This RAG (Retrieval-Augmented Generation) chatbot allows you to upload multiple PDF documents and then chat with them as if you had an expert who had read every page.
The system ingests PDFs, chunks the content, embeds it into a vector store using FAISS, and retrieves the most relevant chunks at query time before passing them to an LLM for response generation. This ensures the model answers from the actual document content rather than hallucinating.
Built with LangChain and OpenAI, it supports follow-up questions with conversation memory.