This is a Retrieval-Augmented Generation (RAG) application using GPT4All models and Gradio for the front end. The application is designed to allow non-technical users in a Public Health department to ask questions from PDF and text documents.
- Upload PDFs: Users can upload PDF documents.
- Query Documents: Users can ask questions, and the system retrieves relevant information from the uploaded documents.
- User-Friendly Interface: Gradio provides an easy-to-use interface for interacting with the application.
- Frontend: Gradio
- Backend: FastAPI
- LLM Framework: LangChain
- Language Model: GPT4All
- Document Processing: PyMuPDF (via LangChain)
- Embedding and Retrieval: FAISS
- Dependency Management: Poetry