We tested the RAG using two language models: Meta Llama-3.1 Instruct 8B and Deepseek-Distill-QWen-14B You can run these two models by running generate_llama3.py or generate_deepseek.py ...

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 ...