Lepton Search is an open-source conversational AI search engine built using less than 500 lines of Python code, leveraging Lepton AI's cloud models and Bing Search API.
What is Lepton Search?
Lepton Search is an open-source conversational AI search engine developed by Lepton AI, founded by former Alibaba VP and AI scientist Yangqing Jia. It leverages large language models and Bing Search API to provide a natural language search experience, all with less than 500 lines of Python code.
Features of Lepton Search
- Open Source: The code is open source, allowing developers to freely use, modify, and distribute it.
- Conversational Search: Users can interact with the search engine using natural language for a more intuitive experience.
- Built-in Large Language Model (LLM) Support: Integrates LLMs to understand and generate natural language, improving search accuracy.
- Search Engine Integration: Uses Bing Search API to quickly retrieve and provide relevant information.
- Customizable UI: Developers can tailor the user interface to fit specific needs.
- Search Result Sharing and Caching: Supports sharing and caching of search results for improved efficiency.
- Cloud-Native Platform: Runs on Lepton AI's cloud platform, offering scalability, flexibility, and security.
How to Use Lepton Search
Regular users can access Lepton Search via its online web version. Developers can deploy it locally by following these steps:
- Clone the project:
git clone https://github.com/leptonai/search_with_lepton.git
- Install dependencies:
pip install -U leptonai && lep login
- Set Bing API key:
export BING_SEARCH_V7_SUBSCRIPTION_KEY=YOUR_BING_SUBSCRIPTION_KEY
- Build the frontend:
cd web && npm install && npm run build
- Run the backend server:
BACKEND=BING python search_with_lepton.py
Official Links