Class ChatXAI

import { ChatXAI } from '@langchain/xai';

const llm = new ChatXAI({
  model: "grok-beta",
  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 French translation of \"I love programming\" is \"J'aime programmer\". In this sentence, \"J'aime\" is the first person singular conjugation of the French verb \"aimer\" which means \"to love\", and \"programmer\" is the French infinitive for \"to program\". I hope this helps! Let me know if you have any other questions.",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 82,
      "promptTokens": 20,
      "totalTokens": 102
    },
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "invalid_tool_calls": []
}
Copy

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

AIMessageChunk {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "The",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " French",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " translation",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " of",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " \"",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "I",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " love",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
...
AIMessageChunk {
  "content": ".",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
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 French translation of \"I love programming\" is \"J'aime programmer\". In this sentence, \"J'aime\" is the first person singular conjugation of the French verb \"aimer\" which means \"to love\", and \"programmer\" is the French infinitive for \"to program\". I hope this helps! Let me know if you have any other questions.",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
Copy

import { z } from 'zod';

const llmForToolCalling = new ChatXAI({
  model: "grok-beta",
  temperature: 0,
  // other params...
});

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 = llmForToolCalling.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: 'call_cd34'
  },
  {
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'call_68rf'
  },
  {
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call',
    id: 'call_f81z'
  },
  {
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'call_8byt'
  }
]
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 = llmForToolCalling.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 wild?",
  punchline: 'Because there are too many cheetahs.'
}
Copy

xAI supports server-side tools that are executed by the API rather than requiring client-side execution. The live_search tool enables the model to search the web for real-time information.

// Method 1: Using the built-in live_search tool
const llm = new ChatXAI({
  model: "grok-beta",
  temperature: 0,
});

const llmWithSearch = llm.bindTools([{ type: "live_search" }]);
const result = await llmWithSearch.invoke("What happened in tech news today?");
console.log(result.content);
// The model will search the web and include real-time information in its response
Copy

// Method 2: Using searchParameters for more control
const llm = new ChatXAI({
  model: "grok-beta",
  searchParameters: {
    mode: "auto", // "auto" | "on" | "off"
    max_search_results: 5,
    from_date: "2024-01-01", // ISO date string
    return_citations: true,
  }
});

const result = await llm.invoke("What are the latest AI developments?");
Copy

// Method 3: Override search parameters per request
const result = await llm.invoke("Find recent news about SpaceX", {
  searchParameters: {
    mode: "on",
    max_search_results: 10,
    sources: [
      { type: "web", allowed_websites: ["spacex.com", "nasa.gov"] },
    ],
  }
});
Copy