What is LangGraph?
A framework for building stateful, multi-step AI agent workflows as graphs. Built on top of LangChain for complex agentic applications.
Searching Glassdoor with LangGraph
This integration lets your LangGraph agent search Glassdoor in real time via the Scavio API. The agent gets back structured JSON with employer_id and profile, overall and category ratings, reviews (max 3 per response), salary bands by title -- ready for reasoning and decision-making.
Setup
pip install langgraph langchain-scavio langchain-openaiCode Example
Here is a complete LangGraph agent that searches Glassdoor using Scavio:
from langgraph.prebuilt import create_react_agent
from langchain_scavio import ScavioSearch
from langchain_openai import ChatOpenAI
tool = ScavioSearch(scavio_api_key="sk_live_your_key")
llm = ChatOpenAI(model="gpt-5.5")
agent = create_react_agent(llm, [tool])
result = agent.invoke({
"messages": [{"role": "user", "content": "Search Glassdoor for Stripe"}]
})
print(result["messages"][-1].content)Full Working Example
A production-ready example with error handling:
"""
LangGraph agent that queries Glassdoor via Scavio.
ScavioSearch calls POST /api/v2/google under the hood.
"""
import os
from langgraph.prebuilt import create_react_agent
from langchain_scavio import ScavioSearch
from langchain_openai import ChatOpenAI
os.environ.setdefault("SCAVIO_API_KEY", "sk_live_your_key")
tool = ScavioSearch()
llm = ChatOpenAI(model="gpt-5.5")
agent = create_react_agent(llm, [tool])
result = agent.invoke({
"messages": [{"role": "user", "content": "Search Glassdoor for Stripe"}]
})
for message in result["messages"]:
if hasattr(message, "content") and message.content:
print(message.type, str(message.content)[:200])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 LangGraph integration. Paid plans start from $24/mo billed yearly for higher volumes.