A simplest conversation-based search demo based on Lepton AI's work.
- OpenAI
- Azure
- ZhipuAI
- Setup Python Dependencies
pip install fastapi loguru toml zhipuai openai- Configure your LLM providers' API keys in
secrets.toml - Run the backend
uvicorn backend:app- Build the frontend
cd web && npm install && npm run build- Run the frontend
export SERVER_URL=http:https://localhost:8000 && npm run dev
- Built-in support for LLM
- Built-in support for search engine
- Customizable pretty UI interface
- Shareable, cached search results
Note
Visit here to get your Bing subscription key.
Note
We recommend using the built-in llm and kv functions with Lepton. Running the following commands to set up them automatically.
pip install -U leptonai && lep login- Set Bing subscription key
export BING_SEARCH_V7_SUBSCRIPTION_KEY=YOUR_BING_SUBSCRIPTION_KEY- Build web
cd web && npm install && npm run build- Run server
BACKEND=BING python search_with_lepton.pyYou can deploy this to Lepton AI with one click:
You can also deploy your own version via
lep photon run -n search-with-lepton-modified -m search_with_lepton.py --env BACKEND=BING --env BING_SEARCH_V7_SUBSCRIPTION_KEY=YOUR_BING_SUBSCRIPTION_KEYLearn more about lep photon here.