Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

docs[minor]: Add TogetherAI updated integration doc #6314

Merged
merged 2 commits into from
Aug 1, 2024
Merged

docs[minor]: Add TogetherAI updated integration doc #6314

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2407149
docs[minor]: Add TogetherAI updated integration doc
bracesproul Aug 1, 2024
4e9b474
drop old file
bracesproul Aug 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
343 changes: 343 additions & 0 deletions docs/core_docs/docs/integrations/chat/togetherai.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,343 @@
{
"cells": [
{
"cell_type": "raw",
"id": "afaf8039",
"metadata": {
"vscode": {
"languageId": "raw"
}
},
"source": [
"---\n",
"sidebar_label: Together\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "e49f1e0d",
"metadata": {},
"source": [
"# ChatTogetherAI\n",
"\n",
"This will help you getting started with `ChatTogetherAI` [chat models](/docs/concepts/#chat-models). For detailed documentation of all `ChatTogetherAI` features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain_community_chat_models_togetherai.ChatTogetherAI.html).\n",
"\n",
"## Overview\n",
"### Integration details\n",
"\n",
"| Class | Package | Local | Serializable | [PY support](https://python.langchain.com/v0.2/docs/integrations/chat/togetherai) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
"| [ChatTogetherAI](https://api.js.langchain.com/classes/langchain_community_chat_models_togetherai.ChatTogetherAI.html) | [@langchain/community](https://api.js.langchain.com/modules/langchain_community_chat_models_togetherai.html) | ❌ | ✅ | ✅ | ![NPM - Downloads](https://img.shields.io/npm/dm/@langchain/community?style=flat-square&label=%20&) | ![NPM - Version](https://img.shields.io/npm/v/@langchain/community?style=flat-square&label=%20&) |\n",
"\n",
"### Model features\n",
"| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
"| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |\n",
"| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | \n",
"\n",
"## Setup\n",
"\n",
"To access `ChatTogetherAI` models you'll need to create a Together account, get an API key [here](https://api.together.xyz/), and install the `@langchain/community` integration package.\n",
"\n",
"### Credentials\n",
"\n",
"Head to [api.together.ai](https://api.together.ai/) to sign up to TogetherAI and generate an API key. Once you've done this set the `TOGETHER_AI_API_KEY` environment variable:\n",
"\n",
"```bash\n",
"export TOGETHER_AI_API_KEY=\"your-api-key\"\n",
"```\n",
"\n",
"If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:\n",
"\n",
"```bash\n",
"# export LANGCHAIN_TRACING_V2=\"true\"\n",
"# export LANGCHAIN_API_KEY=\"your-api-key\"\n",
"```\n",
"\n",
"### Installation\n",
"\n",
"The LangChain ChatTogetherAI integration lives in the `@langchain/community` package:\n",
"\n",
"```{=mdx}\n",
"import IntegrationInstallTooltip from \"@mdx_components/integration_install_tooltip.mdx\";\n",
"import Npm2Yarn from \"@theme/Npm2Yarn\";\n",
"\n",
"<IntegrationInstallTooltip></IntegrationInstallTooltip>\n",
"\n",
"<Npm2Yarn>\n",
" @langchain/community\n",
"</Npm2Yarn>\n",
"\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "a38cde65-254d-4219-a441-068766c0d4b5",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our model object and generate chat completions:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
"metadata": {},
"outputs": [],
"source": [
"import { ChatTogetherAI } from \"@langchain/community/chat_models/togetherai\"\n",
"\n",
"const llm = new ChatTogetherAI({\n",
" model: \"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n",
" temperature: 0,\n",
" maxTokens: undefined,\n",
" timeout: undefined,\n",
" maxRetries: 2,\n",
" // other params...\n",
"})"
]
},
{
"cell_type": "markdown",
"id": "2b4f3e15",
"metadata": {},
"source": [
"## Invocation"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "62e0dbc3",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"AIMessage {\n",
" \"id\": \"chatcmpl-9rT9qEDPZ6iLCk6jt3XTzVDDH6pcI\",\n",
" \"content\": \"J'adore la programmation.\",\n",
" \"additional_kwargs\": {},\n",
" \"response_metadata\": {\n",
" \"tokenUsage\": {\n",
" \"completionTokens\": 8,\n",
" \"promptTokens\": 31,\n",
" \"totalTokens\": 39\n",
" },\n",
" \"finish_reason\": \"stop\"\n",
" },\n",
" \"tool_calls\": [],\n",
" \"invalid_tool_calls\": [],\n",
" \"usage_metadata\": {\n",
" \"input_tokens\": 31,\n",
" \"output_tokens\": 8,\n",
" \"total_tokens\": 39\n",
" }\n",
"}\n"
]
}
],
"source": [
"const aiMsg = await llm.invoke([\n",
" [\n",
" \"system\",\n",
" \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
" ],\n",
" [\"human\", \"I love programming.\"],\n",
"])\n",
"aiMsg"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"J'adore la programmation.\n"
]
}
],
"source": [
"console.log(aiMsg.content)"
]
},
{
"cell_type": "markdown",
"id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
"metadata": {},
"source": [
"## Chaining\n",
"\n",
"We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"AIMessage {\n",
" \"id\": \"chatcmpl-9rT9wolZWfJ3xovORxnkdf1rcPbbY\",\n",
" \"content\": \"Ich liebe das Programmieren.\",\n",
" \"additional_kwargs\": {},\n",
" \"response_metadata\": {\n",
" \"tokenUsage\": {\n",
" \"completionTokens\": 6,\n",
" \"promptTokens\": 26,\n",
" \"totalTokens\": 32\n",
" },\n",
" \"finish_reason\": \"stop\"\n",
" },\n",
" \"tool_calls\": [],\n",
" \"invalid_tool_calls\": [],\n",
" \"usage_metadata\": {\n",
" \"input_tokens\": 26,\n",
" \"output_tokens\": 6,\n",
" \"total_tokens\": 32\n",
" }\n",
"}\n"
]
}
],
"source": [
"import { ChatPromptTemplate } from \"@langchain/core/prompts\"\n",
"\n",
"const prompt = ChatPromptTemplate.fromMessages(\n",
" [\n",
" [\n",
" \"system\",\n",
" \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
" ],\n",
" [\"human\", \"{input}\"],\n",
" ]\n",
")\n",
"\n",
"const chain = prompt.pipe(llm);\n",
"await chain.invoke(\n",
" {\n",
" input_language: \"English\",\n",
" output_language: \"German\",\n",
" input: \"I love programming.\",\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
"metadata": {},
"source": [
"## Tool calling & JSON mode\n",
"\n",
"The TogetherAI chat supports JSON mode and calling tools.\n",
"\n",
"### Tool calling"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "8de584a8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[\n",
" {\n",
" name: 'calculator',\n",
" args: { input: '2 + 3' },\n",
" type: 'tool_call',\n",
" id: 'call_nhtnmganqJPAG9I1cN8ULI9R'\n",
" }\n",
"]\n"
]
}
],
"source": [
"import { ChatTogetherAI } from \"@langchain/community/chat_models/togetherai\";\n",
"import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n",
"import { convertToOpenAITool } from \"@langchain/core/utils/function_calling\";\n",
"import { Calculator } from \"@langchain/community/tools/calculator\";\n",
"\n",
"// Use a pre-built tool\n",
"const calculatorTool = convertToOpenAITool(new Calculator());\n",
"\n",
"const modelWithCalculator = new ChatTogetherAI({\n",
" temperature: 0,\n",
" // This is the default env variable name it will look for if none is passed.\n",
" apiKey: process.env.TOGETHER_AI_API_KEY,\n",
" // Together JSON mode/tool calling only supports a select number of models\n",
" model: \"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n",
"}).bind({\n",
" // Bind the tool to the model.\n",
" tools: [calculatorTool],\n",
" tool_choice: calculatorTool, // Specify what tool the model should use\n",
"});\n",
"\n",
"const promptForTools = ChatPromptTemplate.fromMessages([\n",
" [\"system\", \"You are a super not-so-smart mathmatician.\"],\n",
" [\"human\", \"Help me out, how can I add {math}?\"],\n",
"]);\n",
"\n",
"// Use LCEL to chain the prompt to the model.\n",
"const responseWithTool = await promptForTools.pipe(modelWithCalculator).invoke({\n",
" math: \"2 plus 3\",\n",
"});\n",
"\n",
"console.dir(responseWithTool.tool_calls, { depth: null });"
]
},
{
"cell_type": "markdown",
"id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
"metadata": {},
"source": [
"Behind the scenes, TogetherAI uses the OpenAI SDK and OpenAI compatible API, with some caveats:\n",
"\n",
"- Certain properties are not supported by the TogetherAI API, see [here](https://docs.together.ai/reference/chat-completions).\n",
"\n",
"## API reference\n",
"\n",
"For detailed documentation of all ChatTogetherAI features and configurations head to the API reference: https://api.js.langchain.com/classes/langchain_community_chat_models_togetherai.ChatTogetherAI.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "TypeScript",
"language": "typescript",
"name": "tslab"
},
"language_info": {
"codemirror_mode": {
"mode": "typescript",
"name": "javascript",
"typescript": true
},
"file_extension": ".ts",
"mimetype": "text/typescript",
"name": "typescript",
"version": "3.7.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Loading
Loading