feat(docs): update

README.md

@@ -34,10 +34,12 @@ You can search HuggingFace for available models (Keyword: [`GGUF`](https://huggi
 For create a GGUF model manually, for example in Llama 2:
 
 Download the Llama 2 model
+
 1. Request access from [here](https://ai.meta.com/llama)
 2. Download the model from HuggingFace [here](https://huggingface.co/meta-llama/Llama-2-7b-chat) (`Llama-2-7b-chat`)
 
 Convert the model to ggml format
+
 ```bash
 # Start with submodule in this repo (or you can clone the repo https://github.com/ggerganov/llama.cpp.git)
 yarn && yarn bootstrap
@@ -76,26 +78,53 @@ const context = await initLlama({
   // embedding: true, // use embedding
 })
 
-// Do completion
-const { text, timings } = await context.completion(
+const stopWords = ['</s>', '<|end|>', '<|eot_id|>', '<|end_of_text|>', '<|im_end|>', '<|EOT|>', '<|END_OF_TURN_TOKEN|>', '<|end_of_turn|>', '<|endoftext|>']
+
+// Do chat completion
+const msgResult = await context.completion(
+  {
+    messages: [
+      {
+        role: 'system',
+        content: 'This is a conversation between user and assistant, a friendly chatbot.',
+      },
+      {
+        role: 'user,
+        content: 'Hello!',
+      },
+    ],
+    n_predict: 100,
+    stop: stopWords,
+    // ...other params
+  },
+  (data) => {
+    // This is a partial completion callback
+    const { token } = data
+  },
+)
+console.log('Result:', msgResult.text)
+console.log('Timings:', msgResult.timings)
+
+// Or do text completion
+const textResult = await context.completion(
   {
     prompt: 'This is a conversation between user and llama, a friendly chatbot. respond in simple markdown.\n\nUser: Hello!\nLlama:',
     n_predict: 100,
-    stop: ['</s>', 'Llama:', 'User:'],
-    // n_threads: 4,
+    stop: [...stopWords, 'Llama:', 'User:'],
+    // ...other params
   },
   (data) => {
     // This is a partial completion callback
     const { token } = data
   },
 )
-console.log('Result:', text)
-console.log('Timings:', timings)
+console.log('Result:', textResult.text)
+console.log('Timings:', textResult.timings)
 ```
 
 The binding’s deisgn inspired by [server.cpp](https://github.com/ggerganov/llama.cpp/tree/master/examples/server) example in llama.cpp, so you can map its API to LlamaContext:
 
-- `/completion`: `context.completion(params, partialCompletionCallback)`
+- `/completion` and `/chat/completions`: `context.completion(params, partialCompletionCallback)`
 - `/tokenize`: `context.tokenize(content)`
 - `/detokenize`: `context.detokenize(tokens)`
 - `/embedding`: `context.embedding(content)`
@@ -110,6 +139,7 @@ Please visit the [Documentation](docs/API) for more details.
 You can also visit the [example](example) to see how to use it.
 
 Run the example:
+
 ```bash
 yarn && yarn bootstrap
 
@@ -142,7 +172,9 @@ You can see [GBNF Guide](https://github.com/ggerganov/llama.cpp/tree/master/gram
 ```js
 import { initLlama, convertJsonSchemaToGrammar } from 'llama.rn'
 
-const schema = { /* JSON Schema, see below */ }
+const schema = {
+  /* JSON Schema, see below */
+}
 
 const context = await initLlama({
   model: 'file://<path to gguf model>',
@@ -153,7 +185,7 @@ const context = await initLlama({
   grammar: convertJsonSchemaToGrammar({
     schema,
     propOrder: { function: 0, arguments: 1 },
-  })
+  }),
 })
 
 const { text } = await context.completion({
@@ -171,80 +203,81 @@ console.log('Result:', text)
 {
   oneOf: [
     {
-      type: "object",
-      name: "get_current_weather",
-      description: "Get the current weather in a given location",
+      type: 'object',
+      name: 'get_current_weather',
+      description: 'Get the current weather in a given location',
       properties: {
         function: {
-          const: "get_current_weather",
+          const: 'get_current_weather',
         },
         arguments: {
-          type: "object",
+          type: 'object',
           properties: {
             location: {
-              type: "string",
-              description: "The city and state, e.g. San Francisco, CA",
+              type: 'string',
+              description: 'The city and state, e.g. San Francisco, CA',
             },
             unit: {
-              type: "string",
-              enum: ["celsius", "fahrenheit"],
+              type: 'string',
+              enum: ['celsius', 'fahrenheit'],
             },
           },
-          required: ["location"],
+          required: ['location'],
         },
       },
     },
     {
-      type: "object",
-      name: "create_event",
-      description: "Create a calendar event",
+      type: 'object',
+      name: 'create_event',
+      description: 'Create a calendar event',
       properties: {
         function: {
-          const: "create_event",
+          const: 'create_event',
         },
         arguments: {
-          type: "object",
+          type: 'object',
           properties: {
             title: {
-              type: "string",
-              description: "The title of the event",
+              type: 'string',
+              description: 'The title of the event',
             },
             date: {
-              type: "string",
-              description: "The date of the event",
+              type: 'string',
+              description: 'The date of the event',
             },
             time: {
-              type: "string",
-              description: "The time of the event",
+              type: 'string',
+              description: 'The time of the event',
             },
           },
-          required: ["title", "date", "time"],
+          required: ['title', 'date', 'time'],
         },
       },
     },
     {
-      type: "object",
-      name: "image_search",
-      description: "Search for an image",
+      type: 'object',
+      name: 'image_search',
+      description: 'Search for an image',
       properties: {
         function: {
-          const: "image_search",
+          const: 'image_search',
         },
         arguments: {
-          type: "object",
+          type: 'object',
           properties: {
             query: {
-              type: "string",
-              description: "The search query",
+              type: 'string',
+              description: 'The search query',
             },
           },
-          required: ["query"],
+          required: ['query'],
         },
       },
     },
   ],
 }
 ```
+
 </details>
 
 <details>
@@ -268,6 +301,7 @@ string ::=  "\"" (
 2 ::= "{" space "\"function\"" space ":" space 2-function "," space "\"arguments\"" space ":" space 2-arguments "}" space
 root ::= 0 | 1 | 2
 ```
+
 </details>
 
 ## Mock `llama.rn`
@@ -281,12 +315,14 @@ jest.mock('llama.rn', () => require('llama.rn/jest/mock'))
 ## NOTE
 
 iOS:
+
 - The [Extended Virtual Addressing](https://developer.apple.com/documentation/bundleresources/entitlements/com_apple_developer_kernel_extended-virtual-addressing) capability is recommended to enable on iOS project.
 - Metal:
   - We have tested to know some devices is not able to use Metal ('params.n_gpu_layers > 0') due to llama.cpp used SIMD-scoped operation, you can check if your device is supported in [Metal feature set tables](https://developer.apple.com/metal/Metal-Feature-Set-Tables.pdf), Apple7 GPU will be the minimum requirement.
   - It's also not supported in iOS simulator due to [this limitation](https://developer.apple.com/documentation/metal/developing_metal_apps_that_run_in_simulator#3241609), we used constant buffers more than 14.
 
 Android:
+
 - Currently only supported arm64-v8a / x86_64 platform, this means you can't initialize a context on another platforms. The 64-bit platform are recommended because it can allocate more memory for the model.
 - No integrated any GPU backend yet.
 

docs/API/README.md

@@ -43,17 +43,17 @@ llama.rn
 
 #### Defined in
 
-[index.ts:43](https://github.com/mybigday/llama.rn/blob/f95f600/src/index.ts#L43)
+[index.ts:51](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/index.ts#L51)
 
 ___
 
 ### CompletionParams
 
-Ƭ **CompletionParams**: `Omit`<`NativeCompletionParams`, ``"emit_partial_completion"``\>
+Ƭ **CompletionParams**: `Omit`<`NativeCompletionParams`, ``"emit_partial_completion"`` \| ``"prompt"``\> & { `messages?`: `RNLlamaOAICompatibleMessage`[] ; `prompt?`: `string`  }
 
 #### Defined in
 
-[index.ts:41](https://github.com/mybigday/llama.rn/blob/f95f600/src/index.ts#L41)
+[index.ts:43](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/index.ts#L43)
 
 ___
 
@@ -63,7 +63,7 @@ ___
 
 #### Defined in
 
-[index.ts:39](https://github.com/mybigday/llama.rn/blob/f95f600/src/index.ts#L39)
+[index.ts:41](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/index.ts#L41)
 
 ___
 
@@ -80,7 +80,7 @@ ___
 
 #### Defined in
 
-[index.ts:29](https://github.com/mybigday/llama.rn/blob/f95f600/src/index.ts#L29)
+[index.ts:31](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/index.ts#L31)
 
 ## Functions
 
@@ -104,7 +104,7 @@ ___
 
 #### Defined in
 
-[grammar.ts:824](https://github.com/mybigday/llama.rn/blob/f95f600/src/grammar.ts#L824)
+[grammar.ts:824](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/grammar.ts#L824)
 
 ___
 
@@ -124,7 +124,7 @@ ___
 
 #### Defined in
 
-[index.ts:166](https://github.com/mybigday/llama.rn/blob/f95f600/src/index.ts#L166)
+[index.ts:191](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/index.ts#L191)
 
 ___
 
@@ -138,7 +138,7 @@ ___
 
 #### Defined in
 
-[index.ts:182](https://github.com/mybigday/llama.rn/blob/f95f600/src/index.ts#L182)
+[index.ts:211](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/index.ts#L211)
 
 ___
 
@@ -158,4 +158,4 @@ ___
 
 #### Defined in
 
-[index.ts:162](https://github.com/mybigday/llama.rn/blob/f95f600/src/index.ts#L162)
+[index.ts:187](https://github.com/mybigday/llama.rn/blob/ad7e0a5/src/index.ts#L187)