DocuMind AI is a smart document assistant built using Python. It allows users to upload PDF documents and interactively "chat" with them. The application uses Retrieval-Augmented Generation (RAG) to provide accurate, context-aware answers based solely on the content of the uploaded files.
- Interactive Chat Interface: User-friendly chat interface built with Streamlit.
- PDF Analysis: Extracts and chunks text from PDF files efficiently.
- Vector Search: Uses FAISS to store and retrieve relevant document sections.
- AI-Powered: Utilizes OpenAI's GPT models (via LangChain) to generate natural language responses.
- Secure: API keys are input via the sidebar and are not stored persistently.
- Python (Core Language)
- Streamlit (Web Interface)
- LangChain (LLM Framework & Chains)
- OpenAI API (LLM & Embeddings)
- FAISS (Vector Database)
- PyPDF (PDF Parsing)
Follow these steps to run the project locally:
git clone https://github.com/Dheyaalameri/DocuMind-AI.git
cd DocuMind-AI