Class ChatAnthropic

import { ChatAnthropic } from '@langchain/anthropic';

const llm = new ChatAnthropic({
  model: "claude-3-5-sonnet-20240620",
  temperature: 0,
  maxTokens: undefined,
  maxRetries: 2,
  // apiKey: "...",
  // baseUrl: "...",
  // other params...
});
Copy

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);
Copy

AIMessage {
  "id": "msg_01QDpd78JUHpRP6bRRNyzbW3",
  "content": "Here's the translation to French:\n\nJ'adore la programmation.",
  "response_metadata": {
    "id": "msg_01QDpd78JUHpRP6bRRNyzbW3",
    "model": "claude-3-5-sonnet-20240620",
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "usage": {
      "input_tokens": 25,
      "output_tokens": 19
    },
    "type": "message",
    "role": "assistant"
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 19,
    "total_tokens": 44
  }
}
Copy

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

AIMessageChunk {
  "id": "msg_01N8MwoYxiKo9w4chE4gXUs4",
  "content": "",
  "additional_kwargs": {
    "id": "msg_01N8MwoYxiKo9w4chE4gXUs4",
    "type": "message",
    "role": "assistant",
    "model": "claude-3-5-sonnet-20240620"
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 1,
    "total_tokens": 26
  }
}
AIMessageChunk {
  "content": "",
}
AIMessageChunk {
  "content": "Here",
}
AIMessageChunk {
  "content": "'s",
}
AIMessageChunk {
  "content": " the translation to",
}
AIMessageChunk {
  "content": " French:\n\nJ",
}
AIMessageChunk {
  "content": "'adore la programmation",
}
AIMessageChunk {
  "content": ".",
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {
    "stop_reason": "end_turn",
    "stop_sequence": null
  },
  "usage_metadata": {
    "input_tokens": 0,
    "output_tokens": 19,
    "total_tokens": 19
  }
}
Copy

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);
Copy

AIMessageChunk {
  "id": "msg_01SBTb5zSGXfjUc7yQ8EKEEA",
  "content": "Here's the translation to French:\n\nJ'adore la programmation.",
  "additional_kwargs": {
    "id": "msg_01SBTb5zSGXfjUc7yQ8EKEEA",
    "type": "message",
    "role": "assistant",
    "model": "claude-3-5-sonnet-20240620",
    "stop_reason": "end_turn",
    "stop_sequence": null
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 20,
    "total_tokens": 45
  }
}
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]);
const aiMsg = await llmWithTools.invoke(
  "Which city is hotter today and which is bigger: LA or NY?"
);
console.log(aiMsg.tool_calls);
Copy

[
  {
    name: 'GetWeather',
    args: { location: 'Los Angeles, CA' },
    id: 'toolu_01WjW3Dann6BPJVtLhovdBD5',
    type: 'tool_call'
  },
  {
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    id: 'toolu_01G6wfJgqi5zRmJomsmkyZXe',
    type: 'tool_call'
  },
  {
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    id: 'toolu_0165qYWBA2VFyUst5RA18zew',
    type: 'tool_call'
  },
  {
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    id: 'toolu_01PGNyP33vxr13tGqr7i3rDo',
    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, { name: "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 beautiful and clear. The sky is a vibrant blue with scattered white clouds, suggesting a sunny and pleasant day. The clouds are wispy and light, indicating calm conditions without any signs of storms or heavy weather. The bright green grass on the rolling hills looks lush and well-watered, which could mean recent rainfall or good growing conditions. Overall, the scene depicts a perfect spring or early summer day with mild temperatures, plenty of sunshine, and gentle breezes - ideal weather for enjoying the outdoors or for plant growth.
Copy

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

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

const streamForMetadata = await llm.stream(
  input,
  {
    streamUsage: true
  }
);
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: 20, total_tokens: 45 }
Copy

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

{
  id: 'msg_01STxeQxJmp4sCSpioD6vK3L',
  model: 'claude-3-5-sonnet-20240620',
  stop_reason: 'end_turn',
  stop_sequence: null,
  usage: { input_tokens: 25, output_tokens: 19 },
  type: 'message',
  role: 'assistant'
}
Copy