This guide shows how to use SerpAPI with LangChain to load web search results.

​
Overview

SerpAPI is a real-time API that provides access to search results from various search engines. It is commonly used for tasks like competitor analysis and rank tracking. It empowers businesses to scrape, extract, and make sense of data from all search engines’ result pages. This guide shows how to load web search results using the SerpAPILoader in LangChain. The SerpAPILoader simplifies the process of loading and processing web search results from SerpAPI.

​
Setup

You’ll need to sign up and retrieve your SerpAPI API key.

​
Usage

Here’s an example of how to use the SerpAPILoader:
See this section for general instructions on installing LangChain packages.
npm
npm install @langchain/community @langchain/core @langchain/openai

import { ChatOpenAI, OpenAIEmbeddings } from "@langchain/openai";
import { MemoryVectorStore } from "langchain/vectorstores/memory";
import { SerpAPILoader } from "@langchain/community/document_loaders/web/serpapi";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
import { createRetrievalChain } from "langchain/chains/retrieval";

// Initialize the necessary components
const llm = new ChatOpenAI({
  model: "gpt-4o-mini",
});
const embeddings = new OpenAIEmbeddings();
const apiKey = "Your SerpAPI API key";

// Define your question and query
const question = "Your question here";
const query = "Your query here";

// Use SerpAPILoader to load web search results
const loader = new SerpAPILoader({ q: query, apiKey });
const docs = await loader.load();

// Use MemoryVectorStore to store the loaded documents in memory
const vectorStore = await MemoryVectorStore.fromDocuments(docs, embeddings);

const questionAnsweringPrompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "Answer the user's questions based on the below context:\n\n{context}",
  ],
  ["human", "{input}"],
]);

const combineDocsChain = await createStuffDocumentsChain({
  llm,
  prompt: questionAnsweringPrompt,
});

const chain = await createRetrievalChain({
  retriever: vectorStore.asRetriever(),
  combineDocsChain,
});

const res = await chain.invoke({
  input: question,
});

console.log(res.answer);
In this example, the SerpAPILoader is used to load web search results, which are then stored in memory using MemoryVectorStore. A retrieval chain is then used to retrieve the most relevant documents from the memory and answer the question based on these documents. This demonstrates how the SerpAPILoader can streamline the process of loading and processing web search results.