequest: + type: object + properties: + user_id: + type: string + description: The ID of the user. + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + required: + - user_id + - role + ProjectUserDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.user.deleted + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + ProjectUserListResponse: + type: object + properties: + object: + type: string + data: + type: array + items: + $ref: "#/components/schemas/ProjectUser" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectUserUpdateRequest: + type: object + properties: + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + required: + - role + RealtimeClientEventConversationItemCreate: + type: object + description: > + Add a new Item to the Conversation's context, including messages, + function + + calls, and function call responses. This event can be used both to + populate a + + "history" of the conversation and to add new items mid-stream, but has + the + + current limitation that it cannot populate assistant audio messages. + + + If successful, the server will respond with a + `conversation.item.created` + + event, otherwise an `error` event will be sent. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - conversation.item.create + description: The event type, must be `conversation.item.create`. + previous_item_id: + type: string + description: > + The ID of the preceding item after which the new item will be + inserted. + + If not set, the new item will be appended to the end of the + conversation. + + If set, it allows an item to be inserted mid-conversation. If the + ID + + cannot be found, an error will be returned and the item will not be + added. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - type + - item + x-oaiMeta: + name: conversation.item.create + group: realtime + example: | + { + "event_id": "event_345", + "type": "conversation.item.create", + "previous_item_id": null, + "item": { + "id": "msg_001", + "type": "message", + "role": "user", + "content": [ + { + "type": "input_text", + "text": "Hello, how are you?" + } + ] + } + } + RealtimeClientEventConversationItemDelete: + type: object + description: > + Send this event when you want to remove any item from the conversation + + history. The server will respond with a `conversation.item.deleted` + event, + + unless the item does not exist in the conversation history, in which + case the + + server will respond with an error. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - conversation.item.delete + description: The event type, must be `conversation.item.delete`. + item_id: + type: string + description: The ID of the item to delete. + required: + - type + - item_id + x-oaiMeta: + name: conversation.item.delete + group: realtime + example: | + { + "event_id": "event_901", + "type": "conversation.item.delete", + "item_id": "msg_003" + } + RealtimeClientEventConversationItemTruncate: + type: object + description: > + Send this event to truncate a previous assistant message’s audio. The + server + + will produce audio faster than realtime, so this event is useful when + the user + + interrupts to truncate audio that has already been sent to the client + but not + + yet played. This will synchronize the server's understanding of the + audio with + + the client's playback. + + + Truncating audio will delete the server-side text transcript to ensure + there + + is not text in the context that hasn't been heard by the user. + + + If successful, the server will respond with a + `conversation.item.truncated` + + event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - conversation.item.truncate + description: The event type, must be `conversation.item.truncate`. + item_id: + type: string + description: > + The ID of the assistant message item to truncate. Only assistant + message + + items can be truncated. + content_index: + type: integer + description: The index of the content part to truncate. Set this to 0. + audio_end_ms: + type: integer + description: > + Inclusive duration up to which audio is truncated, in milliseconds. + If + + the audio_end_ms is greater than the actual audio duration, the + server + + will respond with an error. + required: + - type + - item_id + - content_index + - audio_end_ms + x-oaiMeta: + name: conversation.item.truncate + group: realtime + example: | + { + "event_id": "event_678", + "type": "conversation.item.truncate", + "item_id": "msg_002", + "content_index": 0, + "audio_end_ms": 1500 + } + RealtimeClientEventInputAudioBufferAppend: + type: object + description: > + Send this event to append audio bytes to the input audio buffer. The + audio + + buffer is temporary storage you can write to and later commit. In Server + VAD + + mode, the audio buffer is used to detect speech and the server will + decide + + when to commit. When Server VAD is disabled, you must commit the audio + buffer + + manually. + + + The client may choose how much audio to place in each event up to a + maximum + + of 15 MiB, for example streaming smaller chunks from the client may + allow the + + VAD to be more responsive. Unlike made other client events, the server + will + + not send a confirmation response to this event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - input_audio_buffer.append + description: The event type, must be `input_audio_buffer.append`. + audio: + type: string + description: > + Base64-encoded audio bytes. This must be in the format specified by + the + + `input_audio_format` field in the session configuration. + required: + - type + - audio + x-oaiMeta: + name: input_audio_buffer.append + group: realtime + example: | + { + "event_id": "event_456", + "type": "input_audio_buffer.append", + "audio": "Base64EncodedAudioData" + } + RealtimeClientEventInputAudioBufferClear: + type: object + description: | + Send this event to clear the audio bytes in the buffer. The server will + respond with an `input_audio_buffer.cleared` event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - input_audio_buffer.clear + description: The event type, must be `input_audio_buffer.clear`. + required: + - type + x-oaiMeta: + name: input_audio_buffer.clear + group: realtime + example: | + { + "event_id": "event_012", + "type": "input_audio_buffer.clear" + } + RealtimeClientEventInputAudioBufferCommit: + type: object + description: > + Send this event to commit the user input audio buffer, which will create + a + + new user message item in the conversation. This event will produce an + error + + if the input audio buffer is empty. When in Server VAD mode, the client + does + + not need to send this event, the server will commit the audio buffer + + automatically. + + + Committing the input audio buffer will trigger input audio + transcription + + (if enabled in session configuration), but it will not create a + response + + from the model. The server will respond with an + `input_audio_buffer.committed` + + event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - input_audio_buffer.commit + description: The event type, must be `input_audio_buffer.commit`. + required: + - type + x-oaiMeta: + name: input_audio_buffer.commit + group: realtime + example: | + { + "event_id": "event_789", + "type": "input_audio_buffer.commit" + } + RealtimeClientEventResponseCancel: + type: object + description: > + Send this event to cancel an in-progress response. The server will + respond + + with a `response.cancelled` event or an error if there is no response + to + + cancel. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - response.cancel + description: The event type, must be `response.cancel`. + required: + - type + x-oaiMeta: + name: response.cancel + group: realtime + example: | + { + "event_id": "event_567", + "type": "response.cancel" + } + RealtimeClientEventResponseCreate: + type: object + description: > + This event instructs the server to create a Response, which means + triggering + + model inference. When in Server VAD mode, the server will create + Responses + + automatically. + + + A Response will include at least one Item, and may have two, in which + case + + the second will be a function call. These Items will be appended to the + + conversation history. + + + The server will respond with a `response.created` event, events for + Items + + and content created, and finally a `response.done` event to indicate + the + + Response is complete. + + + The `response.create` event includes inference configuration like + + `instructions`, and `temperature`. These fields will override the + Session's + + configuration for this Response only. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - response.create + description: The event type, must be `response.create`. + response: + $ref: "#/components/schemas/RealtimeSession" + required: + - type + - response + x-oaiMeta: + name: response.create + group: realtime + example: | + { + "event_id": "event_234", + "type": "response.create", + "response": { + "modalities": ["text", "audio"], + "instructions": "Please assist the user.", + "voice": "sage", + "output_audio_format": "pcm16", + "tools": [ + { + "type": "function", + "name": "calculate_sum", + "description": "Calculates the sum of two numbers.", + "parameters": { + "type": "object", + "properties": { + "a": { "type": "number" }, + "b": { "type": "number" } + }, + "required": ["a", "b"] + } + } + ], + "tool_choice": "auto", + "temperature": 0.7, + "max_output_tokens": 150 + } + } + RealtimeClientEventSessionUpdate: + type: object + description: > + Send this event to update the session’s default configuration. The + client may + + send this event at any time to update the session configuration, and + any + + field may be updated at any time, except for "voice". The server will + respond + + with a `session.updated` event that shows the full effective + configuration. + + Only fields that are present are updated, thus the correct way to clear + a + + field like "instructions" is to pass an empty string. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - session.update + description: The event type, must be `session.update`. + session: + $ref: "#/components/schemas/RealtimeSession" + required: + - type + - session + x-oaiMeta: + name: session.update + group: realtime + example: | + { + "event_id": "event_123", + "type": "session.update", + "session": { + "modalities": ["text", "audio"], + "instructions": "You are a helpful assistant.", + "voice": "sage", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": { + "model": "whisper-1" + }, + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 500 + }, + "tools": [ + { + "type": "function", + "name": "get_weather", + "description": "Get the current weather...", + "parameters": { + "type": "object", + "properties": { + "location": { "type": "string" } + }, + "required": ["location"] + } + } + ], + "tool_choice": "auto", + "temperature": 0.8, + "max_response_output_tokens": "inf" + } + } + RealtimeConversationItem: + type: object + x-oaiExpandable: true + description: The item to add to the conversation. + properties: + id: + type: string + description: > + The unique ID of the item, this can be generated by the client to + help + + manage server-side context, but is not required because the server + will + + generate one if not provided. + type: + type: string + enum: + - message + - function_call + - function_call_output + description: > + The type of the item (`message`, `function_call`, + `function_call_output`). + object: + type: string + enum: + - realtime.item + description: > + Identifier for the API object being returned - always + `realtime.item`. + status: + type: string + enum: + - completed + - incomplete + description: > + The status of the item (`completed`, `incomplete`). These have no + effect + + on the conversation, but are accepted for consistency with the + + `conversation.item.created` event. + role: + type: string + enum: + - user + - assistant + - systems + description: > + The role of the message sender (`user`, `assistant`, `system`), + only + + applicable for `message` items. + content: + type: array + x-oaiExpandable: true + description: > + The content of the message, applicable for `message` items. + + - Message items of role `system` support only `input_text` content + + - Message items of role `user` support `input_text` and + `input_audio` + content + - Message items of role `assistant` support `text` content. + items: + type: object + x-oaiExpandable: true + properties: + type: + type: string + enum: + - input_audio + - input_text + - text + description: The content type (`input_text`, `input_audio`, `text`). + text: + type: string + description: > + The text content, used for `input_text` and `text` content + types. + audio: + type: string + description: > + Base64-encoded audio bytes, used for `input_audio` content + type. + transcript: + type: string + description: > + The transcript of the audio, used for `input_audio` content + type. + call_id: + type: string + description: > + The ID of the function call (for `function_call` and + + `function_call_output` items). If passed on a + `function_call_output` + + item, the server will check that a `function_call` item with the + same + + ID exists in the conversation history. + name: + type: string description: | - Build assistants that can call models and use tools to perform tasks. - - [Get started with the Assistants API](/docs/assistants) - navigationGroup: assistants - sections: - - type: endpoint - key: createAssistant - path: createAssistant - - type: endpoint - key: listAssistants - path: listAssistants - - type: endpoint - key: getAssistant - path: getAssistant - - type: endpoint - key: modifyAssistant - path: modifyAssistant - - type: endpoint - key: deleteAssistant - path: deleteAssistant - - type: object - key: AssistantObject - path: object - - id: threads - title: Threads - beta: true + The name of the function being called (for `function_call` items). + arguments: + type: string description: | - Create threads that assistants can interact with. - - Related guide: [Assistants](/docs/assistants/overview) - navigationGroup: assistants - sections: - - type: endpoint - key: createThread - path: createThread - - type: endpoint - key: getThread - path: getThread - - type: endpoint - key: modifyThread - path: modifyThread - - type: endpoint - key: deleteThread - path: deleteThread - - type: object - key: ThreadObject - path: object - - id: messages - title: Messages - beta: true + The arguments of the function call (for `function_call` items). + output: + type: string description: | - Create messages within threads - - Related guide: [Assistants](/docs/assistants/overview) - navigationGroup: assistants - sections: - - type: endpoint - key: createMessage - path: createMessage - - type: endpoint - key: listMessages - path: listMessages - - type: endpoint - key: getMessage - path: getMessage - - type: endpoint - key: modifyMessage - path: modifyMessage - - type: endpoint - key: deleteMessage - path: deleteMessage - - type: object - key: MessageObject - path: object - - id: runs - title: Runs - beta: true + The output of the function call (for `function_call_output` items). + RealtimeResponse: + type: object + description: The response resource. + properties: + id: + type: string + description: The unique ID of the response. + object: + type: string + enum: + - realtime.response + description: The object type, must be `realtime.response`. + status: + type: string + enum: + - completed + - cancelled + - failed + - incomplete + description: > + The final status of the response (`completed`, `cancelled`, + `failed`, or + + `incomplete`). + status_details: + type: object + description: Additional details about the status. + properties: + type: + type: string + enum: + - completed + - cancelled + - failed + - incomplete + description: > + The type of error that caused the response to fail, + corresponding + + with the `status` field (`cancelled`, `incomplete`, `failed`). + reason: + type: string + enum: + - turn_detected + - client_cancelled + - max_output_tokens + - content_filter + description: > + The reason the Response did not complete. For a `cancelled` + Response, + + one of `turn_detected` (the server VAD detected a new start of + speech) + + or `client_cancelled` (the client sent a cancel event). For an + + `incomplete` Response, one of `max_output_tokens` or + `content_filter` + + (the server-side safety filter activated and cut off the + response). + error: + type: object + description: | + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + properties: + type: + type: string + description: The type of error. + code: + type: string + description: Error code, if any. + output: + type: array + description: The list of output items generated by the response. + items: + $ref: "#/components/schemas/RealtimeConversationItem" + usage: + type: object + description: > + Usage statistics for the Response, this will correspond to billing. + A + + Realtime API session will maintain a conversation context and append + new + + Items to the Conversation, thus output from previous turns (text + and + + audio tokens) will become the input for later turns. + properties: + total_tokens: + type: integer + description: > + The total number of tokens in the Response including input and + output + + text and audio tokens. + input_tokens: + type: integer + description: > + The number of input tokens used in the Response, including text + and + + audio tokens. + output_tokens: + type: integer + description: > + The number of output tokens sent in the Response, including text + and + + audio tokens. + input_token_details: + type: object + description: Details about the input tokens used in the Response. + properties: + cached_tokens: + type: integer + description: The number of cached tokens used in the Response. + text_tokens: + type: integer + description: The number of text tokens used in the Response. + audio_tokens: + type: integer + description: The number of audio tokens used in the Response. + output_token_details: + type: object + description: Details about the output tokens used in the Response. + properties: + text_tokens: + type: integer + description: The number of text tokens used in the Response. + audio_tokens: + type: integer + description: The number of audio tokens used in the Response. + RealtimeServerEventConversationCreated: + type: object + description: > + Returned when a conversation is created. Emitted right after session + creation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.created + description: The event type, must be `conversation.created`. + conversation: + type: object + description: The conversation resource. + properties: + id: + type: string + description: The unique ID of the conversation. + object: + type: string + description: The object type, must be `realtime.conversation`. + required: + - event_id + - type + - conversation + x-oaiMeta: + name: conversation.created + group: realtime + example: | + { + "event_id": "event_9101", + "type": "conversation.created", + "conversation": { + "id": "conv_001", + "object": "realtime.conversation" + } + } + RealtimeServerEventConversationItemCreated: + type: object + description: > + Returned when a conversation item is created. There are several + scenarios that + + produce this event: + - The server is generating a Response, which if successful will produce + either one or two Items, which will be of type `message` + (role `assistant`) or type `function_call`. + - The input audio buffer has been committed, either by the client or the + server (in `server_vad` mode). The server will take the content of the + input audio buffer and add it to a new user message Item. + - The client has sent a `conversation.item.create` event to add a new Item + to the Conversation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.created + description: The event type, must be `conversation.item.created`. + previous_item_id: + type: string + description: > + The ID of the preceding item in the Conversation context, allows + the + + client to understand the order of the conversation. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - event_id + - type + - previous_item_id + - item + x-oaiMeta: + name: conversation.item.created + group: realtime + example: | + { + "event_id": "event_1920", + "type": "conversation.item.created", + "previous_item_id": "msg_002", + "item": { + "id": "msg_003", + "object": "realtime.item", + "type": "message", + "status": "completed", + "role": "user", + "content": [ + { + "type": "input_audio", + "transcript": "hello how are you", + "audio": "base64encodedaudio==" + } + ] + } + } + RealtimeServerEventConversationItemDeleted: + type: object + description: > + Returned when an item in the conversation is deleted by the client with + a + + `conversation.item.delete` event. This event is used to synchronize the + + server's understanding of the conversation history with the client's + view. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.deleted + description: The event type, must be `conversation.item.deleted`. + item_id: + type: string + description: The ID of the item that was deleted. + required: + - event_id + - type + - item_id + x-oaiMeta: + name: conversation.item.deleted + group: realtime + example: | + { + "event_id": "event_2728", + "type": "conversation.item.deleted", + "item_id": "msg_005" + } + RealtimeServerEventConversationItemInputAudioTranscriptionCompleted: + type: object + description: > + This event is the output of audio transcription for user audio written + to the + + user audio buffer. Transcription begins when the input audio buffer is + + committed by the client or server (in `server_vad` mode). Transcription + runs + + asynchronously with Response creation, so this event may come before or + after + + the Response events. + + + Realtime API models accept audio natively, and thus input transcription + is a + + separate process run on a separate ASR (Automatic Speech Recognition) + model, + + currently always `whisper-1`. Thus the transcript may diverge somewhat + from + + the model's interpretation, and should be treated as a rough guide. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.input_audio_transcription.completed description: | - Represents an execution run on a thread. - - Related guide: [Assistants](/docs/assistants/overview) - navigationGroup: assistants - sections: - - type: endpoint - key: createRun - path: createRun - - type: endpoint - key: createThreadAndRun - path: createThreadAndRun - - type: endpoint - key: listRuns - path: listRuns - - type: endpoint - key: getRun - path: getRun - - type: endpoint - key: modifyRun - path: modifyRun - - type: endpoint - key: submitToolOuputsToRun - path: submitToolOutputs - - type: endpoint - key: cancelRun - path: cancelRun - - type: object - key: RunObject - path: object - - id: run-steps - title: Run Steps - beta: true + The event type, must be + `conversation.item.input_audio_transcription.completed`. + item_id: + type: string + description: The ID of the user message item containing the audio. + content_index: + type: integer + description: The index of the content part containing the audio. + transcript: + type: string + description: The transcribed text. + required: + - event_id + - type + - item_id + - content_index + - transcript + x-oaiMeta: + name: conversation.item.input_audio_transcription.completed + group: realtime + example: | + { + "event_id": "event_2122", + "type": "conversation.item.input_audio_transcription.completed", + "item_id": "msg_003", + "content_index": 0, + "transcript": "Hello, how are you?" + } + RealtimeServerEventConversationItemInputAudioTranscriptionFailed: + type: object + description: > + Returned when input audio transcription is configured, and a + transcription + + request for a user message failed. These events are separate from other + + `error` events so that the client can identify the related Item. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.input_audio_transcription.failed description: | - Represents the steps (model and tool calls) taken during the run. - - Related guide: [Assistants](/docs/assistants/overview) - navigationGroup: assistants - sections: - - type: endpoint - key: listRunSteps - path: listRunSteps - - type: endpoint - key: getRunStep - path: getRunStep - - type: object - key: RunStepObject - path: step-object - - id: vector-stores - title: Vector Stores - beta: true + The event type, must be + `conversation.item.input_audio_transcription.failed`. + item_id: + type: string + description: The ID of the user message item. + content_index: + type: integer + description: The index of the content part containing the audio. + error: + type: object + description: Details of the transcription error. + properties: + type: + type: string + description: The type of error. + code: + type: string + description: Error code, if any. + message: + type: string + description: A human-readable error message. + param: + type: string + description: Parameter related to the error, if any. + required: + - event_id + - type + - item_id + - content_index + - error + x-oaiMeta: + name: conversation.item.input_audio_transcription.failed + group: realtime + example: | + { + "event_id": "event_2324", + "type": "conversation.item.input_audio_transcription.failed", + "item_id": "msg_003", + "content_index": 0, + "error": { + "type": "transcription_error", + "code": "audio_unintelligible", + "message": "The audio could not be transcribed.", + "param": null + } + } + RealtimeServerEventConversationItemTruncated: + type: object + description: > + Returned when an earlier assistant audio message item is truncated by + the + + client with a `conversation.item.truncate` event. This event is used to + + synchronize the server's understanding of the audio with the client's + playback. + + + This action will truncate the audio and remove the server-side text + transcript + + to ensure there is no text in the context that hasn't been heard by the + user. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.truncated + description: The event type, must be `conversation.item.truncated`. + item_id: + type: string + description: The ID of the assistant message item that was truncated. + content_index: + type: integer + description: The index of the content part that was truncated. + audio_end_ms: + type: integer description: | - Vector stores are used to store files for use by the `file_search` tool. - - Related guide: [File Search](/docs/assistants/tools/file-search) - navigationGroup: assistants - sections: - - type: endpoint - key: createVectorStore - path: create - - type: endpoint - key: listVectorStores - path: list - - type: endpoint - key: getVectorStore - path: retrieve - - type: endpoint - key: modifyVectorStore - path: modify - - type: endpoint - key: deleteVectorStore - path: delete - - type: object - key: VectorStoreObject - path: object - - id: vector-stores-files - title: Vector Store Files - beta: true + The duration up to which the audio was truncated, in milliseconds. + required: + - event_id + - type + - item_id + - content_index + - audio_end_ms + x-oaiMeta: + name: conversation.item.truncated + group: realtime + example: | + { + "event_id": "event_2526", + "type": "conversation.item.truncated", + "item_id": "msg_004", + "content_index": 0, + "audio_end_ms": 1500 + } + RealtimeServerEventError: + type: object + description: > + Returned when an error occurs, which could be a client problem or a + server + + problem. Most errors are recoverable and the session will stay open, we + + recommend to implementors to monitor and log error messages by default. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - error + description: The event type, must be `error`. + error: + type: object + description: Details of the error. + properties: + type: + type: string + description: > + The type of error (e.g., "invalid_request_error", + "server_error"). + code: + type: string + description: Error code, if any. + message: + type: string + description: A human-readable error message. + param: + type: string + description: Parameter related to the error, if any. + event_id: + type: string + description: > + The event_id of the client event that caused the error, if + applicable. + required: + - event_id + - type + - error + x-oaiMeta: + name: error + group: realtime + example: | + { + "event_id": "event_890", + "type": "error", + "error": { + "type": "invalid_request_error", + "code": "invalid_event", + "message": "The 'type' field is missing.", + "param": null, + "event_id": "event_567" + } + } + RealtimeServerEventInputAudioBufferCleared: + type: object + description: | + Returned when the input audio buffer is cleared by the client with a + `input_audio_buffer.clear` event. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.cleared + description: The event type, must be `input_audio_buffer.cleared`. + required: + - event_id + - type + x-oaiMeta: + name: input_audio_buffer.cleared + group: realtime + example: | + { + "event_id": "event_1314", + "type": "input_audio_buffer.cleared" + } + RealtimeServerEventInputAudioBufferCommitted: + type: object + description: > + Returned when an input audio buffer is committed, either by the client + or + + automatically in server VAD mode. The `item_id` property is the ID of + the user + + message item that will be created, thus a `conversation.item.created` + event + + will also be sent to the client. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.committed + description: The event type, must be `input_audio_buffer.committed`. + previous_item_id: + type: string + description: > + The ID of the preceding item after which the new item will be + inserted. + item_id: + type: string + description: The ID of the user message item that will be created. + required: + - event_id + - type + - previous_item_id + - item_id + x-oaiMeta: + name: input_audio_buffer.committed + group: realtime + example: | + { + "event_id": "event_1121", + "type": "input_audio_buffer.committed", + "previous_item_id": "msg_001", + "item_id": "msg_002" + } + RealtimeServerEventInputAudioBufferSpeechStarted: + type: object + description: > + Sent by the server when in `server_vad` mode to indicate that speech has + been + + detected in the audio buffer. This can happen any time audio is added to + the + + buffer (unless speech is already detected). The client may want to use + this + + event to interrupt audio playback or provide visual feedback to the + user. + + + The client should expect to receive a + `input_audio_buffer.speech_stopped` event + + when speech stops. The `item_id` property is the ID of the user message + item + + that will be created when speech stops and will also be included in the + + `input_audio_buffer.speech_stopped` event (unless the client manually + commits + + the audio buffer during VAD activation). + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.speech_started + description: The event type, must be `input_audio_buffer.speech_started`. + audio_start_ms: + type: integer + description: > + Milliseconds from the start of all audio written to the buffer + during the + + session when speech was first detected. This will correspond to the + + beginning of audio sent to the model, and thus includes the + + `prefix_padding_ms` configured in the Session. + item_id: + type: string + description: > + The ID of the user message item that will be created when speech + stops. + required: + - event_id + - type + - audio_start_ms + - item_id + x-oaiMeta: + name: input_audio_buffer.speech_started + group: realtime + example: | + { + "event_id": "event_1516", + "type": "input_audio_buffer.speech_started", + "audio_start_ms": 1000, + "item_id": "msg_003" + } + RealtimeServerEventInputAudioBufferSpeechStopped: + type: object + description: > + Returned in `server_vad` mode when the server detects the end of speech + in + + the audio buffer. The server will also send an + `conversation.item.created` + + event with the user message item that is created from the audio buffer. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.speech_stopped + description: The event type, must be `input_audio_buffer.speech_stopped`. + audio_end_ms: + type: integer + description: > + Milliseconds since the session started when speech stopped. This + will + + correspond to the end of audio sent to the model, and thus includes + the + + `min_silence_duration_ms` configured in the Session. + item_id: + type: string + description: The ID of the user message item that will be created. + required: + - event_id + - type + - audio_end_ms + - item_id + x-oaiMeta: + name: input_audio_buffer.speech_stopped + group: realtime + example: | + { + "event_id": "event_1718", + "type": "input_audio_buffer.speech_stopped", + "audio_end_ms": 2000, + "item_id": "msg_003" + } + RealtimeServerEventRateLimitsUpdated: + type: object + description: > + Emitted at the beginning of a Response to indicate the updated rate + limits. + + When a Response is created some tokens will be "reserved" for the + output + + tokens, the rate limits shown here reflect that reservation, which is + then + + adjusted accordingly once the Response is completed. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - rate_limits.updated + description: The event type, must be `rate_limits.updated`. + rate_limits: + type: array + description: List of rate limit information. + items: + type: object + properties: + name: + type: string + description: The name of the rate limit (`requests`, `tokens`). + limit: + type: integer + description: The maximum allowed value for the rate limit. + remaining: + type: integer + description: The remaining value before the limit is reached. + reset_seconds: + type: number + description: Seconds until the rate limit resets. + required: + - event_id + - type + - rate_limits + x-oaiMeta: + name: rate_limits.updated + group: realtime + example: | + { + "event_id": "event_5758", + "type": "rate_limits.updated", + "rate_limits": [ + { + "name": "requests", + "limit": 1000, + "remaining": 999, + "reset_seconds": 60 + }, + { + "name": "tokens", + "limit": 50000, + "remaining": 49950, + "reset_seconds": 60 + } + ] + } + RealtimeServerEventResponseAudioDelta: + type: object + description: Returned when the model-generated audio is updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio.delta + description: The event type, must be `response.audio.delta`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + delta: + type: string + description: Base64-encoded audio data delta. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - delta + x-oaiMeta: + name: response.audio.delta + group: realtime + example: | + { + "event_id": "event_4950", + "type": "response.audio.delta", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0, + "delta": "Base64EncodedAudioDelta" + } + RealtimeServerEventResponseAudioDone: + type: object + description: > + Returned when the model-generated audio is done. Also emitted when a + Response + + is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio.done + description: The event type, must be `response.audio.done`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + x-oaiMeta: + name: response.audio.done + group: realtime + example: | + { + "event_id": "event_5152", + "type": "response.audio.done", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0 + } + RealtimeServerEventResponseAudioTranscriptDelta: + type: object + description: > + Returned when the model-generated transcription of audio output is + updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio_transcript.delta + description: The event type, must be `response.audio_transcript.delta`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + delta: + type: string + description: The transcript delta. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - delta + x-oaiMeta: + name: response.audio_transcript.delta + group: realtime + example: | + { + "event_id": "event_4546", + "type": "response.audio_transcript.delta", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0, + "delta": "Hello, how can I a" + } + RealtimeServerEventResponseAudioTranscriptDone: + type: object + description: | + Returned when the model-generated transcription of audio output is done + streaming. Also emitted when a Response is interrupted, incomplete, or + cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio_transcript.done + description: The event type, must be `response.audio_transcript.done`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + transcript: + type: string + description: The final transcript of the audio. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - transcript + x-oaiMeta: + name: response.audio_transcript.done + group: realtime + example: | + { + "event_id": "event_4748", + "type": "response.audio_transcript.done", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0, + "transcript": "Hello, how can I assist you today?" + } + RealtimeServerEventResponseContentPartAdded: + type: object + description: > + Returned when a new content part is added to an assistant message item + during + + response generation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.content_part.added + description: The event type, must be `response.content_part.added`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item to which the content part was added. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + part: + type: object + description: The content part that was added. + properties: + type: + type: string + enum: + - audio + - text + description: The content type ("text", "audio"). + text: + type: string + description: The text content (if type is "text"). + audio: + type: string + description: Base64-encoded audio data (if type is "audio"). + transcript: + type: string + description: The transcript of the audio (if type is "audio"). + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - part + x-oaiMeta: + name: response.content_part.added + group: realtime + example: | + { + "event_id": "event_3738", + "type": "response.content_part.added", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "part": { + "type": "text", + "text": "" + } + } + RealtimeServerEventResponseContentPartDone: + type: object + description: > + Returned when a content part is done streaming in an assistant message + item. + + Also emitted when a Response is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.content_part.done + description: The event type, must be `response.content_part.done`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + part: + type: object + description: The content part that is done. + properties: + type: + type: string + description: The content type ("text", "audio"). + text: + type: string + description: The text content (if type is "text"). + audio: + type: string + description: Base64-encoded audio data (if type is "audio"). + transcript: + type: string + description: The transcript of the audio (if type is "audio"). + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - part + x-oaiMeta: + name: response.content_part.done + group: realtime + example: | + { + "event_id": "event_3940", + "type": "response.content_part.done", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "part": { + "type": "text", + "text": "Sure, I can help with that." + } + } + RealtimeServerEventResponseCreated: + type: object + description: > + Returned when a new Response is created. The first event of response + creation, + + where the response is in an initial state of `in_progress`. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.created + description: The event type, must be `response.created`. + response: + $ref: "#/components/schemas/RealtimeResponse" + required: + - event_id + - type + - response + x-oaiMeta: + name: response.created + group: realtime + example: | + { + "event_id": "event_2930", + "type": "response.created", + "response": { + "id": "resp_001", + "object": "realtime.response", + "status": "in_progress", + "status_details": null, + "output": [], + "usage": null + } + } + RealtimeServerEventResponseDone: + type: object + description: > + Returned when a Response is done streaming. Always emitted, no matter + the + + final state. The Response object included in the `response.done` event + will + + include all output Items in the Response but will omit the raw audio + data. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.done + description: The event type, must be `response.done`. + response: + $ref: "#/components/schemas/RealtimeResponse" + required: + - event_id + - type + - response + x-oaiMeta: + name: response.done + group: realtime + example: | + { + "event_id": "event_3132", + "type": "response.done", + "response": { + "id": "resp_001", + "object": "realtime.response", + "status": "completed", + "status_details": null, + "output": [ + { + "id": "msg_006", + "object": "realtime.item", + "type": "message", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "text", + "text": "Sure, how can I assist you today?" + } + ] + } + ], + "usage": { + "total_tokens":275, + "input_tokens":127, + "output_tokens":148, + "input_token_details": { + "cached_tokens":384, + "text_tokens":119, + "audio_tokens":8, + "cached_tokens_details": { + "text_tokens": 128, + "audio_tokens": 256 + } + }, + "output_token_details": { + "text_tokens":36, + "audio_tokens":112 + } + } + } + } + RealtimeServerEventResponseFunctionCallArgumentsDelta: + type: object + description: | + Returned when the model-generated function call arguments are updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.function_call_arguments.delta description: | - Vector store files represent files inside a vector store. - - Related guide: [File Search](/docs/assistants/tools/file-search) - navigationGroup: assistants - sections: - - type: endpoint - key: createVectorStoreFile - path: createFile - - type: endpoint - key: listVectorStoreFiles - path: listFiles - - type: endpoint - key: getVectorStoreFile - path: getFile - - type: endpoint - key: deleteVectorStoreFile - path: deleteFile - - type: object - key: VectorStoreFileObject - path: file-object - - id: vector-stores-file-batches - title: Vector Store File Batches - beta: true + The event type, must be `response.function_call_arguments.delta`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the function call item. + output_index: + type: integer + description: The index of the output item in the response. + call_id: + type: string + description: The ID of the function call. + delta: + type: string + description: The arguments delta as a JSON string. + required: + - event_id + - type + - response_id + - item_id + - output_index + - call_id + - delta + x-oaiMeta: + name: response.function_call_arguments.delta + group: realtime + example: | + { + "event_id": "event_5354", + "type": "response.function_call_arguments.delta", + "response_id": "resp_002", + "item_id": "fc_001", + "output_index": 0, + "call_id": "call_001", + "delta": "{\"location\": \"San\"" + } + RealtimeServerEventResponseFunctionCallArgumentsDone: + type: object + description: > + Returned when the model-generated function call arguments are done + streaming. + + Also emitted when a Response is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.function_call_arguments.done description: | - Vector store file batches represent operations to add multiple files to a vector store. - - Related guide: [File Search](/docs/assistants/tools/file-search) - navigationGroup: assistants - sections: - - type: endpoint - key: createVectorStoreFileBatch - path: createBatch - - type: endpoint - key: getVectorStoreFileBatch - path: getBatch - - type: endpoint - key: cancelVectorStoreFileBatch - path: cancelBatch - - type: endpoint - key: listFilesInVectorStoreBatch - path: listBatchFiles - - type: object - key: VectorStoreFileBatchObject - path: batch-object - - id: assistants-streaming - title: Streaming - beta: true + The event type, must be `response.function_call_arguments.done`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the function call item. + output_index: + type: integer + description: The index of the output item in the response. + call_id: + type: string + description: The ID of the function call. + arguments: + type: string + description: The final arguments as a JSON string. + required: + - event_id + - type + - response_id + - item_id + - output_index + - call_id + - arguments + x-oaiMeta: + name: response.function_call_arguments.done + group: realtime + example: | + { + "event_id": "event_5556", + "type": "response.function_call_arguments.done", + "response_id": "resp_002", + "item_id": "fc_001", + "output_index": 0, + "call_id": "call_001", + "arguments": "{\"location\": \"San Francisco\"}" + } + RealtimeServerEventResponseOutputItemAdded: + type: object + description: Returned when a new Item is created during Response generation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.output_item.added + description: The event type, must be `response.output_item.added`. + response_id: + type: string + description: The ID of the Response to which the item belongs. + output_index: + type: integer + description: The index of the output item in the Response. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - event_id + - type + - response_id + - output_index + - item + x-oaiMeta: + name: response.output_item.added + group: realtime + example: | + { + "event_id": "event_3334", + "type": "response.output_item.added", + "response_id": "resp_001", + "output_index": 0, + "item": { + "id": "msg_007", + "object": "realtime.item", + "type": "message", + "status": "in_progress", + "role": "assistant", + "content": [] + } + } + RealtimeServerEventResponseOutputItemDone: + type: object + description: > + Returned when an Item is done streaming. Also emitted when a Response + is + + interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.output_item.done + description: The event type, must be `response.output_item.done`. + response_id: + type: string + description: The ID of the Response to which the item belongs. + output_index: + type: integer + description: The index of the output item in the Response. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - event_id + - type + - response_id + - output_index + - item + x-oaiMeta: + name: response.output_item.done + group: realtime + example: | + { + "event_id": "event_3536", + "type": "response.output_item.done", + "response_id": "resp_001", + "output_index": 0, + "item": { + "id": "msg_007", + "object": "realtime.item", + "type": "message", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "text", + "text": "Sure, I can help with that." + } + ] + } + } + RealtimeServerEventResponseTextDelta: + type: object + description: Returned when the text value of a "text" content part is updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.text.delta + description: The event type, must be `response.text.delta`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + delta: + type: string + description: The text delta. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - delta + x-oaiMeta: + name: response.text.delta + group: realtime + example: | + { + "event_id": "event_4142", + "type": "response.text.delta", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "delta": "Sure, I can h" + } + RealtimeServerEventResponseTextDone: + type: object + description: > + Returned when the text value of a "text" content part is done streaming. + Also + + emitted when a Response is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.text.done + description: The event type, must be `response.text.done`. + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + text: + type: string + description: The final text content. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - text + x-oaiMeta: + name: response.text.done + group: realtime + example: | + { + "event_id": "event_4344", + "type": "response.text.done", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "text": "Sure, I can help with that." + } + RealtimeServerEventSessionCreated: + type: object + description: > + Returned when a Session is created. Emitted automatically when a new + + connection is established as the first server event. This event will + contain + + the default Session configuration. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - session.created + description: The event type, must be `session.created`. + session: + $ref: "#/components/schemas/RealtimeSession" + required: + - event_id + - type + - session + x-oaiMeta: + name: session.created + group: realtime + example: | + { + "event_id": "event_1234", + "type": "session.created", + "session": { + "id": "sess_001", + "object": "realtime.session", + "model": "gpt-4o-realtime-preview-2024-10-01", + "modalities": ["text", "audio"], + "instructions": "...model instructions here...", + "voice": "sage", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": null, + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 200 + }, + "tools": [], + "tool_choice": "auto", + "temperature": 0.8, + "max_response_output_tokens": "inf" + } + } + RealtimeServerEventSessionUpdated: + type: object + description: > + Returned when a session is updated with a `session.update` event, + unless + + there is an error. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - session.updated + description: The event type, must be `session.updated`. + session: + $ref: "#/components/schemas/RealtimeSession" + required: + - event_id + - type + - session + x-oaiMeta: + name: session.updated + group: realtime + example: | + { + "event_id": "event_5678", + "type": "session.updated", + "session": { + "id": "sess_001", + "object": "realtime.session", + "model": "gpt-4o-realtime-preview-2024-10-01", + "modalities": ["text"], + "instructions": "New instructions", + "voice": "sage", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": { + "model": "whisper-1" + }, + "turn_detection": null, + "tools": [], + "tool_choice": "none", + "temperature": 0.7, + "max_response_output_tokens": 200 + } + } + RealtimeSession: + type: object + description: Realtime session object configuration. + properties: + modalities: description: | - Stream the result of executing a Run or resuming a Run after submitting tool outputs. - - You can stream events from the [Create Thread and Run](/docs/api-reference/runs/createThreadAndRun), - [Create Run](/docs/api-reference/runs/createRun), and [Submit Tool Outputs](/docs/api-reference/runs/submitToolOutputs) - endpoints by passing `"stream": true`. The response will be a [Server-Sent events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) stream. - - Our Node and Python SDKs provide helpful utilities to make streaming easy. Reference the - [Assistants API quickstart](/docs/assistants/overview) to learn more. - navigationGroup: assistants - sections: - - type: object - key: MessageDeltaObject - path: message-delta-object - - type: object - key: RunStepDeltaObject - path: run-step-delta-object - - type: object - key: AssistantStreamEvent - path: events - - id: completions - title: Completions - legacy: true - navigationGroup: legacy + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + items: + type: string + enum: + - text + - audio + instructions: + type: string + description: > + The default system instructions (i.e. system message) prepended to + model + + calls. This field allows the client to guide the model on desired + + responses. The model can be instructed on response content and + format, + + (e.g. "be extremely succinct", "act friendly", "here are examples of + good + + responses") and on audio behavior (e.g. "talk quickly", "inject + emotion + + into your voice", "laugh frequently"). The instructions are not + guaranteed + + to be followed by the model, but they provide guidance to the model + on the + + desired behavior. + + + Note that the server sets default instructions which will be used if + this + + field is not set and are visible in the `session.created` event at + the + + start of the session. + voice: + type: string + enum: + - alloy + - ash + - ballad + - coral + - echo + - sage + - shimmer + - verse + description: > + The voice the model uses to respond. Current voice options are + `ash`, + + `ballad`, `coral`, `sage`, and `verse`. + + + Also supported but not recommended are `alloy`, `echo`, and + `shimmer`. + + These older voices are less expressive. + + + Voice cannot be changed during the session once the model has + + responded with audio at least once. + input_audio_format: + type: string + description: > + The format of input audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + output_audio_format: + type: string + description: > + The format of output audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + input_audio_transcription: + type: object + description: > + Configuration for input audio transcription, defaults to off and can + be + + set to `null` to turn off once on. Input audio transcription is not + native + + to the model, since the model consumes audio directly. Transcription + runs + + asynchronously through Whisper and should be treated as rough + guidance + + rather than the representation understood by the model. + properties: + model: + type: string + description: > + The model to use for transcription, `whisper-1` is the only + currently + + supported model. + turn_detection: + type: object + description: > + Configuration for turn detection. Can be set to `null` to turn off. + Server + + VAD means that the model will detect the start and end of speech + based on + + audio volume and respond at the end of user speech. + properties: + type: + type: string + description: > + Type of turn detection, only `server_vad` is currently supported. + threshold: + type: number + description: > + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. + A + + higher threshold will require louder audio to activate the + model, and + + thus might perform better in noisy environments. + prefix_padding_ms: + type: integer + description: | + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + silence_duration_ms: + type: integer + description: > + Duration of silence to detect speech stop (in milliseconds). + Defaults + + to 500ms. With shorter values the model will respond more + quickly, + + but may jump in on short pauses from the user. + tools: + type: array + description: Tools (functions) available to the model. + items: + type: object + properties: + type: + type: string + enum: + - function + description: The type of the tool, i.e. `function`. + name: + type: string + description: The name of the function. + description: + type: string + description: > + The description of the function, including guidance on when + and how + + to call it, and guidance about what to tell the user when + calling + + (if anything). + parameters: + type: object + description: Parameters of the function in JSON Schema. + tool_choice: + type: string + description: > + How the model chooses tools. Options are `auto`, `none`, `required`, + or + + specify a function. + temperature: + type: number + description: > + Sampling temperature for the model, limited to [0.6, 1.2]. Defaults + to 0.8. + max_response_output_tokens: + oneOf: + - type: integer + - type: string + enum: + - inf description: | - Given a prompt, the model will return one or more predicted completions along with the probabilities of alternative tokens at each position. Most developer should use our [Chat Completions API](/docs/guides/text-generation/text-generation-models) to leverage our best and newest models. - sections: - - type: endpoint - key: createCompletion - path: create - - type: object - key: CreateCompletionResponse - path: object + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + ResponseFormatJsonObject: + type: object + properties: + type: + type: string + description: "The type of response format being defined: `json_object`" + enum: + - json_object + required: + - type + ResponseFormatJsonSchema: + type: object + properties: + type: + type: string + description: "The type of response format being defined: `json_schema`" + enum: + - json_schema + json_schema: + type: object + properties: + description: + type: string + description: A description of what the response format is for, used by the model + to determine how to respond in the format. + name: + type: string + description: The name of the response format. Must be a-z, A-Z, 0-9, or contain + underscores and dashes, with a maximum length of 64. + schema: + $ref: "#/components/schemas/ResponseFormatJsonSchemaSchema" + strict: + type: boolean + nullable: true + default: false + description: Whether to enable strict schema adherence when generating the + output. If set to true, the model will always follow the exact + schema defined in the `schema` field. Only a subset of JSON + Schema is supported when `strict` is `true`. To learn more, read + the [Structured Outputs guide](/docs/guides/structured-outputs). + required: + - type + - name + required: + - type + - json_schema + ResponseFormatJsonSchemaSchema: + type: object + description: The schema for the response format, described as a JSON Schema object. + additionalProperties: true + ResponseFormatText: + type: object + properties: + type: + type: string + description: "The type of response format being defined: `text`" + enum: + - text + required: + - type + RunCompletionUsage: + type: object + description: Usage statistics related to the run. This value will be `null` if + the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.). + properties: + completion_tokens: + type: integer + description: Number of completion tokens used over the course of the run. + prompt_tokens: + type: integer + description: Number of prompt tokens used over the course of the run. + total_tokens: + type: integer + description: Total number of tokens used (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + nullable: true + RunObject: + type: object + title: A run on a thread + description: Represents an execution run on a [thread](/docs/api-reference/threads). + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `thread.run`. + type: string + enum: + - thread.run + created_at: + description: The Unix timestamp (in seconds) for when the run was created. + type: integer + thread_id: + description: The ID of the [thread](/docs/api-reference/threads) that was + executed on as a part of this run. + type: string + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) used for + execution of this run. + type: string + status: + description: The status of the run, which can be either `queued`, `in_progress`, + `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, + `incomplete`, or `expired`. + type: string + enum: + - queued + - in_progress + - requires_action + - cancelling + - cancelled + - failed + - completed + - incomplete + - expired + required_action: + type: object + description: Details on the action required to continue the run. Will be `null` + if no action is required. + nullable: true + properties: + type: + description: For now, this is always `submit_tool_outputs`. + type: string + enum: + - submit_tool_outputs + submit_tool_outputs: + type: object + description: Details on the tool outputs needed for this run to continue. + properties: + tool_calls: + type: array + description: A list of the relevant tool calls. + items: + $ref: "#/components/schemas/RunToolCallObject" + required: + - tool_calls + required: + - type + - submit_tool_outputs + last_error: + type: object + description: The last error associated with this run. Will be `null` if there + are no errors. + nullable: true + properties: + code: + type: string + description: One of `server_error`, `rate_limit_exceeded`, or `invalid_prompt`. + enum: + - server_error + - rate_limit_exceeded + - invalid_prompt + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + expires_at: + description: The Unix timestamp (in seconds) for when the run will expire. + type: integer + nullable: true + started_at: + description: The Unix timestamp (in seconds) for when the run was started. + type: integer + nullable: true + cancelled_at: + description: The Unix timestamp (in seconds) for when the run was cancelled. + type: integer + nullable: true + failed_at: + description: The Unix timestamp (in seconds) for when the run failed. + type: integer + nullable: true + completed_at: + description: The Unix timestamp (in seconds) for when the run was completed. + type: integer + nullable: true + incomplete_details: + description: Details on why the run is incomplete. Will be `null` if the run is + not incomplete. + type: object + nullable: true + properties: + reason: + description: The reason why the run is incomplete. This will point to which + specific token limit was reached over the course of the run. + type: string + enum: + - max_completion_tokens + - max_prompt_tokens + model: + description: The model that the [assistant](/docs/api-reference/assistants) used + for this run. + type: string + instructions: + description: The instructions that the + [assistant](/docs/api-reference/assistants) used for this run. + type: string + tools: + description: The list of tools that the + [assistant](/docs/api-reference/assistants) used for this run. + default: [] + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + usage: + $ref: "#/components/schemas/RunCompletionUsage" + temperature: + description: The sampling temperature used for this run. If not set, defaults to + 1. + type: number + nullable: true + top_p: + description: The nucleus sampling value used for this run. If not set, defaults + to 1. + type: number + nullable: true + max_prompt_tokens: + type: integer + nullable: true + description: > + The maximum number of prompt tokens specified to have been used over + the course of the run. + minimum: 256 + max_completion_tokens: + type: integer + nullable: true + description: > + The maximum number of completion tokens specified to have been used + over the course of the run. + minimum: 256 + truncation_strategy: + $ref: "#/components/schemas/TruncationObject" + nullable: true + tool_choice: + $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + nullable: true + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - id + - object + - created_at + - thread_id + - assistant_id + - status + - required_action + - last_error + - expires_at + - started_at + - cancelled_at + - failed_at + - completed_at + - model + - instructions + - tools + - metadata + - usage + - incomplete_details + - max_prompt_tokens + - max_completion_tokens + - truncation_strategy + - tool_choice + - parallel_tool_calls + - response_format + x-oaiMeta: + name: The run object + beta: true + example: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1698107661, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699073476, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699073498, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "tools": [{"type": "file_search"}, {"type": "code_interpreter"}], + "metadata": {}, + "incomplete_details": null, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + RunStepCompletionUsage: + type: object + description: Usage statistics related to the run step. This value will be `null` + while the run step's status is `in_progress`. + properties: + completion_tokens: + type: integer + description: Number of completion tokens used over the course of the run step. + prompt_tokens: + type: integer + description: Number of prompt tokens used over the course of the run step. + total_tokens: + type: integer + description: Total number of tokens used (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + nullable: true + RunStepDeltaObject: + type: object + title: Run step delta object + description: > + Represents a run step delta i.e. any changed fields on a run step during + streaming. + properties: + id: + description: The identifier of the run step, which can be referenced in API + endpoints. + type: string + object: + description: The object type, which is always `thread.run.step.delta`. + type: string + enum: + - thread.run.step.delta + delta: + description: The delta containing the fields that have changed on the run step. + type: object + properties: + step_details: + type: object + description: The details of the run step. + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsMessageCreationObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsObject" + x-oaiExpandable: true + required: + - id + - object + - delta + x-oaiMeta: + name: The run step delta object + beta: true + example: | + { + "id": "step_123", + "object": "thread.run.step.delta", + "delta": { + "step_details": { + "type": "tool_calls", + "tool_calls": [ + { + "index": 0, + "id": "call_123", + "type": "code_interpreter", + "code_interpreter": { "input": "", "outputs": [] } + } + ] + } + } + } + RunStepDeltaStepDetailsMessageCreationObject: + title: Message creation + type: object + description: Details of the message creation by the run step. + properties: + type: + description: Always `message_creation`. + type: string + enum: + - message_creation + message_creation: + type: object + properties: + message_id: + type: string + description: The ID of the message that was created by this run step. + required: + - type + RunStepDeltaStepDetailsToolCallsCodeObject: + title: Code interpreter tool call + type: object + description: Details of the Code Interpreter tool call the run step was involved in. + properties: + index: + type: integer + description: The index of the tool call in the tool calls array. + id: + type: string + description: The ID of the tool call. + type: + type: string + description: The type of tool call. This is always going to be + `code_interpreter` for this type of tool call. + enum: + - code_interpreter + code_interpreter: + type: object + description: The Code Interpreter tool call definition. + properties: + input: + type: string + description: The input to the Code Interpreter tool call. + outputs: + type: array + description: The outputs from the Code Interpreter tool call. Code Interpreter + can output one or more items, including text (`logs`) or images + (`image`). Each of these are represented by a different object + type. + items: + type: object + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputLogsObjec\ + t" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputImageObje\ + ct" + x-oaiExpandable: true + required: + - index + - type + RunStepDeltaStepDetailsToolCallsCodeOutputImageObject: + title: Code interpreter image output + type: object + properties: + index: + type: integer + description: The index of the output in the outputs array. + type: + description: Always `image`. + type: string + enum: + - image + image: + type: object + properties: + file_id: + description: The [file](/docs/api-reference/files) ID of the image. + type: string + required: + - index + - type + RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject: + title: Code interpreter log output + type: object + description: Text output from the Code Interpreter tool call as part of a run step. + properties: + index: + type: integer + description: The index of the output in the outputs array. + type: + description: Always `logs`. + type: string + enum: + - logs + logs: + type: string + description: The text output from the Code Interpreter tool call. + required: + - index + - type + RunStepDeltaStepDetailsToolCallsFileSearchObject: + title: File search tool call + type: object + properties: + index: + type: integer + description: The index of the tool call in the tool calls array. + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `file_search` for + this type of tool call. + enum: + - file_search + file_search: + type: object + description: For now, this is always going to be an empty object. + x-oaiTypeLabel: map + required: + - index + - type + - file_search + RunStepDeltaStepDetailsToolCallsFunctionObject: + type: object + title: Function tool call + properties: + index: + type: integer + description: The index of the tool call in the tool calls array. + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `function` for + this type of tool call. + enum: + - function + function: + type: object + description: The definition of the function that was called. + properties: + name: + type: string + description: The name of the function. + arguments: + type: string + description: The arguments passed to the function. + output: + type: string + description: The output of the function. This will be `null` if the outputs have + not been [submitted](/docs/api-reference/runs/submitToolOutputs) + yet. + nullable: true + required: + - index + - type + RunStepDeltaStepDetailsToolCallsObject: + title: Tool calls + type: object + description: Details of the tool call. + properties: + type: + description: Always `tool_calls`. + type: string + enum: + - tool_calls + tool_calls: + type: array + description: > + An array of tool calls the run step was involved in. These can be + associated with one of three types of tools: `code_interpreter`, + `file_search`, or `function`. + items: + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFileSearchObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFunctionObject" + x-oaiExpandable: true + required: + - type + RunStepDetailsMessageCreationObject: + title: Message creation + type: object + description: Details of the message creation by the run step. + properties: + type: + description: Always `message_creation`. + type: string + enum: + - message_creation + message_creation: + type: object + properties: + message_id: + type: string + description: The ID of the message that was created by this run step. + required: + - message_id + required: + - type + - message_creation + RunStepDetailsToolCallsCodeObject: + title: Code Interpreter tool call + type: object + description: Details of the Code Interpreter tool call the run step was involved in. + properties: + id: + type: string + description: The ID of the tool call. + type: + type: string + description: The type of tool call. This is always going to be + `code_interpreter` for this type of tool call. + enum: + - code_interpreter + code_interpreter: + type: object + description: The Code Interpreter tool call definition. + required: + - input + - outputs + properties: + input: + type: string + description: The input to the Code Interpreter tool call. + outputs: + type: array + description: The outputs from the Code Interpreter tool call. Code Interpreter + can output one or more items, including text (`logs`) or images + (`image`). Each of these are represented by a different object + type. + items: + type: object + oneOf: + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputLogsObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputImageObject" + x-oaiExpandable: true + required: + - id + - type + - code_interpreter + RunStepDetailsToolCallsCodeOutputImageObject: + title: Code Interpreter image output + type: object + properties: + type: + description: Always `image`. + type: string + enum: + - image + image: + type: object + properties: + file_id: + description: The [file](/docs/api-reference/files) ID of the image. + type: string + required: + - file_id + required: + - type + - image + RunStepDetailsToolCallsCodeOutputLogsObject: + title: Code Interpreter log output + type: object + description: Text output from the Code Interpreter tool call as part of a run step. + properties: + type: + description: Always `logs`. + type: string + enum: + - logs + logs: + type: string + description: The text output from the Code Interpreter tool call. + required: + - type + - logs + RunStepDetailsToolCallsFileSearchObject: + title: File search tool call + type: object + properties: + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `file_search` for + this type of tool call. + enum: + - file_search + file_search: + type: object + description: For now, this is always going to be an empty object. + x-oaiTypeLabel: map + properties: + ranking_options: + $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchRankingOptionsObje\ + ct" + results: + type: array + description: The results of the file search. + items: + $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchResultObject" + required: + - id + - type + - file_search + RunStepDetailsToolCallsFileSearchRankingOptionsObject: + title: File search tool call ranking options + type: object + description: The ranking options for the file search. + properties: + ranker: + type: string + description: The ranker used for the file search. + enum: + - default_2024_08_21 + score_threshold: + type: number + description: The score threshold for the file search. All values must be a + floating point number between 0 and 1. + minimum: 0 + maximum: 1 + required: + - ranker + - score_threshold + RunStepDetailsToolCallsFileSearchResultObject: + title: File search tool call result + type: object + description: A result instance of the file search. + x-oaiTypeLabel: map + properties: + file_id: + type: string + description: The ID of the file that result was found in. + file_name: + type: string + description: The name of the file that result was found in. + score: + type: number + description: The score of the result. All values must be a floating point number + between 0 and 1. + minimum: 0 + maximum: 1 + content: + type: array + description: The content of the result that was found. The content is only + included if requested via the include query parameter. + items: + type: object + properties: + type: + type: string + description: The type of the content. + enum: + - text + text: + type: string + description: The text content of the file. + required: + - file_id + - file_name + - score + RunStepDetailsToolCallsFunctionObject: + type: object + title: Function tool call + properties: + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `function` for + this type of tool call. + enum: + - function + function: + type: object + description: The definition of the function that was called. + properties: + name: + type: string + description: The name of the function. + arguments: + type: string + description: The arguments passed to the function. + output: + type: string + description: The output of the function. This will be `null` if the outputs have + not been [submitted](/docs/api-reference/runs/submitToolOutputs) + yet. + nullable: true + required: + - name + - arguments + - output + required: + - id + - type + - function + RunStepDetailsToolCallsObject: + title: Tool calls + type: object + description: Details of the tool call. + properties: + type: + description: Always `tool_calls`. + type: string + enum: + - tool_calls + tool_calls: + type: array + description: > + An array of tool calls the run step was involved in. These can be + associated with one of three types of tools: `code_interpreter`, + `file_search`, or `function`. + items: + oneOf: + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsFunctionObject" + x-oaiExpandable: true + required: + - type + - tool_calls + RunStepObject: + type: object + title: Run steps + description: | + Represents a step in execution of a run. + properties: + id: + description: The identifier of the run step, which can be referenced in API + endpoints. + type: string + object: + description: The object type, which is always `thread.run.step`. + type: string + enum: + - thread.run.step + created_at: + description: The Unix timestamp (in seconds) for when the run step was created. + type: integer + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) + associated with the run step. + type: string + thread_id: + description: The ID of the [thread](/docs/api-reference/threads) that was run. + type: string + run_id: + description: The ID of the [run](/docs/api-reference/runs) that this run step is + a part of. + type: string + type: + description: The type of run step, which can be either `message_creation` or + `tool_calls`. + type: string + enum: + - message_creation + - tool_calls + status: + description: The status of the run step, which can be either `in_progress`, + `cancelled`, `failed`, `completed`, or `expired`. + type: string + enum: + - in_progress + - cancelled + - failed + - completed + - expired + step_details: + type: object + description: The details of the run step. + oneOf: + - $ref: "#/components/schemas/RunStepDetailsMessageCreationObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsObject" + x-oaiExpandable: true + last_error: + type: object + description: The last error associated with this run step. Will be `null` if + there are no errors. + nullable: true + properties: + code: + type: string + description: One of `server_error` or `rate_limit_exceeded`. + enum: + - server_error + - rate_limit_exceeded + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + expired_at: + description: The Unix timestamp (in seconds) for when the run step expired. A + step is considered expired if the parent run is expired. + type: integer + nullable: true + cancelled_at: + description: The Unix timestamp (in seconds) for when the run step was cancelled. + type: integer + nullable: true + failed_at: + description: The Unix timestamp (in seconds) for when the run step failed. + type: integer + nullable: true + completed_at: + description: The Unix timestamp (in seconds) for when the run step completed. + type: integer + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + usage: + $ref: "#/components/schemas/RunStepCompletionUsage" + required: + - id + - object + - created_at + - assistant_id + - thread_id + - run_id + - type + - status + - step_details + - last_error + - expired_at + - cancelled_at + - failed_at + - completed_at + - metadata + - usage + x-oaiMeta: + name: The run step object + beta: true + example: | + { + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" + } + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } + } + RunStepStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: + - thread.run.step.created + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + is created. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.in_progress + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + moves to an `in_progress` state. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.delta + data: + $ref: "#/components/schemas/RunStepDeltaObject" + required: + - event + - data + description: Occurs when parts of a [run + step](/docs/api-reference/run-steps/step-object) are being streamed. + x-oaiMeta: + dataDescription: "`data` is a [run step + delta](/docs/api-reference/assistants-streaming/run-step-delta-ob\ + ject)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.completed + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + is completed. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.failed + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + fails. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.cancelled + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + is cancelled. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.expired + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + expires. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + RunStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: + - thread.run.created + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a new [run](/docs/api-reference/runs/object) is created. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.queued + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a + `queued` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.in_progress + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to an + `in_progress` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.requires_action + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a + `requires_action` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.completed + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) is completed. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.incomplete + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) ends with + status `incomplete`. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.failed + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) fails. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.cancelling + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a + `cancelling` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.cancelled + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) is cancelled. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.expired + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) expires. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + RunToolCallObject: + type: object + description: Tool call objects + properties: + id: + type: string + description: The ID of the tool call. This ID must be referenced when you submit + the tool outputs in using the [Submit tool outputs to + run](/docs/api-reference/runs/submitToolOutputs) endpoint. + type: + type: string + description: The type of tool call the output is required for. For now, this is + always `function`. + enum: + - function + function: + type: object + description: The function definition. + properties: + name: + type: string + description: The name of the function. + arguments: + type: string + description: The arguments that the model expects you to pass to the function. + required: + - name + - arguments + required: + - id + - type + - function + StaticChunkingStrategy: + type: object + additionalProperties: false + properties: + max_chunk_size_tokens: + type: integer + minimum: 100 + maximum: 4096 + description: The maximum number of tokens in each chunk. The default value is + `800`. The minimum value is `100` and the maximum value is `4096`. + chunk_overlap_tokens: + type: integer + description: > + The number of tokens that overlap between chunks. The default value + is `400`. + + + Note that the overlap must not exceed half of + `max_chunk_size_tokens`. + required: + - max_chunk_size_tokens + - chunk_overlap_tokens + StaticChunkingStrategyRequestParam: + type: object + title: Static Chunking Strategy + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + static: + $ref: "#/components/schemas/StaticChunkingStrategy" + required: + - type + - static + StaticChunkingStrategyResponseParam: + type: object + title: Static Chunking Strategy + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + static: + $ref: "#/components/schemas/StaticChunkingStrategy" + required: + - type + - static + SubmitToolOutputsRunRequest: + type: object + additionalProperties: false + properties: + tool_outputs: + description: A list of tools for which the outputs are being submitted. + type: array + items: + type: object + properties: + tool_call_id: + type: string + description: The ID of the tool call in the `required_action` object within the + run object the output is being submitted for. + output: + type: string + description: The output of the tool call to be submitted to continue the run. + stream: + type: boolean + nullable: true + description: > + If `true`, returns a stream of events that happen during the Run as + server-sent events, terminating when the Run enters a terminal state + with a `data: [DONE]` message. + required: + - tool_outputs + ThreadObject: + type: object + title: Thread + description: Represents a thread that contains + [messages](/docs/api-reference/messages). + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `thread`. + type: string + enum: + - thread + created_at: + description: The Unix timestamp (in seconds) for when the thread was created. + type: integer + tool_resources: + type: object + description: > + A set of resources that are made available to the assistant's tools + in this thread. The resources are specific to the type of tool. For + example, the `code_interpreter` tool requires a list of file IDs, + while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this thread. There can be a maximum of 1 vector + store attached to the thread. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + required: + - id + - object + - created_at + - tool_resources + - metadata + x-oaiMeta: + name: The thread object + beta: true + example: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1698107661, + "metadata": {} + } + ThreadStreamEvent: + oneOf: + - type: object + properties: + enabled: + type: boolean + description: Whether to enable input audio transcription. + event: + type: string + enum: + - thread.created + data: + $ref: "#/components/schemas/ThreadObject" + required: + - event + - data + description: Occurs when a new [thread](/docs/api-reference/threads/object) is + created. + x-oaiMeta: + dataDescription: "`data` is a [thread](/docs/api-reference/threads/object)" + TranscriptionSegment: + type: object + properties: + id: + type: integer + description: Unique identifier of the segment. + seek: + type: integer + description: Seek offset of the segment. + start: + type: number + format: float + description: Start time of the segment in seconds. + end: + type: number + format: float + description: End time of the segment in seconds. + text: + type: string + description: Text content of the segment. + tokens: + type: array + items: + type: integer + description: Array of token IDs for the text content. + temperature: + type: number + format: float + description: Temperature parameter used for generating the segment. + avg_logprob: + type: number + format: float + description: Average logprob of the segment. If the value is lower than -1, + consider the logprobs failed. + compression_ratio: + type: number + format: float + description: Compression ratio of the segment. If the value is greater than 2.4, + consider the compression failed. + no_speech_prob: + type: number + format: float + description: Probability of no speech in the segment. If the value is higher + than 1.0 and the `avg_logprob` is below -1, consider this segment + silent. + required: + - id + - seek + - start + - end + - text + - tokens + - temperature + - avg_logprob + - compression_ratio + - no_speech_prob + TranscriptionWord: + type: object + properties: + word: + type: string + description: The text content of the word. + start: + type: number + format: float + description: Start time of the word in seconds. + end: + type: number + format: float + description: End time of the word in seconds. + required: + - word + - start + - end + TruncationObject: + type: object + title: Thread Truncation Controls + description: Controls for how a thread will be truncated prior to the run. Use + this to control the intial context window of the run. + properties: + type: + type: string + description: The truncation strategy to use for the thread. The default is + `auto`. If set to `last_messages`, the thread will be truncated to + the n most recent messages in the thread. When set to `auto`, + messages in the middle of the thread will be dropped to fit the + context length of the model, `max_prompt_tokens`. + enum: + - auto + - last_messages + last_messages: + type: integer + description: The number of most recent messages from the thread when + constructing the context for the run. + minimum: 1 + nullable: true + required: + - type + UpdateVectorStoreRequest: + type: object + additionalProperties: false + properties: + name: + description: The name of the vector store. + type: string + nullable: true + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + Upload: + type: object + title: Upload + description: | + The Upload object can accept byte chunks in the form of Parts. + properties: + id: + type: string + description: The Upload unique identifier, which can be referenced in API + endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the Upload was created. + filename: + type: string + description: The name of the file to be uploaded. + bytes: + type: integer + description: The intended number of bytes to be uploaded. + purpose: + type: string + description: The intended purpose of the file. [Please refer + here](/docs/api-reference/files/object#files/object-purpose) for + acceptable values. + status: + type: string + description: The status of the Upload. + enum: + - pending + - completed + - cancelled + - expired + expires_at: + type: integer + description: The Unix timestamp (in seconds) for when the Upload was created. + object: + type: string + description: The object type, which is always "upload". + enum: + - upload + file: + $ref: "#/components/schemas/OpenAIFile" + nullable: true + description: The ready File object after the Upload is completed. + required: + - bytes + - created_at + - expires_at + - filename + - id + - purpose + - status + x-oaiMeta: + name: The upload object + example: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "completed", + "expires_at": 1719127296, + "file": { + "id": "file-xyz321", + "object": "file", + "bytes": 2147483648, + "created_at": 1719186911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + } + } + UploadPart: + type: object + title: UploadPart + description: > + The upload Part represents a chunk of bytes we can add to an Upload + object. + properties: + id: + type: string + description: The upload Part unique identifier, which can be referenced in API + endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the Part was created. + upload_id: + type: string + description: The ID of the Upload object that this Part was added to. + object: + type: string + description: The object type, which is always `upload.part`. + enum: + - upload.part + required: + - created_at + - id + - object + - upload_id + x-oaiMeta: + name: The upload part object + example: | + { + "id": "part_def456", + "object": "upload.part", + "created_at": 1719186911, + "upload_id": "upload_abc123" + } + UsageAudioSpeechesResult: + type: object + description: The aggregated audio speeches usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.audio_speeches.result + characters: + type: integer + description: The number of characters processed. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - characters + - num_model_requests + x-oaiMeta: + name: Audio speeches usage object + example: | + { + "object": "organization.usage.audio_speeches.result", + "characters": 45, + "num_model_requests": 1, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "tts-1" + } + UsageAudioTranscriptionsResult: + type: object + description: The aggregated audio transcriptions usage details of the specific + time bucket. + properties: + object: + type: string + enum: + - organization.usage.audio_transcriptions.result + seconds: + type: integer + description: The number of seconds processed. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - seconds + - num_model_requests + x-oaiMeta: + name: Audio transcriptions usage object + example: | + { + "object": "organization.usage.audio_transcriptions.result", + "seconds": 10, + "num_model_requests": 1, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "tts-1" + } + UsageCodeInterpreterSessionsResult: + type: object + description: The aggregated code interpreter sessions usage details of the + specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.code_interpreter_sessions.result + sessions: + type: integer + description: The number of code interpreter sessions. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + required: + - object + - sessions + x-oaiMeta: + name: Code interpreter sessions usage object + example: | + { + "object": "organization.usage.code_interpreter_sessions.result", + "sessions": 1, + "project_id": "proj_abc" + } + UsageCompletionsResult: + type: object + description: The aggregated completions usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.completions.result + input_tokens: + type: integer + description: The aggregated number of input tokens used. For customers subscribe + to scale tier, this includes scale tier tokens. + input_cached_tokens: + type: integer + description: The aggregated number of input tokens that has been cached from + previous requests. For customers subscribe to scale tier, this + includes scale tier tokens. + output_tokens: + type: integer + description: The aggregated number of output tokens used. For customers + subscribe to scale tier, this includes scale tier tokens. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + batch: + type: boolean + nullable: true + description: When `group_by=batch`, this field tells whether the grouped usage + result is batch or not. + required: + - object + - input_tokens + - output_tokens + - num_model_requests + x-oaiMeta: + name: Completions usage object + example: | + { + "object": "organization.usage.completions.result", + "input_tokens": 5000, + "output_tokens": 1000, + "input_cached_tokens": 4000, + "num_model_requests": 5, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "gpt-4o-mini-2024-07-18", + "batch": false + } + UsageEmbeddingsResult: + type: object + description: The aggregated embeddings usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.embeddings.result + input_tokens: + type: integer + description: The aggregated number of input tokens used. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - input_tokens + - num_model_requests + x-oaiMeta: + name: Embeddings usage object + example: | + { + "object": "organization.usage.embeddings.result", + "input_tokens": 20, + "num_model_requests": 2, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "text-embedding-ada-002-v2" + } + UsageImagesResult: + type: object + description: The aggregated images usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.images.result + images: + type: integer + description: The number of images processed. + num_model_requests: + type: integer + description: The count of requests made to the model. + source: + type: string + nullable: true + description: When `group_by=source`, this field provides the source of the + grouped usage result, possible values are `image.generation`, + `image.edit`, `image.variation`. + size: + type: string + nullable: true + description: When `group_by=size`, this field provides the image size of the + grouped usage result. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - images + - num_model_requests + x-oaiMeta: + name: Images usage object + example: | + { + "object": "organization.usage.images.result", + "images": 2, + "num_model_requests": 2, + "size": "1024x1024", + "source": "image.generation", + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "dall-e-3" + } + UsageModerationsResult: + type: object + description: The aggregated moderations usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.moderations.result + input_tokens: + type: integer + description: The aggregated number of input tokens used. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - input_tokens + - num_model_requests + x-oaiMeta: + name: Moderations usage object + example: | + { + "object": "organization.usage.moderations.result", + "input_tokens": 20, + "num_model_requests": 2, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "text-moderation" + } + UsageResponse: + type: object + properties: + object: + type: string + enum: + - page + data: + type: array + items: + $ref: "#/components/schemas/UsageTimeBucket" + has_more: + type: boolean + next_page: + type: string + required: + - object + - data + - has_more + - next_page + UsageTimeBucket: + type: object + properties: + object: + type: string + enum: + - bucket + start_time: + type: integer + end_time: + type: integer + result: + type: array + items: + oneOf: + - $ref: "#/components/schemas/UsageCompletionsResult" + - $ref: "#/components/schemas/UsageEmbeddingsResult" + - $ref: "#/components/schemas/UsageModerationsResult" + - $ref: "#/components/schemas/UsageImagesResult" + - $ref: "#/components/schemas/UsageAudioSpeechesResult" + - $ref: "#/components/schemas/UsageAudioTranscriptionsResult" + - $ref: "#/components/schemas/UsageVectorStoresResult" + - $ref: "#/components/schemas/UsageCodeInterpreterSessionsResult" + - $ref: "#/components/schemas/CostsResult" + required: + - object + - start_time + - end_time + - result + UsageVectorStoresResult: + type: object + description: The aggregated vector stores usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.vector_stores.result + usage_bytes: + type: integer + description: The vector stores usage in bytes. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + required: + - object + - usage_bytes + x-oaiMeta: + name: Vector stores usage object + example: | + { + "object": "organization.usage.vector_stores.result", + "usage_bytes": 1024, + "project_id": "proj_abc" + } + User: + type: object + description: Represents an individual `user` within an organization. + properties: + object: + type: string + enum: + - organization.user + description: The object type, which is always `organization.user` + id: + type: string + description: The identifier, which can be referenced in API endpoints + name: + type: string + description: The name of the user + email: + type: string + description: The email address of the user + role: + type: string + enum: + - owner + - reader + description: "`owner` or `reader`" + added_at: + type: integer + description: The Unix timestamp (in seconds) of when the user was added. + required: + - object + - id + - name + - email + - role + - added_at + x-oaiMeta: + name: The user object + example: | + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + UserDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.user.deleted + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + UserListResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: "#/components/schemas/User" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + UserRoleUpdateRequest: + type: object + properties: + role: + type: string + enum: + - owner + - reader + description: "`owner` or `reader`" + required: + - role + VectorStoreExpirationAfter: + type: object + title: Vector store expiration policy + description: The expiration policy for a vector store. + properties: + anchor: + description: "Anchor timestamp after which the expiration policy applies. + Supported anchors: `last_active_at`." + type: string + enum: + - last_active_at + days: + description: The number of days after the anchor time that the vector store will + expire. + type: integer + minimum: 1 + maximum: 365 + required: + - anchor + - days + VectorStoreFileBatchObject: + type: object + title: Vector store file batch + description: A batch of files attached to a vector store. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `vector_store.file_batch`. + type: string + enum: + - vector_store.files_batch + created_at: + description: The Unix timestamp (in seconds) for when the vector store files + batch was created. + type: integer + vector_store_id: + description: The ID of the [vector + store](/docs/api-reference/vector-stores/object) that the + [File](/docs/api-reference/files) is attached to. + type: string + status: + description: The status of the vector store files batch, which can be either + `in_progress`, `completed`, `cancelled` or `failed`. + type: string + enum: + - in_progress + - completed + - cancelled + - failed + file_counts: + type: object + properties: + in_progress: + description: The number of files that are currently being processed. + type: integer + completed: + description: The number of files that have been processed. + type: integer + failed: + description: The number of files that have failed to process. + type: integer + cancelled: + description: The number of files that where cancelled. + type: integer + total: + description: The total number of files. + type: integer + required: + - in_progress + - completed + - cancelled + - failed + - total + required: + - id + - object + - created_at + - vector_store_id + - status + - file_counts + x-oaiMeta: + name: The vector store files batch object + beta: true + example: | + { + "id": "vsfb_123", + "object": "vector_store.files_batch", + "created_at": 1698107661, + "vector_store_id": "vs_abc123", + "status": "completed", + "file_counts": { + "in_progress": 0, + "completed": 100, + "failed": 0, + "cancelled": 0, + "total": 100 + } + } + VectorStoreFileObject: + type: object + title: Vector store files + description: A list of files attached to a vector store. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `vector_store.file`. + type: string + enum: + - vector_store.file + usage_bytes: + description: The total vector store usage in bytes. Note that this may be + different from the original file size. + type: integer + created_at: + description: The Unix timestamp (in seconds) for when the vector store file was + created. + type: integer + vector_store_id: + description: The ID of the [vector + store](/docs/api-reference/vector-stores/object) that the + [File](/docs/api-reference/files) is attached to. + type: string + status: + description: The status of the vector store file, which can be either + `in_progress`, `completed`, `cancelled`, or `failed`. The status + `completed` indicates that the vector store file is ready for use. + type: string + enum: + - in_progress + - completed + - cancelled + - failed + last_error: + type: object + description: The last error associated with this vector store file. Will be + `null` if there are no errors. + nullable: true + properties: + code: + type: string + description: One of `server_error` or `rate_limit_exceeded`. + enum: + - server_error + - unsupported_file + - invalid_file + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + chunking_strategy: + type: object + description: The strategy used to chunk the file. + oneOf: + - $ref: "#/components/schemas/StaticChunkingStrategyResponseParam" + - $ref: "#/components/schemas/OtherChunkingStrategyResponseParam" + x-oaiExpandable: true + required: + - id + - object + - usage_bytes + - created_at + - vector_store_id + - status + - last_error + x-oaiMeta: + name: The vector store file object + beta: true + example: | + { + "id": "file-abc123", + "object": "vector_store.file", + "usage_bytes": 1234, + "created_at": 1698107661, + "vector_store_id": "vs_abc123", + "status": "completed", + "last_error": null, + "chunking_strategy": { + "type": "static", + "static": { + "max_chunk_size_tokens": 800, + "chunk_overlap_tokens": 400 + } + } + } + VectorStoreObject: + type: object + title: Vector store + description: A vector store is a collection of processed files can be used by + the `file_search` tool. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `vector_store`. + type: string + enum: + - vector_store + created_at: + description: The Unix timestamp (in seconds) for when the vector store was + created. + type: integer + name: + description: The name of the vector store. + type: string + usage_bytes: + description: The total number of bytes used by the files in the vector store. + type: integer + file_counts: + type: object + properties: + in_progress: + description: The number of files that are currently being processed. + type: integer + completed: + description: The number of files that have been successfully processed. + type: integer + failed: + description: The number of files that have failed to process. + type: integer + cancelled: + description: The number of files that were cancelled. + type: integer + total: + description: The total number of files. + type: integer + required: + - in_progress + - completed + - failed + - cancelled + - total + status: + description: The status of the vector store, which can be either `expired`, + `in_progress`, or `completed`. A status of `completed` indicates + that the vector store is ready for use. + type: string + enum: + - expired + - in_progress + - completed + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + expires_at: + description: The Unix timestamp (in seconds) for when the vector store will + expire. + type: integer + nullable: true + last_active_at: + description: The Unix timestamp (in seconds) for when the vector store was last + active. + type: integer + nullable: true + metadata: + description: > + Set of 16 key-value pairs that can be attached to an object. This + can be useful for storing additional information about the object in + a structured format. Keys can be a maximum of 64 characters long and + values can be a maximum of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + required: + - id + - object + - usage_bytes + - created_at + - status + - last_active_at + - name + - file_counts + - metadata + x-oaiMeta: + name: The vector store object + beta: true + example: | + { + "id": "vs_123", + "object": "vector_store", + "created_at": 1698107661, + "usage_bytes": 123456, + "last_active_at": 1698107661, + "name": "my_vector_store", + "status": "completed", + "file_counts": { + "in_progress": 0, + "completed": 100, + "cancelled": 0, + "failed": 0, + "total": 100 + }, + "metadata": {}, + "last_used_at": 1698107661 + } + securitySchemes: + ApiKeyAuth: + type: http + scheme: bearer +security: + - ApiKeyAuth: [] +x-oaiMeta: + navigationGroups: + - id: endpoints + title: Endpoints + - id: assistants + title: Assistants + beta: true + - id: administration + title: Administration + - id: realtime + title: Realtime + beta: true + - id: legacy + title: Legacy + groups: + - id: audio + title: Audio + description: | + Learn how to turn audio into text or text into audio. + + Related guide: [Speech to text](/docs/guides/speech-to-text) + navigationGroup: endpoints + sections: + - type: endpoint + key: createSpeech + path: createSpeech + - type: endpoint + key: createTranscription + path: createTranscription + - type: endpoint + key: createTranslation + path: createTranslation + - type: object + key: CreateTranscriptionResponseJson + path: json-object + - type: object + key: CreateTranscriptionResponseVerboseJson + path: verbose-json-object + - id: chat + title: Chat + description: > + Given a list of messages comprising a conversation, the model will + return a response. + + Related guide: [Chat Completions](/docs/guides/text-generation) + navigationGroup: endpoints + sections: + - type: endpoint + key: createChatCompletion + path: create + - type: object + key: CreateChatCompletionResponse + path: object + - type: object + key: CreateChatCompletionStreamResponse + path: streaming + - id: embeddings + title: Embeddings + description: > + Get a vector representation of a given input that can be easily consumed + by machine learning models and algorithms. + + Related guide: [Embeddings](/docs/guides/embeddings) + navigationGroup: endpoints + sections: + - type: endpoint + key: createEmbedding + path: create + - type: object + key: Embedding + path: object + - id: fine-tuning + title: Fine-tuning + description: > + Manage fine-tuning jobs to tailor a model to your specific training + data. + + Related guide: [Fine-tune models](/docs/guides/fine-tuning) + navigationGroup: endpoints + sections: + - type: endpoint + key: createFineTuningJob + path: create + - type: endpoint + key: listPaginatedFineTuningJobs + path: list + - type: endpoint + key: listFineTuningEvents + path: list-events + - type: endpoint + key: listFineTuningJobCheckpoints + path: list-checkpoints + - type: endpoint + key: retrieveFineTuningJob + path: retrieve + - type: endpoint + key: cancelFineTuningJob + path: cancel + - type: object + key: FinetuneChatRequestInput + path: chat-input + - type: object + key: FinetuneCompletionRequestInput + path: completions-input + - type: object + key: FineTuningJob + path: object + - type: object + key: FineTuningJobEvent + path: event-object + - type: object + key: FineTuningJobCheckpoint + path: checkpoint-object + - id: batch + title: Batch + description: > + Create large batches of API requests for asynchronous processing. The + Batch API returns completions within 24 hours for a 50% discount. + + Related guide: [Batch](/docs/guides/batch) + navigationGroup: endpoints + sections: + - type: endpoint + key: createBatch + path: create + - type: endpoint + key: retrieveBatch + path: retrieve + - type: endpoint + key: cancelBatch + path: cancel + - type: endpoint + key: listBatches + path: list + - type: object + key: Batch + path: object + - type: object + key: BatchRequestInput + path: request-input + - type: object + key: BatchRequestOutput + path: request-output + - id: files + title: Files + description: > + Files are used to upload documents that can be used with features like + [Assistants](/docs/api-reference/assistants), + [Fine-tuning](/docs/api-reference/fine-tuning), and [Batch + API](/docs/guides/batch). + navigationGroup: endpoints + sections: + - type: endpoint + key: createFile + path: create + - type: endpoint + key: listFiles + path: list + - type: endpoint + key: retrieveFile + path: retrieve + - type: endpoint + key: deleteFile + path: delete + - type: endpoint + key: downloadFile + path: retrieve-contents + - type: object + key: OpenAIFile + path: object + - id: uploads + title: Uploads + description: | + Allows you to upload large files in multiple parts. + navigationGroup: endpoints + sections: + - type: endpoint + key: createUpload + path: create + - type: endpoint + key: addUploadPart + path: add-part + - type: endpoint + key: completeUpload + path: complete + - type: endpoint + key: cancelUpload + path: cancel + - type: object + key: Upload + path: object + - type: object + key: UploadPart + path: part-object + - id: images + title: Images + description: > + Given a prompt and/or an input image, the model will generate a new + image. + + Related guide: [Image generation](/docs/guides/images) + navigationGroup: endpoints + sections: + - type: endpoint + key: createImage + path: create + - type: endpoint + key: createImageEdit + path: createEdit + - type: endpoint + key: createImageVariation + path: createVariation + - type: object + key: Image + path: object + - id: models + title: Models + description: > + List and describe the various models available in the API. You can refer + to the [Models](/docs/models) documentation to understand what models + are available and the differences between them. + navigationGroup: endpoints + sections: + - type: endpoint + key: listModels + path: list + - type: endpoint + key: retrieveModel + path: retrieve + - type: endpoint + key: deleteModel + path: delete + - type: object + key: Model + path: object + - id: moderations + title: Moderations + description: > + Given text and/or image inputs, classifies if those inputs are + potentially harmful across several categories. + + Related guide: [Moderations](/docs/guides/moderation) + navigationGroup: endpoints + sections: + - type: endpoint + key: createModeration + path: create + - type: object + key: CreateModerationResponse + path: object + - id: assistants + title: Assistants + beta: true + description: | + Build assistants that can call models and use tools to perform tasks. + + [Get started with the Assistants API](/docs/assistants) + navigationGroup: assistants + sections: + - type: endpoint + key: createAssistant + path: createAssistant + - type: endpoint + key: listAssistants + path: listAssistants + - type: endpoint + key: getAssistant + path: getAssistant + - type: endpoint + key: modifyAssistant + path: modifyAssistant + - type: endpoint + key: deleteAssistant + path: deleteAssistant + - type: object + key: AssistantObject + path: object + - id: threads + title: Threads + beta: true + description: | + Create threads that assistants can interact with. + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: createThread + path: createThread + - type: endpoint + key: getThread + path: getThread + - type: endpoint + key: modifyThread + path: modifyThread + - type: endpoint + key: deleteThread + path: deleteThread + - type: object + key: ThreadObject + path: object + - id: messages + title: Messages + beta: true + description: | + Create messages within threads + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: createMessage + path: createMessage + - type: endpoint + key: listMessages + path: listMessages + - type: endpoint + key: getMessage + path: getMessage + - type: endpoint + key: modifyMessage + path: modifyMessage + - type: endpoint + key: deleteMessage + path: deleteMessage + - type: object + key: MessageObject + path: object + - id: runs + title: Runs + beta: true + description: | + Represents an execution run on a thread. + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: createRun + path: createRun + - type: endpoint + key: createThreadAndRun + path: createThreadAndRun + - type: endpoint + key: listRuns + path: listRuns + - type: endpoint + key: getRun + path: getRun + - type: endpoint + key: modifyRun + path: modifyRun + - type: endpoint + key: submitToolOuputsToRun + path: submitToolOutputs + - type: endpoint + key: cancelRun + path: cancelRun + - type: object + key: RunObject + path: object + - id: run-steps + title: Run steps + beta: true + description: | + Represents the steps (model and tool calls) taken during the run. + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: listRunSteps + path: listRunSteps + - type: endpoint + key: getRunStep + path: getRunStep + - type: object + key: RunStepObject + path: step-object + - id: vector-stores + title: Vector stores + beta: true + description: | + Vector stores are used to store files for use by the `file_search` tool. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: assistants + sections: + - type: endpoint + key: createVectorStore + path: create + - type: endpoint + key: listVectorStores + path: list + - type: endpoint + key: getVectorStore + path: retrieve + - type: endpoint + key: modifyVectorStore + path: modify + - type: endpoint + key: deleteVectorStore + path: delete + - type: object + key: VectorStoreObject + path: object + - id: vector-stores-files + title: Vector store files + beta: true + description: | + Vector store files represent files inside a vector store. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: assistants + sections: + - type: endpoint + key: createVectorStoreFile + path: createFile + - type: endpoint + key: listVectorStoreFiles + path: listFiles + - type: endpoint + key: getVectorStoreFile + path: getFile + - type: endpoint + key: deleteVectorStoreFile + path: deleteFile + - type: object + key: VectorStoreFileObject + path: file-object + - id: vector-stores-file-batches + title: Vector store file batches + beta: true + description: > + Vector store file batches represent operations to add multiple files to + a vector store. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: assistants + sections: + - type: endpoint + key: createVectorStoreFileBatch + path: createBatch + - type: endpoint + key: getVectorStoreFileBatch + path: getBatch + - type: endpoint + key: cancelVectorStoreFileBatch + path: cancelBatch + - type: endpoint + key: listFilesInVectorStoreBatch + path: listBatchFiles + - type: object + key: VectorStoreFileBatchObject + path: batch-object + - id: assistants-streaming + title: Streaming + beta: true + description: > + Stream the result of executing a Run or resuming a Run after submitting + tool outputs. + + You can stream events from the [Create Thread and + Run](/docs/api-reference/runs/createThreadAndRun), + + [Create Run](/docs/api-reference/runs/createRun), and [Submit Tool + Outputs](/docs/api-reference/runs/submitToolOutputs) + + endpoints by passing `"stream": true`. The response will be a + [Server-Sent + events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) + stream. + + Our Node and Python SDKs provide helpful utilities to make streaming + easy. Reference the + + [Assistants API quickstart](/docs/assistants/overview) to learn more. + navigationGroup: assistants + sections: + - type: object + key: MessageDeltaObject + path: message-delta-object + - type: object + key: RunStepDeltaObject + path: run-step-delta-object + - type: object + key: AssistantStreamEvent + path: events + - id: administration + title: Administration + description: > + Programmatically manage your organization. + + The Audit Logs endpoint provides a log of all actions taken in + the organization for security and monitoring purposes. + + To access these endpoints please generate an Admin API Key through the + [API Platform Organization overview](/organization/admin-keys). Admin + API keys cannot be used for non-administration endpoints. + + For best practices on setting up your organization, please refer to this + [guide](/docs/guides/production-best-practices#setting-up-your-organization) + navigationGroup: administration + - id: invite + title: Invites + description: Invite and manage invitations for an organization. Invited users + are automatically added to the Default project. + navigationGroup: administration + sections: + - type: endpoint + key: list-invites + path: list + - type: endpoint + key: inviteUser + path: create + - type: endpoint + key: retrieve-invite + path: retrieve + - type: endpoint + key: delete-invite + path: delete + - type: object + key: Invite + path: object + - id: users + title: Users + description: > + Manage users and their role in an organization. Users will be + automatically added to the Default project. + navigationGroup: administration + sections: + - type: endpoint + key: list-users + path: list + - type: endpoint + key: modify-user + path: modify + - type: endpoint + key: retrieve-user + path: retrieve + - type: endpoint + key: delete-user + path: delete + - type: object + key: User + path: object + - id: projects + title: Projects + description: > + Manage the projects within an orgnanization includes creation, updating, + and archiving or projects. + + The Default project cannot be modified or archived. + navigationGroup: administration + sections: + - type: endpoint + key: list-projects + path: list + - type: endpoint + key: create-project + path: create + - type: endpoint + key: retrieve-project + path: retrieve + - type: endpoint + key: modify-project + path: modify + - type: endpoint + key: archive-project + path: archive + - type: object + key: Project + path: object + - id: project-users + title: Project users + description: > + Manage users within a project, including adding, updating roles, and + removing users. + + Users cannot be removed from the Default project, unless they are being + removed from the organization. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-users + path: list + - type: endpoint + key: create-project-user + path: creeate + - type: endpoint + key: retrieve-project-user + path: retrieve + - type: endpoint + key: modify-project-user + path: modify + - type: endpoint + key: delete-project-user + path: delete + - type: object + key: ProjectUser + path: object + - id: project-service-accounts + title: Project service accounts + description: > + Manage service accounts within a project. A service account is a bot + user that is not associated with a user. + + If a user leaves an organization, their keys and membership in projects + will no longer work. Service accounts + + do not have this limitation. However, service accounts can also be + deleted from a project. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-service-accounts + path: list + - type: endpoint + key: create-project-service-account + path: create + - type: endpoint + key: retrieve-project-service-account + path: retrieve + - type: endpoint + key: delete-project-service-account + path: delete + - type: object + key: ProjectServiceAccount + path: object + - id: project-api-keys + title: Project API keys + description: > + Manage API keys for a given project. Supports listing and deleting keys + for users. + + This API does not allow issuing keys for users, as users need to + authorize themselves to generate keys. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-api-keys + path: list + - type: endpoint + key: retrieve-project-api-key + path: retrieve + - type: endpoint + key: delete-project-api-key + path: delete + - type: object + key: ProjectApiKey + path: object + - id: project-rate-limits + title: Project rate limits + description: > + Manage rate limits per model for projects. Rate limits may be configured + to be equal to or lower than the organization's rate limits. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-rate-limits + path: list + - type: endpoint + key: update-project-rate-limits + path: update + - type: object + key: ProjectRateLimit + path: object + - id: audit-logs + title: Audit logs + description: > + Logs of user actions and configuration changes within this + organization. + + To log events, you must activate logging in the [Organization + Settings](/settings/organization/general). + + Once activated, for security reasons, logging cannot be deactivated. + navigationGroup: administration + sections: + - type: endpoint + key: list-audit-logs + path: list + - type: object + key: AuditLog + path: object + - id: usage + title: Usage + description: > + The **Usage API** provides detailed insights into your activity across + the OpenAI API. It also includes a separate [Costs + endpoint](/docs/api-reference/usage/costs), which offers visibility into + your spend, breaking down consumption by invoice line items and project + IDs. + + + While the Usage API delivers granular usage data, it may not always + reconcile perfectly with the Costs due to minor differences in how usage + and spend are recorded. For financial purposes, we recommend using the + [Costs endpoint](/docs/api-reference/usage/costs) or the [Costs + tab](/settings/organization/usage) in the Usage Dashboard, which will + reconcile back to your billing invoice. + navigationGroup: administration + sections: + - type: endpoint + key: usage-completions + path: completions + - type: object + key: UsageCompletionsResult + path: completions_object + - type: endpoint + key: usage-embeddings + path: embeddings + - type: object + key: UsageEmbeddingsResult + path: embeddings_object + - type: endpoint + key: usage-moderations + path: moderations + - type: object + key: UsageModerationsResult + path: moderations_object + - type: endpoint + key: usage-images + path: images + - type: object + key: UsageImagesResult + path: images_object + - type: endpoint + key: usage-audio-speeches + path: audio_speeches + - type: object + key: UsageAudioSpeechesResult + path: audio_speeches_object + - type: endpoint + key: usage-audio-transcriptions + path: audio_transcriptions + - type: object + key: UsageAudioTranscriptionsResult + path: audio_transcriptions_object + - type: endpoint + key: usage-vector-stores + path: vector_stores + - type: object + key: UsageVectorStoresResult + path: vector_stores_object + - type: endpoint + key: usage-code-interpreter-sessions + path: code_interpreter_sessions + - type: object + key: UsageCodeInterpreterSessionsResult + path: code_interpreter_sessions_object + - type: endpoint + key: usage-costs + path: costs + - type: object + key: CostsResult + path: costs_object + - id: realtime + title: Realtime + beta: true + description: > + Communicate with a GPT-4o class model live, in real time, over + WebSocket. + + Produces both audio and text transcriptions. + + [Learn more about the Realtime API](/docs/guides/realtime). + navigationGroup: realtime + - id: realtime-client-events + title: Client events + description: > + These are events that the OpenAI Realtime WebSocket server will accept + from the client. + navigationGroup: realtime + sections: + - type: object + key: RealtimeClientEventSessionUpdate + path: + - type: object + key: RealtimeClientEventInputAudioBufferAppend + path: + - type: object + key: RealtimeClientEventInputAudioBufferCommit + path: + - type: object + key: RealtimeClientEventInputAudioBufferClear + path: + - type: object + key: RealtimeClientEventConversationItemCreate + path: + - type: object + key: RealtimeClientEventConversationItemTruncate + path: + - type: object + key: RealtimeClientEventConversationItemDelete + path: + - type: object + key: RealtimeClientEventResponseCreate + path: + - type: object + key: RealtimeClientEventResponseCancel + path: + - id: realtime-server-events + title: Server events + description: > + These are events emitted from the OpenAI Realtime WebSocket server to + the client. + navigationGroup: realtime + sections: + - type: object + key: RealtimeServerEventError + path: + - type: object + key: RealtimeServerEventSessionCreated + path: + - type: object + key: RealtimeServerEventSessionUpdated + path: + - type: object + key: RealtimeServerEventConversationCreated + path: + - type: object + key: RealtimeServerEventConversationItemCreated + path: + - type: object + key: RealtimeServerEventConversationItemInputAudioTranscriptionCompleted + path: + - type: object + key: RealtimeServerEventConversationItemInputAudioTranscriptionFailed + path: + - type: object + key: RealtimeServerEventConversationItemTruncated + path: + - type: object + key: RealtimeServerEventConversationItemDeleted + path: + - type: object + key: RealtimeServerEventInputAudioBufferCommitted + path: + - type: object + key: RealtimeServerEventInputAudioBufferCleared + path: + - type: object + key: RealtimeServerEventInputAudioBufferSpeechStarted + path: + - type: object + key: RealtimeServerEventInputAudioBufferSpeechStopped + path: + - type: object + key: RealtimeServerEventResponseCreated + path: + - type: object + key: RealtimeServerEventResponseDone + path: + - type: object + key: RealtimeServerEventResponseOutputItemAdded + path: + - type: object + key: RealtimeServerEventResponseOutputItemDone + path: + - type: object + key: RealtimeServerEventResponseContentPartAdded + path: + - type: object + key: RealtimeServerEventResponseContentPartDone + path: + - type: object + key: RealtimeServerEventResponseTextDelta + path: + - type: object + key: RealtimeServerEventResponseTextDone + path: + - type: object + key: RealtimeServerEventResponseAudioTranscriptDelta + path: + - type: object + key: RealtimeServerEventResponseAudioTranscriptDone + path: + - type: object + key: RealtimeServerEventResponseAudioDelta + path: + - type: object + key: RealtimeServerEventResponseAudioDone + path: + - type: object + key: RealtimeServerEventResponseFunctionCallArgumentsDelta + path: + - type: object + key: RealtimeServerEventResponseFunctionCallArgumentsDone + path: + - type: object + key: RealtimeServerEventRateLimitsUpdated + path: + - id: completions + title: Completions + legacy: true + navigationGroup: legacy + description: > + Given a prompt, the model will return one or more predicted completions + along with the probabilities of alternative tokens at each position. + Most developer should use our [Chat Completions + API](/docs/guides/text-generation#text-generation-models) to leverage + our best and newest models. + sections: + - type: endpoint + key: createCompletion + path: create + - type: object + key: CreateCompletionResponse + path: object \ No newline at end of file