BedrockChat

import { BedrockChat } from '@langchain/community/chat_models/bedrock/web';

const llm = new BedrockChat({
  region: process.env.AWS_REGION,
  maxRetries: 0,
  model: "anthropic.claude-sonnet-4-5-20250929-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-sonnet-4-5-20250929-v1:0",
  credentials: {
    secretAccessKey: process.env.BEDROCK_AWS_SECRET_ACCESS_KEY!,
    accessKeyId: process.env.BEDROCK_AWS_ACCESS_KEY_ID!,
  },
});

const input = `Translate "I love programming" into French.`;

// Models also accept a list of chat messages or a formatted prompt
const result = await llm.invoke(input);
console.log(result);

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-sonnet-4-5-20250929",
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "usage": {
      "input_tokens": 25,
      "output_tokens": 19
    }
  },
  "tool_calls": [],
  "invalid_tool_calls": []
}

for await (const chunk of await llm.stream(input)) {
  console.log(chunk);
}

AIMessageChunk {
  "content": "",
  "additional_kwargs": {
    "id": "msg_bdrk_01RhFuGR9uJ2bj5GbdAma4y6"
  },
  "response_metadata": {
    "type": "message",
    "role": "assistant",
    "model": "claude-sonnet-4-5-20250929",
    "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
  }
}

import { AIMessageChunk } from '@langchain/core/messages';
import { concat } from '@langchain/core/utils/stream';

const stream = await llm.stream(input);
let full: AIMessageChunk | undefined;
for await (const chunk of stream) {
  full = !full ? chunk : concat(full, chunk);
}
console.log(full);

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-sonnet-4-5-20250929",
    "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
  }
}

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);

[
  {
    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'
  }
]

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);

{
  setup: "Why don't cats play poker in the jungle?",
  punchline: 'Too many cheetahs!'
}

const aiMsgForResponseMetadata = await llm.invoke(input);
console.log(aiMsgForResponseMetadata.response_metadata);

"response_metadata": {
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-4-5-20250929",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 25,
    "output_tokens": 19
  }
}