🦜

LangChain Integration

Popular
AI & Machine Learning

Native SERPII loader for building search-powered AI agents and chains

Official Documentation

Features

Document Loader

Load search results as documents for RAG applications.

Agent Tools

Use SERPII as a tool in LangChain agents for autonomous search.

Memory Integration

Store and recall search results in conversation memory.

Chain Composition

Combine search with other LangChain components seamlessly.

Setup

Step 1

Install LangChain

Install LangChain and required dependencies.

pip install langchain langchain-openai requests
Step 2

Create SERPII Tool

Define a custom tool for LangChain agents.

from langchain.tools import Tool
from langchain.agents import initialize_agent, AgentType
from langchain_openai import ChatOpenAI
import requests
import os

def search_serpii(query: str) -> str:
    """Search the web using SERPII API"""
    response = requests.get(
        "https://api.serpii.com/v1/google/light/search",
        params={"q": query},
        headers={"x-api-key": os.getenv("SERPII_API_KEY")}
    )
    results = response.json()["organic_results"][:5]
    return "\n\n".join([
        f"{r['position']}. {r['title']}\n{r['link']}\n{r.get('snippet', '')}"
        for r in results
    ])

serpii_tool = Tool(
    name="Search",
    func=search_serpii,
    description="Search the web for current information. Input should be a search query."
)

Code Examples

from langchain.tools import Tool
from langchain.agents import initialize_agent, AgentType
from langchain_openai import ChatOpenAI
import requests
import os

# Define SERPII tool
def search_serpii(query: str) -> str:
    response = requests.get(
        "https://api.serpii.com/v1/google/light/search",
        params={"q": query},
        headers={"x-api-key": os.getenv("SERPII_API_KEY")}
    )
    results = response.json()["organic_results"][:5]
    return "\n\n".join([
        f"{r['position']}. {r['title']}\n{r['link']}\n{r.get('snippet', '')}"
        for r in results
    ])

serpii_tool = Tool(
    name="Search",
    func=search_serpii,
    description="Search the web for current information."
)

# Create agent
llm = ChatOpenAI(temperature=0, model="gpt-4")
agent = initialize_agent(
    [serpii_tool],
    llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True
)

# Use agent
result = agent.run("What are the latest developments in quantum computing?")
print(result)

Common Use Cases

  • →Building AI agents with web search capabilities
  • →Creating RAG applications with real-time data
  • →Autonomous research assistants
  • →Question answering with current information
  • →Fact-checking and verification agents
  • →Competitive intelligence gathering