nandani-1411/DocuChat-AI

Multi-File RAG Chatbot is an open-source Retrieval-Augmented Generation system for contextual question-answering over multiple document types (PDF, DOCX, PPTX, XLSX, CSV, TXT). It extracts text, chunks documents, generates embeddings, stores vectors in a vector DB (ChromaDB/FAISS), and uses LangChain and Mistral via a FastAPI backend with a React frontend to produce context-aware answers. Who uses it: developers, analysts, and knowledge workers who need semantic search, summarization, cross-file comparison, and note generation. Key features: multi-file upload (drag-and-drop), semantic retrieval, chat (/chat) and upload (/upload) endpoints, local dev setup (Python venv, uvicorn), configurable vector DB, and pipeline for embedding + retrieval. Planned improvements include streaming, auth, multi-user support, and source citations.

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.