Context-Aware Document Q&A
Retrieval-augmented generation over PDFs and web content, with a Streamlit interface.
A retrieval-augmented generation system for querying documents in natural language.
Pipeline. Documents (PDFs or scraped web content) are chunked and embedded with sentence-transformers, indexed in a FAISS vector store, and retrieved at query time to condition a Gemini call. A Streamlit front end handles upload and chat.