> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# ChatXAI 集成

> 使用 LangChain JavaScript 集成 ChatXAI chat model。

[xAI](https://x.ai/) is an artificial intelligence company that develops Large Language Models (LLMs). Their flagship model, Grok, is trained on real-time X (formerly Twitter) data and aims to provide witty, personality-rich responses while maintaining high capability on technical tasks.

本指南将帮助你开始使用 `ChatXAI` [chat models](/oss/javascript/langchain/models)。有关所有 `ChatXAI` 功能和配置的详细文档，请前往 [API 参考](https://reference.langchain.com/javascript/langchain-xai/ChatXAI)。

## 概述

### 集成详情

| Class                                                                         | Package                                                          | Serializable | PY support |                                            Downloads                                           |                                           Version                                           |
| :---------------------------------------------------------------------------- | :--------------------------------------------------------------- | :----------: | :--------: | :--------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------: |
| [`ChatXAI`](https://reference.langchain.com/javascript/langchain-xai/ChatXAI) | [`@langchain/xai`](https://www.npmjs.com/package/@langchain/xai) |       ✅      |      ❌     | ![NPM - Downloads](https://img.shields.io/npm/dm/@langchain/xai?style=flat-square\&label=%20&) | ![NPM - Version](https://img.shields.io/npm/v/@langchain/xai?style=flat-square\&label=%20&) |

### 模型功能

请参阅下表标题中的链接，了解如何使用特定功能。

| [Tool calling](/oss/javascript/langchain/tools) | [Structured output](/oss/javascript/langchain/structured-output) | [Image input](/oss/javascript/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/javascript/langchain/streaming/) | [Token usage](/oss/javascript/langchain/models#token-usage) | [Logprobs](/oss/javascript/langchain/models#log-probabilities) |
| :---------------------------------------------: | :--------------------------------------------------------------: | :----------------------------------------------------------: | :---------: | :---------: | :-----------------------------------------------------------: | :---------------------------------------------------------: | :------------------------------------------------------------: |
|                        ✅                        |                                 ✅                                |                               ❌                              |      ❌      |      ❌      |                               ✅                               |                              ✅                              |                                ✅                               |

## 设置

要访问 `ChatXAI` models，你需要create an xAI account, [get an API key](https://console.x.ai/), and install the `@langchain/xai` integration package.

### 凭证

前往 [the xAI website](https://x.ai) 注册 xAI 并生成 API 密钥。完成后设置 `XAI_API_KEY` 环境变量：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export XAI_API_KEY="your-api-key"
```

如果你想要自动追踪模型调用，还可以设置你的 [LangSmith](/langsmith/home) API 密钥，取消注释以下内容：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"
```

### 安装

LangChain 的 `ChatXAI` 集成位于 `@langchain/xai` 包中：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @langchain/xai @langchain/core
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @langchain/xai @langchain/core
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @langchain/xai @langchain/core
  ```
</CodeGroup>

## 实例化

现在我们可以实例化模型对象并生成聊天补全：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { ChatXAI } from "@langchain/xai"

const llm = new ChatXAI({
    model: "grok-beta", // default
    temperature: 0,
    maxTokens: undefined,
    maxRetries: 2,
    // 其他参数...
})
```

## 调用

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const aiMsg = await llm.invoke([
    [
      "system",
      "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ],
    ["human", "I love programming."],
])
console.log(aiMsg)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
AIMessage {
  "id": "71d7e3d8-30dd-472c-8038-b6b283dcee63",
  "content": "J'adore programmer.",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "promptTokens": 30,
      "completionTokens": 6,
      "totalTokens": 36
    },
    "finish_reason": "stop",
    "usage": {
      "prompt_tokens": 30,
      "completion_tokens": 6,
      "total_tokens": 36
    },
    "system_fingerprint": "fp_3e3898d4ce"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "output_tokens": 6,
    "input_tokens": 30,
    "total_tokens": 36,
    "input_token_details": {},
    "output_token_details": {}
  }
}
```

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
console.log(aiMsg.content)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
J'adore programmer.
```

***

## API 参考

有关所有 `ChatXAI` 功能和配置的详细文档，请前往 [API 参考](https://reference.langchain.com/javascript/langchain-xai/ChatXAI)。

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档连接到](/use-these-docs) Claude、VSCode 等工具，通过 MCP 获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/javascript/integrations/chat/xai.mdx) 或 [提交 issue](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>