A LangChain-compatible agent and weather tool designed for seamless integration with CometChat and other chat platforms. This package demonstrates how to build and expose agentic workflows using LangGraph, with real-time streaming and tool execution.
- Weather tool using OpenWeatherMap
- LangGraph agent workflow
- FastAPI server example for NDJSON streaming
- Designed for easy integration with CometChat’s Agentic Platform
git clone https://github.com/cometchat/cometchat-langgraph-agent
cd cometchat-langgraph-agent/
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
pip install -r requirements.txtCopy .env.example to .env and fill in your API keys:
cp .env.example .envEdit .env and set:
OPENAI_API_KEYOPENWEATHER_API_KEY- (Optional)
MODEL,PORT,HOST
from cometchat_langgraph_agent.agent import graph
from langchain_core.messages import HumanMessage
result = graph.invoke({
"messages": [HumanMessage(content="What's the weather in London?")]
})
print(result["messages"][-1].content)Or run the FastAPI server for CometChat integration:
python examples/server.pycometchat_langgraph_agent/
__init__.py
agent.py
weather_tool.py
examples/
server.py
tests/
unit_tests/
integration_tests/
.env.example
pyproject.toml
README.md
requirements.txt
pytestThis agent is designed to work out-of-the-box with CometChat’s Agentic Platform. The included FastAPI server streams NDJSON responses compatible with CometChat’s real-time chat interface. See examples/server.py for integration details.
- Create a CometChat account: https://app.cometchat.com/signup
- Create a new app in the CometChat dashboard.
- Navigate to the Agents section and create a new agent (choose "Custom Agent").
- Set the deployment URL to your running FastAPI server endpoint (e.g.,
https://your-server.com/kickoff). - Test the integration using CometChat’s dashboard or client SDKs.