Skip to main content

SerpAPI

SerpAPI 允许您将搜索引擎结果集成到您的 LLM 应用中

本指南简要介绍了如何开始使用 SerpAPI 工具。如需了解 SerpAPI 所有功能和配置的详细文档，请前往 API 参考文档。

概览​

集成详情​

类包PY 支持包最新版本
SerpAPI@langchain/community✅NPM - 版本

安装设置​

该集成位于 @langchain/community 包中，您可以按照以下方式安装：

:::提示 请参阅安装集成包的一般说明部分。 :::

yarn add @langchain/community @langchain/core

凭据​

在此处 设置 API 密钥，并将其设置为名为 SERPAPI_API_KEY 的环境变量。

process.env.SERPAPI_API_KEY = "YOUR_API_KEY";

此外，设置 LangSmith 以获得最佳观测能力也很有帮助（但不是必须的）：

process.env.LANGSMITH_TRACING = "true";
process.env.LANGSMITH_API_KEY = "your-api-key";

实例化​

你可以通过以下方式导入并实例化 SerpAPI 工具：

import { SerpAPI } from "@langchain/community/tools/serpapi";

const tool = new SerpAPI();

调用​

使用参数直接调用​

你可以像这样直接调用工具：

await tool.invoke({
  input: "what is the current weather in SF?",
});
{"type":"weather_result","temperature":"63","unit":"Fahrenheit","precipitation":"3%","humidity":"91%","wind":"5 mph","location":"San Francisco, CA","date":"Sunday 9:00 AM","weather":"Mostly cloudy"}

使用 ToolCall 调用​

我们还可以通过模型生成的 ToolCall 来调用工具，在这种情况下将返回一个 ToolMessage：

// This is usually generated by a model, but we'll create a tool call directly for demo purposes.
const modelGeneratedToolCall = {
  args: {
    input: "what is the current weather in SF?",
  },
  id: "1",
  name: tool.name,
  type: "tool_call",
};

await tool.invoke(modelGeneratedToolCall);
ToolMessage {
  "content": "{\"type\":\"weather_result\",\"temperature\":\"63\",\"unit\":\"Fahrenheit\",\"precipitation\":\"3%\",\"humidity\":\"91%\",\"wind\":\"5 mph\",\"location\":\"San Francisco, CA\",\"date\":\"Sunday 9:00 AM\",\"weather\":\"Mostly cloudy\"}",
  "name": "search",
  "additional_kwargs": {},
  "response_metadata": {},
  "tool_call_id": "1"
}

链式调用​

我们可以通过首先将其绑定到一个工具调用模型，然后调用它，以链式方式使用我们的工具：

Pick your chat model:

Install dependencies

tip

See this section for general instructions on installing integration packages.

yarn add @langchain/groq

Add environment variables

GROQ_API_KEY=your-api-key

Instantiate the model

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

const llm = new ChatGroq({
  model: "llama-3.3-70b-versatile",
  temperature: 0
});
import { HumanMessage } from "@langchain/core/messages";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { RunnableLambda } from "@langchain/core/runnables";

const prompt = ChatPromptTemplate.fromMessages([
  ["system", "You are a helpful assistant."],
  ["placeholder", "{messages}"],
]);

const llmWithTools = llm.bindTools([tool]);

const chain = prompt.pipe(llmWithTools);

const toolChain = RunnableLambda.from(async (userInput: string, config) => {
  const humanMessage = new HumanMessage(userInput);
  const aiMsg = await chain.invoke(
    {
      messages: [new HumanMessage(userInput)],
    },
    config
  );
  const toolMsgs = await tool.batch(aiMsg.tool_calls, config);
  return chain.invoke(
    {
      messages: [humanMessage, aiMsg, ...toolMsgs],
    },
    config
  );
});

const toolChainResult = await toolChain.invoke(
  "what is the current weather in sf?"
);
const { tool_calls, content } = toolChainResult;

console.log(
  "AIMessage",
  JSON.stringify(
    {
      tool_calls,
      content,
    },
    null,
    2
  )
);
AIMessage {
  "tool_calls": [],
  "content": "The current weather in San Francisco is mostly cloudy, with a temperature of 64°F. The humidity is at 90%, there is a 3% chance of precipitation, and the wind is blowing at 5 mph."
}

代理​

关于如何在代理中使用 LangChain 工具的指南，请参阅 LangGraph.js 文档。

API 参考文档​

有关所有 SerpAPI 功能和配置的详细文档，请访问 API 参考页面: https://api.js.langchain.com/classes/\_langchain_community.tools_serpapi.SerpAPI.html

Was this page helpful?


You can also leave detailed feedback on GitHub.