A chatbot that uses RAG to answer questions about sports, weightlifting, testosterone... all with the goal of getting you swole. 💪🏻
- RAG-powered responses using OpenAI models
- Smart document processing with hierarchical chunking
- Semantic search with Jina AI embeddings and reranking
- Source tracking and citation
- Intelligent content validation
- Intelligent scraping of documents from the web
- Vector storage with Chroma
- Clone the repository
- Install Poetry if you haven't already
- Install dependencies with
poetry install
- Create a
.env
file based on the.env.example
file - Scrape documents with
make scrape
- Chat with the bot with
make chat
- Transition into a web app using FastHTML.
- Implement semantic chunking based on section headers, smart overlap that preserves complete sentences and dynamic chunk sized based on content type
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
Please use descriptive commit messages and add a PR description describing the why behind the changes you're making.
This project is licensed under the MIT License - see the LICENSE file for details.