What is LangChain?
The most popular framework for building LLM-powered applications. Provides chains, agents, and tools for composing AI workflows.
Searching X (Twitter) with LangChain
This integration lets your LangChain agent search X (Twitter) in real time via the Scavio API. The agent gets back structured JSON with post snippets, author handles, timestamps, engagement signals — ready for reasoning and decision-making.
Setup
Bash
pip install langchain langchain-scavio langchain-openaiCode Example
Here is a complete LangChain agent that searches X (Twitter) using Scavio:
Python
from langchain_scavio import ScavioSearch
from langchain_openai import ChatOpenAI
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate
# Initialize the Scavio search tool
tool = ScavioSearch(api_key="your_scavio_api_key")
# Create an agent with the tool
llm = ChatOpenAI(model="gpt-4o")
prompt = ChatPromptTemplate.from_messages([
("system", "You are a helpful research assistant."),
("human", "{input}"),
("placeholder", "{agent_scratchpad}"),
])
agent = create_tool_calling_agent(llm, [tool], prompt)
executor = AgentExecutor(agent=agent, tools=[tool])
# Search specifically on X (Twitter)
result = agent.invoke({"input": "Search X (Twitter) for site:x.com AI agents 2026"})
print(result["output"])Full Working Example
A production-ready example with error handling:
Python
"""
Search X (Twitter) with LangChain + Scavio.
Uses Scavio as a LangChain tool for real-time web data.
"""
from langchain_scavio import ScavioSearch
from langchain_openai import ChatOpenAI
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate
tool = ScavioSearch(api_key="your_scavio_api_key")
llm = ChatOpenAI(model="gpt-4o")
prompt = ChatPromptTemplate.from_messages([
("system", "You are a helpful assistant with access to real-time search."),
("human", "{input}"),
("placeholder", "{agent_scratchpad}"),
])
agent = create_tool_calling_agent(llm, [tool], prompt)
executor = AgentExecutor(agent=agent, tools=[tool], verbose=True)
# Search specifically on X (Twitter)
result = agent.invoke({"input": "Search X (Twitter) for site:x.com AI agents 2026"})
print(result["output"])Pricing
Scavio offers a free tier with 500 credits/month (1 credit per search). No credit card required. This is enough to build and test your LangChain integration. Paid plans start at $30/month for higher volumes.