PDF RAG Chatbot: Intelligent Document

PDF RAG Chatbot: Intelligent Document Q&A System

Built a production-ready Retrieval-Augmented Generation (RAG) system that allows users to upload PDF documents and ask complex questions, receiving accurate, context-aware answers instantly.

Engineering Challenges Solved:

Context Retrieval: Implemented a hybrid search system combining BM25 (keyword) and Vector Embeddings (semantic) using ChromaDB to ensure highly relevant document chunks are retrieved before passing them to the LLM.

LLM Integration: Connected the retrieval pipeline to Groq's Llama 3.1 API, achieving sub-second inference times while maintaining high answer relevancy.

Document Processing: Engineered a robust pipeline using pdfplumber to extract text from multi-page PDFs, with chunking and embedding strategies optimized for retrieval accuracy.

Tech Stack: Python, Flask, ChromaDB, Groq API (Llama 3.1), Sentence-Transformers, pdfplumber.