ChatGroq

Groq 是一家提供快速 AI 推理的公司，其 LPU™ AI 推理技术提供快速、经济高效且节能的 AI。

这将帮助您开始使用 ChatGroq 聊天模型。有关所有 ChatGroq 功能和配置的详细文档，请前往 API 参考。

概述

集成详情

类	包	本地	可序列化	PY 支持	包下载	包最新版本
ChatGroq	@langchain/groq	❌	❌	✅

模型功能

有关如何使用特定功能的指南，请参阅下方表头的链接。

工具调用	结构化输出	JSON 模式	图像输入	音频输入	视频输入	令牌级流式传输	令牌使用	Logprobs
✅	✅	✅	❌	❌	❌	✅	✅	✅

设置

要访问 ChatGroq 模型，您需要创建一个 Groq 帐户，获取 API 密钥并安装 @langchain/groq 集成包。

凭据

要使用 Groq API，您需要一个 API 密钥。您可以注册一个 Groq 帐户并创建一个 API 密钥 此处。然后，您可以在终端中将 API 密钥设置为环境变量

export GROQ_API_KEY="your-api-key"

如果您希望获得模型调用的自动跟踪，您也可以通过取消下面的注释来设置您的 LangSmith API 密钥

# export LANGCHAIN_TRACING_V2="true"
# export LANGCHAIN_API_KEY="your-api-key"

安装

LangChain ChatGroq 集成位于 @langchain/groq 包中

提示

有关安装集成包的一般说明，请参阅 本节。

npm

npm i @langchain/groq @langchain/core

yarn

yarn add @langchain/groq @langchain/core

pnpm

pnpm add @langchain/groq @langchain/core

实例化

现在我们可以实例化我们的模型对象并生成聊天补全

import { ChatGroq } from "@langchain/groq";

const llm = new ChatGroq({
  model: "mixtral-8x7b-32768",
  temperature: 0,
  maxTokens: undefined,
  maxRetries: 2,
  // other params...
});

调用

const aiMsg = await llm.invoke([
  {
    role: "system",
    content:
      "You are a helpful assistant that translates English to French. Translate the user sentence.",
  },
  { role: "user", content: "I love programming." },
]);
aiMsg;

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": []
}

console.log(aiMsg.content);

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

const messages = [
  {
    role: "system",
    content:
      "You are a math tutor that handles math exercises and makes output in json in format { result: number }.",
  },
  { role: "user", content: "2 + 2 * 2" },
];

const aiInvokeMsg = await llm.invoke(messages, {
  response_format: { type: "json_object" },
});

// if you want not to pass response_format in every invoke, you can bind it to the instance
const llmWithResponseFormat = llm.bind({
  response_format: { type: "json_object" },
});
const aiBindMsg = await llmWithResponseFormat.invoke(messages);

// they are the same
console.log({
  aiInvokeMsgContent: aiInvokeMsg.content,
  aiBindMsg: aiBindMsg.content,
});

{
  aiInvokeMsgContent: '{\n"result": 6\n}',
  aiBindMsg: '{\n"result": 6\n}'
}

链式

我们可以 链式 我们的模型，使用如下提示模板

import { ChatPromptTemplate } from "@langchain/core/prompts";

const prompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "You are a helpful assistant that translates {input_language} to {output_language}.",
  ],
  ["human", "{input}"],
]);

const chain = prompt.pipe(llm);
await chain.invoke({
  input_language: "English",
  output_language: "German",
  input: "I love programming.",
});

AIMessage {
  "content": "That's great! I can help you translate English phrases related to programming into German.\n\n\"I love programming\" can be translated to German as \"Ich liebe Programmieren\".\n\nHere are some more programming-related phrases translated into German:\n\n* \"Programming language\" = \"Programmiersprache\"\n* \"Code\" = \"Code\"\n* \"Variable\" = \"Variable\"\n* \"Function\" = \"Funktion\"\n* \"Array\" = \"Array\"\n* \"Object-oriented programming\" = \"Objektorientierte Programmierung\"\n* \"Algorithm\" = \"Algorithmus\"\n* \"Data structure\" = \"Datenstruktur\"\n* \"Debugging\" = \"Debuggen\"\n* \"Compile\" = \"Kompilieren\"\n* \"Link\" = \"Verknüpfen\"\n* \"Run\" = \"Ausführen\"\n* \"Test\" = \"Testen\"\n* \"Deploy\" = \"Bereitstellen\"\n* \"Version control\" = \"Versionskontrolle\"\n* \"Open source\" = \"Open Source\"\n* \"Software development\" = \"Softwareentwicklung\"\n* \"Agile methodology\" = \"Agile Methodik\"\n* \"DevOps\" = \"DevOps\"\n* \"Cloud computing\" = \"Cloud Computing\"\n\nI hope this helps! Let me know if you have any other questions or if you need further translations.",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 327,
      "promptTokens": 25,
      "totalTokens": 352
    },
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "invalid_tool_calls": []
}

API 参考

有关所有 ChatGroq 功能和配置的详细文档，请访问 API 参考：https://api.js.langchain.com/classes/langchain_groq.ChatGroq.html

相关

• 聊天模型 概念指南
• 聊天模型 操作指南