RAG-powered Document Q&A app using Python, Streamlit, LangChain, FAISS, and HuggingFace embeddings. Supports multi-PDF ingestion, vector search, and high-speed Llama-3/Groq & OpenAI inference for ...
• Built a complete pipeline to read PDFs, clean content, and split documents into meaningful chunks for easier searching. • Added support for images using OCR (Tesseract) to read text in images and ...