A Retrieval-Augmented Generation (RAG) chatbot built with FastAPI (backend API) and Streamlit (frontend UI).
This chatbot allows you to upload documents, process them into embeddings, and ask questions to get accurate, context-aware answers.
- 📂 Upload PDF/DOCX/Text documents
- 🔎 Vector-based document retrieval using embeddings
- 💬 Chat with your documents in real time
- ⚡ FastAPI backend for serving the RAG pipeline
- 🎨 Streamlit frontend for interactive UI
- Python 3.10+
- FastAPI → Backend REST API
- Streamlit → Frontend UI
- LangChain / Chroma → Vector DB for retrieval
- OpenAI → LLM for response generation
- Start FastAPI server
- Open Streamlit app
- Upload a document (PDF/DOCX/TXT)
- Ask questions about the uploaded doc
- Get contextual answers from your LLM 🎉