PerplexitySearchResults 集成

使用 LangChain JavaScript 集成 PerplexitySearchResults tool。

The Perplexity Search API returns real-time, grounded web search results. PerplexitySearchResults is a LangChain tool wrapper that lets agents query the API and receive a JSON array of search results.

概述

集成详情

Class	Package	PY support	Version
PerplexitySearchResults	@langchain/perplexity	✅

设置

The integration lives in the @langchain/perplexity package:

npm

npm install @langchain/perplexity @langchain/core

凭证

Set up a Perplexity API key and set it as an environment variable named PERPLEXITY_API_KEY:

process.env.PERPLEXITY_API_KEY = "your-api-key";

It’s also helpful (but not needed) to set up LangSmith for best-in-class observability:

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

实例化

import { PerplexitySearchResults } from "@langchain/perplexity";

const tool = new PerplexitySearchResults({
  maxResults: 5,
  // searchDomainFilter: ["wikipedia.org"],
  // searchRecencyFilter: "week",
});

Constructor options include maxResults, country, searchDomainFilter, searchRecencyFilter, searchAfterDate, and searchBeforeDate. See the Perplexity Search API parameters for details.

调用

Direct call

const result = await tool.invoke("Who won the most recent FIFA World Cup?");
console.log(result);

The tool returns a JSON-encoded array of search results, each with title, url, snippet, date, and last_updated.

Use with an agent

import { ChatAnthropic } from "@langchain/anthropic";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const llm = new ChatAnthropic({ model: "claude-3-5-haiku-latest" });

const agent = createReactAgent({
  llm,
  tools: [tool],
});

const response = await agent.invoke({
  messages: [
    { role: "user", content: "What's the latest news on the Mars Sample Return mission?" },
  ],
});

API 参考

有关所有 PerplexitySearchResults 功能和配置的详细文档，请前往 API 参考。

---

将这些文档连接到 Claude、VSCode 等工具，通过 MCP 获取实时答案。

在 GitHub 上编辑此页面 或 提交 issue。