Class ChatMistralAI<CallOptions>

import { ChatMistralAI } from '@langchain/mistralai';

const llm = new ChatMistralAI({
  model: "mistral-large-2402",
  temperature: 0,
  // 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 {
  "content": "The translation of \"I love programming\" into French is \"J'aime la programmation\". Here's the breakdown:\n\n- \"I\" translates to \"Je\"\n- \"love\" translates to \"aime\"\n- \"programming\" translates to \"la programmation\"\n\nSo, \"J'aime la programmation\" means \"I love programming\" in French.",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 89,
      "promptTokens": 13,
      "totalTokens": 102
    },
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 13,
    "output_tokens": 89,
    "total_tokens": 102
  }
}
Copy

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

AIMessageChunk {
  "content": "The",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " translation",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " of",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " \"",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "I",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
 "content": ".",
 "additional_kwargs": {},
 "response_metadata": {
   "prompt": 0,
   "completion": 0
 },
 "tool_calls": [],
 "tool_call_chunks": [],
 "invalid_tool_calls": []
}
AIMessageChunk {
 "content": "",
 "additional_kwargs": {},
 "response_metadata": {
   "prompt": 0,
   "completion": 0
 },
 "tool_calls": [],
 "tool_call_chunks": [],
 "invalid_tool_calls": [],
 "usage_metadata": {
   "input_tokens": 13,
   "output_tokens": 89,
   "total_tokens": 102
 }
}
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 {
  "content": "The translation of \"I love programming\" into French is \"J'aime la programmation\". Here's the breakdown:\n\n- \"I\" translates to \"Je\"\n- \"love\" translates to \"aime\"\n- \"programming\" translates to \"la programmation\"\n\nSo, \"J'aime la programmation\" means \"I love programming\" in French.",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 13,
    "output_tokens": 89,
    "total_tokens": 102
  }
}
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' },
    type: 'tool_call',
    id: '47i216yko'
  },
  {
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'nb3v8Fpcn'
  },
  {
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call',
    id: 'EedWzByIB'
  },
  {
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'jLdLia7zC'
  }
]
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

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

{ input_tokens: 13, output_tokens: 89, total_tokens: 102 }
Copy