357 lines
9.1 KiB
JavaScript
357 lines
9.1 KiB
JavaScript
import { defaultProvider, } from "@aws-sdk/credential-provider-node";
|
|
import { BedrockChat as BaseBedrockChat } from "./web.js";
|
|
/**
|
|
* AWS Bedrock chat model integration.
|
|
*
|
|
* Setup:
|
|
* Install `@langchain/community` and set the following environment variables:
|
|
*
|
|
* ```bash
|
|
* npm install @langchain/openai
|
|
* export AWS_REGION="your-aws-region"
|
|
* export AWS_SECRET_ACCESS_KEY="your-aws-secret-access-key"
|
|
* export AWS_ACCESS_KEY_ID="your-aws-access-key-id"
|
|
* ```
|
|
*
|
|
* ## [Constructor args](/classes/langchain_community_chat_models_bedrock.BedrockChat.html#constructor)
|
|
*
|
|
* ## [Runtime args](/interfaces/langchain_community_chat_models_bedrock_web.BedrockChatCallOptions.html)
|
|
*
|
|
* Runtime args can be passed as the second argument to any of the base runnable methods `.invoke`. `.stream`, `.batch`, etc.
|
|
* They can also be passed via `.bind`, or the second arg in `.bindTools`, like shown in the examples below:
|
|
*
|
|
* ```typescript
|
|
* // When calling `.bind`, call options should be passed via the first argument
|
|
* const llmWithArgsBound = llm.bind({
|
|
* stop: ["\n"],
|
|
* tools: [...],
|
|
* });
|
|
*
|
|
* // When calling `.bindTools`, call options should be passed via the second argument
|
|
* const llmWithTools = llm.bindTools(
|
|
* [...],
|
|
* {
|
|
* stop: ["stop on this token!"],
|
|
* }
|
|
* );
|
|
* ```
|
|
*
|
|
* ## Examples
|
|
*
|
|
* <details open>
|
|
* <summary><strong>Instantiate</strong></summary>
|
|
*
|
|
* ```typescript
|
|
* import { BedrockChat } from '@langchain/community/chat_models/bedrock';
|
|
*
|
|
* const llm = new BedrockChat({
|
|
* region: process.env.BEDROCK_AWS_REGION,
|
|
* maxRetries: 0,
|
|
* model: "anthropic.claude-3-5-sonnet-20240620-v1:0",
|
|
* temperature: 0,
|
|
* maxTokens: undefined,
|
|
* // other params...
|
|
* });
|
|
*
|
|
* // You can also pass credentials in explicitly:
|
|
* const llmWithCredentials = new BedrockChat({
|
|
* region: process.env.BEDROCK_AWS_REGION,
|
|
* model: "anthropic.claude-3-5-sonnet-20240620-v1:0",
|
|
* credentials: {
|
|
* secretAccessKey: process.env.BEDROCK_AWS_SECRET_ACCESS_KEY!,
|
|
* accessKeyId: process.env.BEDROCK_AWS_ACCESS_KEY_ID!,
|
|
* },
|
|
* });
|
|
* ```
|
|
* </details>
|
|
*
|
|
* <br />
|
|
*
|
|
* <details>
|
|
* <summary><strong>Invoking</strong></summary>
|
|
*
|
|
* ```typescript
|
|
* const messages = [
|
|
* {
|
|
* type: "system" as const,
|
|
* content: "You are a helpful translator. Translate the user sentence to French.",
|
|
* },
|
|
* {
|
|
* type: "human" as const,
|
|
* content: "I love programming.",
|
|
* },
|
|
* ];
|
|
* const result = await llm.invoke(messages);
|
|
* console.log(result);
|
|
* ```
|
|
*
|
|
* ```txt
|
|
* AIMessage {
|
|
* "content": "Here's the translation to French:\n\nJ'adore la programmation.",
|
|
* "additional_kwargs": {
|
|
* "id": "msg_bdrk_01HCZHa2mKbMZeTeHjLDd286"
|
|
* },
|
|
* "response_metadata": {
|
|
* "type": "message",
|
|
* "role": "assistant",
|
|
* "model": "claude-3-5-sonnet-20240620",
|
|
* "stop_reason": "end_turn",
|
|
* "stop_sequence": null,
|
|
* "usage": {
|
|
* "input_tokens": 25,
|
|
* "output_tokens": 19
|
|
* }
|
|
* },
|
|
* "tool_calls": [],
|
|
* "invalid_tool_calls": []
|
|
* }
|
|
* ```
|
|
* </details>
|
|
*
|
|
* <br />
|
|
*
|
|
* <details>
|
|
* <summary><strong>Streaming Chunks</strong></summary>
|
|
*
|
|
* ```typescript
|
|
* for await (const chunk of await llm.stream(messages)) {
|
|
* console.log(chunk);
|
|
* }
|
|
* ```
|
|
*
|
|
* ```txt
|
|
* AIMessageChunk {
|
|
* "content": "",
|
|
* "additional_kwargs": {
|
|
* "id": "msg_bdrk_01RhFuGR9uJ2bj5GbdAma4y6"
|
|
* },
|
|
* "response_metadata": {
|
|
* "type": "message",
|
|
* "role": "assistant",
|
|
* "model": "claude-3-5-sonnet-20240620",
|
|
* "stop_reason": null,
|
|
* "stop_sequence": null
|
|
* },
|
|
* }
|
|
* AIMessageChunk {
|
|
* "content": "J",
|
|
* }
|
|
* AIMessageChunk {
|
|
* "content": "'adore la",
|
|
* }
|
|
* AIMessageChunk {
|
|
* "content": " programmation.",
|
|
* }
|
|
* AIMessageChunk {
|
|
* "content": "",
|
|
* "additional_kwargs": {
|
|
* "stop_reason": "end_turn",
|
|
* "stop_sequence": null
|
|
* },
|
|
* }
|
|
* AIMessageChunk {
|
|
* "content": "",
|
|
* "response_metadata": {
|
|
* "amazon-bedrock-invocationMetrics": {
|
|
* "inputTokenCount": 25,
|
|
* "outputTokenCount": 11,
|
|
* "invocationLatency": 659,
|
|
* "firstByteLatency": 506
|
|
* }
|
|
* },
|
|
* "usage_metadata": {
|
|
* "input_tokens": 25,
|
|
* "output_tokens": 11,
|
|
* "total_tokens": 36
|
|
* }
|
|
* }
|
|
* ```
|
|
* </details>
|
|
*
|
|
* <br />
|
|
*
|
|
* <details>
|
|
* <summary><strong>Aggregate Streamed Chunks</strong></summary>
|
|
*
|
|
* ```typescript
|
|
* import { AIMessageChunk } from '@langchain/core/messages';
|
|
* import { concat } from '@langchain/core/utils/stream';
|
|
*
|
|
* const stream = await llm.stream(messages);
|
|
* let full: AIMessageChunk | undefined;
|
|
* for await (const chunk of stream) {
|
|
* full = !full ? chunk : concat(full, chunk);
|
|
* }
|
|
* console.log(full);
|
|
* ```
|
|
*
|
|
* ```txt
|
|
* AIMessageChunk {
|
|
* "content": "J'adore la programmation.",
|
|
* "additional_kwargs": {
|
|
* "id": "msg_bdrk_017b6PuBybA51P5LZ9K6gZHm",
|
|
* "stop_reason": "end_turn",
|
|
* "stop_sequence": null
|
|
* },
|
|
* "response_metadata": {
|
|
* "type": "message",
|
|
* "role": "assistant",
|
|
* "model": "claude-3-5-sonnet-20240620",
|
|
* "stop_reason": null,
|
|
* "stop_sequence": null,
|
|
* "amazon-bedrock-invocationMetrics": {
|
|
* "inputTokenCount": 25,
|
|
* "outputTokenCount": 11,
|
|
* "invocationLatency": 1181,
|
|
* "firstByteLatency": 1177
|
|
* }
|
|
* },
|
|
* "usage_metadata": {
|
|
* "input_tokens": 25,
|
|
* "output_tokens": 11,
|
|
* "total_tokens": 36
|
|
* }
|
|
* }
|
|
* ```
|
|
* </details>
|
|
*
|
|
* <br />
|
|
*
|
|
* <details>
|
|
* <summary><strong>Bind tools</strong></summary>
|
|
*
|
|
* ```typescript
|
|
* import { z } from 'zod';
|
|
* import { AIMessage } from '@langchain/core/messages';
|
|
*
|
|
* const GetWeather = {
|
|
* name: "GetWeather",
|
|
* description: "Get the current weather in a given location",
|
|
* schema: z.object({
|
|
* location: z.string().describe("The city and state, e.g. San Francisco, CA")
|
|
* }),
|
|
* }
|
|
*
|
|
* const GetPopulation = {
|
|
* name: "GetPopulation",
|
|
* description: "Get the current population in a given location",
|
|
* schema: z.object({
|
|
* location: z.string().describe("The city and state, e.g. San Francisco, CA")
|
|
* }),
|
|
* }
|
|
*
|
|
* const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);
|
|
* const aiMsg: AIMessage = await llmWithTools.invoke(
|
|
* "Which city is hotter today and which is bigger: LA or NY?"
|
|
* );
|
|
* console.log(aiMsg.tool_calls);
|
|
* ```
|
|
*
|
|
* ```txt
|
|
* [
|
|
* {
|
|
* name: 'GetWeather',
|
|
* args: { location: 'Los Angeles, CA' },
|
|
* id: 'toolu_bdrk_01R2daqwHR931r4baVNzbe38',
|
|
* type: 'tool_call'
|
|
* },
|
|
* {
|
|
* name: 'GetWeather',
|
|
* args: { location: 'New York, NY' },
|
|
* id: 'toolu_bdrk_01WDadwNc7PGqVZvCN7Dr7eD',
|
|
* type: 'tool_call'
|
|
* },
|
|
* {
|
|
* name: 'GetPopulation',
|
|
* args: { location: 'Los Angeles, CA' },
|
|
* id: 'toolu_bdrk_014b8zLkpAgpxrPfewKinJFc',
|
|
* type: 'tool_call'
|
|
* },
|
|
* {
|
|
* name: 'GetPopulation',
|
|
* args: { location: 'New York, NY' },
|
|
* id: 'toolu_bdrk_01Tt8K2MUP15kNuMDFCLEFKN',
|
|
* type: 'tool_call'
|
|
* }
|
|
* ]
|
|
* ```
|
|
* </details>
|
|
*
|
|
* <br />
|
|
*
|
|
* <details>
|
|
* <summary><strong>Structured Output</strong></summary>
|
|
*
|
|
* ```typescript
|
|
* const Joke = z.object({
|
|
* setup: z.string().describe("The setup of the joke"),
|
|
* punchline: z.string().describe("The punchline to the joke"),
|
|
* rating: z.number().optional().describe("How funny the joke is, from 1 to 10")
|
|
* }).describe('Joke to tell user.');
|
|
*
|
|
* const structuredLlm = llm.withStructuredOutput(Joke);
|
|
* const jokeResult = await structuredLlm.invoke("Tell me a joke about cats");
|
|
* console.log(jokeResult);
|
|
* ```
|
|
*
|
|
* ```txt
|
|
* {
|
|
* setup: "Why don't cats play poker in the jungle?",
|
|
* punchline: 'Too many cheetahs!'
|
|
* }
|
|
* ```
|
|
* </details>
|
|
*
|
|
* <br />
|
|
*
|
|
* <details>
|
|
* <summary><strong>Response Metadata</strong></summary>
|
|
*
|
|
* ```typescript
|
|
* const aiMsgForResponseMetadata = await llm.invoke(messages);
|
|
* console.log(aiMsgForResponseMetadata.response_metadata);
|
|
* ```
|
|
*
|
|
* ```txt
|
|
* "response_metadata": {
|
|
* "type": "message",
|
|
* "role": "assistant",
|
|
* "model": "claude-3-5-sonnet-20240620",
|
|
* "stop_reason": "end_turn",
|
|
* "stop_sequence": null,
|
|
* "usage": {
|
|
* "input_tokens": 25,
|
|
* "output_tokens": 19
|
|
* }
|
|
* }
|
|
* ```
|
|
* </details>
|
|
*/
|
|
export class BedrockChat extends BaseBedrockChat {
|
|
static lc_name() {
|
|
return "BedrockChat";
|
|
}
|
|
constructor(fields) {
|
|
const { profile, filepath, configFilepath, ignoreCache, mfaCodeProvider, roleAssumer, roleArn, webIdentityTokenFile, roleAssumerWithWebIdentity, ...rest } = fields ?? {};
|
|
super({
|
|
...rest,
|
|
credentials: rest?.credentials ??
|
|
defaultProvider({
|
|
profile,
|
|
filepath,
|
|
configFilepath,
|
|
ignoreCache,
|
|
mfaCodeProvider,
|
|
roleAssumer,
|
|
roleArn,
|
|
webIdentityTokenFile,
|
|
roleAssumerWithWebIdentity,
|
|
}),
|
|
});
|
|
}
|
|
}
|
|
export { convertMessagesToPromptAnthropic, convertMessagesToPrompt, } from "./web.js";
|
|
/**
|
|
* @deprecated Use `BedrockChat` instead.
|
|
*/
|
|
export const ChatBedrock = BedrockChat;
|