> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.
# ChatGroq 集成
> 使用 LangChain JavaScript 集成 ChatGroq 聊天模型。
[Groq](https://groq.com/) 是一家提供快速 AI 推理服务的公司，其基于 LPU™ AI 推理技术，能够提供快速、经济且节能的 AI 解决方案。
本文将帮助您开始使用 Groq 的[聊天模型](/oss/javascript/langchain/models)。有关 `ChatGroq` 所有功能和配置的详细文档，请参阅 [API 参考](https://reference.langchain.com/javascript/langchain-groq/ChatGroq)。
## 概述
### 集成详情
| 类 | 包 | 可序列化 | [Python 支持](https://python.langchain.com/docs/integrations/chat/groq) | 下载量 | 版本 |
| :------------------------------------------------------------------------------- | :----------------------------------------------------------------- | :--: | :-------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------: |
| [`ChatGroq`](https://reference.langchain.com/javascript/langchain-groq/ChatGroq) | [`@langchain/groq`](https://www.npmjs.com/package/@langchain/groq) | ❌ | ✅ |  |  |
### 模型功能
下表标题中的链接提供了如何使用特定功能的指南。
| [工具调用](/oss/javascript/langchain/tools) | [结构化输出](/oss/javascript/langchain/structured-output) | [图像输入](/oss/javascript/langchain/messages#multimodal) | 音频输入 | 视频输入 | [令牌级流式传输](/oss/javascript/langchain/streaming/) | [令牌使用量](/oss/javascript/langchain/models#token-usage) | [对数概率](/oss/javascript/langchain/models#log-probabilities) |
| :-------------------------------------: | :--------------------------------------------------: | :---------------------------------------------------: | :--: | :--: | :---------------------------------------------: | :---------------------------------------------------: | :--------------------------------------------------------: |
| ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ |
## 设置
要访问 ChatGroq 模型，您需要创建一个 Groq 账户，获取 API 密钥，并安装 `@langchain/groq` 集成包。
### 凭证
要使用 Groq API，您需要一个 API 密钥。[注册 Groq 账户并创建 API 密钥](https://wow.groq.com/)。
然后，您可以在终端中将 API 密钥设置为环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export GROQ_API_KEY="your-api-key"
```
如果您希望自动追踪模型调用，还可以通过取消注释以下行来设置您的 [LangSmith](/langsmith/home) API 密钥：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"
```
### 安装
LangChain ChatGroq 集成位于 `@langchain/groq` 包中：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm install @langchain/groq @langchain/core
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/groq @langchain/core
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/groq @langchain/core
```
## 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 { ChatGroq } from "@langchain/groq"
const llm = new ChatGroq({
model: "llama-3.3-70b-versatile",
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([
{
role: "system",
content: "你是一个将英语翻译成法语的助手。请翻译用户的句子。",
},
{ role: "user", content: "I love programming." },
])
aiMsg
```
```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
AIMessage {
"content": "I enjoy programming. (The French translation is: \"J'aime programmer.\")\n\nNote: I chose to translate \"I love programming\" as \"J'aime programmer\" instead of \"Je suis amoureux de programmer\" because the latter has a romantic connotation that is not present in the original English sentence.",
"additional_kwargs": {},
"response_metadata": {
"tokenUsage": {
"completionTokens": 73,
"promptTokens": 31,
"totalTokens": 104
},
"finish_reason": "stop"
},
"tool_calls": [],
"invalid_tool_calls": []
}
```
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
console.log(aiMsg.content)
```
```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
I enjoy programming. (The French translation is: "J'aime programmer.")
Note: I chose to translate "I love programming" as "J'aime programmer" instead of "Je suis amoureux de programmer" because the latter has a romantic connotation that is not present in the original English sentence.
```
## JSON 调用
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const messages = [
{
role: "system",
content: "你是一个数学导师，负责处理数学练习并以 JSON 格式输出，格式为 { result: number }。",
},
{ role: "user", content: "2 + 2 * 2" },
];
const aiInvokeMsg = await llm.invoke(messages, { response_format: { type: "json_object" } });
// 如果不想在每次调用时都传递 response_format，可以将其绑定到实例
const llmWithResponseFormat = llm.bind({ response_format: { type: "json_object" } });
const aiBindMsg = await llmWithResponseFormat.invoke(messages);
// 它们是相同的
console.log({ aiInvokeMsgContent: aiInvokeMsg.content, aiBindMsg: aiBindMsg.content });
```
```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{
aiInvokeMsgContent: '{\n"result": 6\n}',
aiBindMsg: '{\n"result": 6\n}'
}
```
***
## API 参考
有关 `ChatGroq` 所有功能和配置的详细文档，请参阅 [API 参考](https://reference.langchain.com/javascript/langchain-groq/ChatGroq)。
***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\javascript\integrations\chat\groq.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.