Class ChatBedrockConverse

import { ChatBedrockConverse } from '@langchain/aws';

const llm = new ChatBedrockConverse({
  model: "anthropic.claude-3-5-sonnet-20240620-v1:0",
  temperature: 0,
  maxTokens: undefined,
  timeout: undefined,
  maxRetries: 2,
  region: process.env.BEDROCK_AWS_REGION,
  credentials: {
    secretAccessKey: process.env.BEDROCK_AWS_SECRET_ACCESS_KEY!,
    accessKeyId: process.env.BEDROCK_AWS_ACCESS_KEY_ID!,
  },
  // other params...
});
Copy

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);
Copy

AIMessage {
  "id": "81a27f7a-550c-473d-8307-c2fbb9c74956",
  "content": "Here's the translation to French:\n\nJ'adore la programmation.",
  "response_metadata": {
    "$metadata": {
      "httpStatusCode": 200,
      "requestId": "81a27f7a-550c-473d-8307-c2fbb9c74956",
      "attempts": 1,
      "totalRetryDelay": 0
    },
    "metrics": {
      "latencyMs": 1109
    },
    "stopReason": "end_turn",
    "usage": {
      "inputTokens": 25,
      "outputTokens": 19,
      "totalTokens": 44
    }
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 19,
    "total_tokens": 44
  }
}
Copy

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

AIMessageChunk {
  "content": ""
  "response_metadata": {
    "messageStart": {
      "p": "abcdefghijk",
      "role": "assistant"
    }
  }
}
AIMessageChunk {
  "content": "Here"
}
AIMessageChunk {
  "content": "'s"
}
AIMessageChunk {
  "content": " the translation"
}
AIMessageChunk {
  "content": " to"
}
AIMessageChunk {
  "content": " French:\n\nJ"
}
AIMessageChunk {
  "content": "'adore la"
}
AIMessageChunk {
  "content": " programmation."
}
AIMessageChunk {
  "content": ""
  "response_metadata": {
    "contentBlockStop": {
      "contentBlockIndex": 0,
      "p": "abcdefghijk"
    }
  }
}
AIMessageChunk {
  "content": ""
  "response_metadata": {
    "messageStop": {
      "stopReason": "end_turn"
    }
  }
}
AIMessageChunk {
  "content": ""
  "response_metadata": {
    "metadata": {
      "metrics": {
        "latencyMs": 838
      },
      "p": "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123",
      "usage": {
        "inputTokens": 25,
        "outputTokens": 19,
        "totalTokens": 44
      }
    }
  }
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 19,
    "total_tokens": 44
  }
}
Copy

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);
Copy

AIMessageChunk {
  "content": "Here's the translation to French:\n\nJ'adore la programmation.",
  "response_metadata": {
    "messageStart": {
      "p": "ab",
      "role": "assistant"
    },
    "contentBlockStop": {
      "contentBlockIndex": 0,
      "p": "abcdefghijklmnopqrstuvwxyzABCDEFGHIJK"
    },
    "messageStop": {
      "stopReason": "end_turn"
    },
    "metadata": {
      "metrics": {
        "latencyMs": 838
      },
      "p": "abcdefghijklmnopqrstuvwxyz",
      "usage": {
        "inputTokens": 25,
        "outputTokens": 19,
        "totalTokens": 44
      }
    }
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 19,
    "total_tokens": 44
  }
}
Copy

import { z } from 'zod';

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],
  {
    // strict: true  // enforce tool args schema is respected
  }
);
const aiMsg = await llmWithTools.invoke(
  "Which city is hotter today and which is bigger: LA or NY?"
);
console.log(aiMsg.tool_calls);
Copy

[
  {
    id: 'tooluse_hIaiqfweRtSiJyi6J4naJA',
    name: 'GetWeather',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call'
  },
  {
    id: 'tooluse_nOS8B0UlTd2FdpH4MSHw9w',
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    type: 'tool_call'
  },
  {
    id: 'tooluse_XxMpZiETQ5aVS5opVDyIaw',
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call'
  },
  {
    id: 'tooluse_GpYvAfldT2aR8VQfH-p4PQ',
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    type: 'tool_call'
  }
]
Copy

import { z } from 'zod';

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);
Copy

{
  setup: "Why don't cats play poker in the jungle?",
  punchline: 'Too many cheetahs!',
  rating: 7
}
Copy

import { HumanMessage } from '@langchain/core/messages';

const imageUrl = "https://example.com/image.jpg";
const imageData = await fetch(imageUrl).then(res => res.arrayBuffer());
const base64Image = Buffer.from(imageData).toString('base64');

const message = new HumanMessage({
  content: [
    { type: "text", text: "describe the weather in this image" },
    {
      type: "image_url",
      image_url: { url: `data:image/jpeg;base64,${base64Image}` },
    },
  ]
});

const imageDescriptionAiMsg = await llm.invoke([message]);
console.log(imageDescriptionAiMsg.content);
Copy

The weather in this image appears to be clear and pleasant. The sky is a vibrant blue with scattered white clouds, suggesting a sunny day with good visibility. The clouds are light and wispy, indicating fair weather conditions. There's no sign of rain, storm, or any adverse weather patterns. The lush green grass on the rolling hills looks well-watered and healthy, which could indicate recent rainfall or generally favorable weather conditions. Overall, the image depicts a beautiful, calm day with blue skies and sunshine - perfect weather for enjoying the outdoors.
Copy

const aiMsgForMetadata = await llm.invoke(messages);
console.log(aiMsgForMetadata.usage_metadata);
Copy

{ input_tokens: 25, output_tokens: 19, total_tokens: 44 }
Copy

const streamForMetadata = await llm.stream(messages);
let fullForMetadata: AIMessageChunk | undefined;
for await (const chunk of streamForMetadata) {
  fullForMetadata = !fullForMetadata ? chunk : concat(fullForMetadata, chunk);
}
console.log(fullForMetadata?.usage_metadata);
Copy

{ input_tokens: 25, output_tokens: 19, total_tokens: 44 }
Copy

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

{
  '$metadata': {
    httpStatusCode: 200,
    requestId: '5de2a2e5-d1dc-4dff-bb02-31361f4107bc',
    extendedRequestId: undefined,
    cfId: undefined,
    attempts: 1,
    totalRetryDelay: 0
  },
  metrics: { latencyMs: 1163 },
  stopReason: 'end_turn',
  usage: { inputTokens: 25, outputTokens: 19, totalTokens: 44 }
}
Copy