What is LangChain?
The most popular framework for building LLM-powered applications. Provides chains, agents, and tools for composing AI workflows.
Searching Google Scholar with LangChain
This integration lets your LangChain agent search Google Scholar in real time via the Scavio API. The agent gets back structured JSON with paper titles, paper URLs, SERP snippets -- ready for reasoning and decision-making.
Setup
Bash
pip install langchain langchain-scavio langchain-openaiCode Example
Here is a complete LangChain agent that searches Google Scholar 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
# scavio_api_key is the keyword the tool takes; SCAVIO_API_KEY also works.
tool = ScavioSearch(scavio_api_key="sk_live_your_key")
llm = ChatOpenAI(model="gpt-5.5")
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])
result = executor.invoke({"input": "Search Google Scholar for retrieval augmented generation 2024"})
print(result["output"])Full Working Example
A production-ready example with error handling:
Python
"""
Query Google Scholar with LangChain + Scavio.
ScavioSearch calls POST /api/v2/google under the hood.
"""
import os
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
os.environ.setdefault("SCAVIO_API_KEY", "sk_live_your_key")
tool = ScavioSearch()
llm = ChatOpenAI(model="gpt-5.5")
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)
result = executor.invoke({"input": "Search Google Scholar for retrieval augmented generation 2024"})
print(result["output"])Pricing
Scavio offers a free tier with 50 credits on signup (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.