Developed a Retrieval-Augmented Generation (RAG) based Document Question Answering system that enables users to upload PDF documents and interact with them through natural language queries. The application processes documents, generates semantic embeddings, stores them in a vector database, retrieves the most relevant context using similarity search, and leverages Large Language Models (LLMs) to generate accurate, context-aware responses. Built with Streamlit for an interactive user experience, the system reduces hallucinations by grounding answers in the uploaded document content, providing reliable and efficient document intelligence for knowledge retrieval and exploration.