Skip to main content

ChatGroq

Groq 是一家公司，提供由 LPU™ AI 推理技术驱动的快速 AI 推理，该技术提供快速、经济高效且节能的 AI。

这将帮助你开始使用 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。

概览​

集成详情​

类别包本地可序列化PY 支持包下载量包最新版本
ChatGroq@langchain/groq❌❌✅NPM - 下载量NPM - 版本

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的指南。

工具调用结构化输出JSON 模式图像输入音频输入视频输入逐 token 流式传输token 使用情况logprobs
✅✅✅❌❌❌✅✅✅

准备工作​

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

凭据​

为了使用 Groq API，你需要一个 API 密钥。你可以在这里注册一个 Groq 账户并创建一个 API 密钥 此处。 然后，你可以在终端中将 API 密钥设置为环境变量：

export GROQ_API_KEY="your-api-key"

如果你想获得模型调用的自动跟踪，也可以通过取消下面的注释来设置你的 LangSmith API 密钥：

# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

安装​

LangChain ChatGroq 集成位于 @langchain/groq 包中：

:::提示 请参阅安装集成包的一般说明部分。 :::

yarn 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: "llama-3.3-70b-versatile",
  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}'
}

链式调用​

我们可以像这样将模型与提示模板链式调用：

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 参考文档​

有关 ChatGroq 所有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

Was this page helpful?


You can also leave detailed feedback on GitHub.