Chat with a Web page using Llama 3.2

Introducing a cutting-edge chat application powered by Generative AI. This innovative solution leverages the advanced capabilities of llama3.2, running locally, coupled with Retrieval Augmented Generation (RAG) technique. Built on a robust foundation of Streamlit and FastAPI, the application intelligently responds to user queries by dynamically referencing information associated with the provided Universal Resource Identifier (URI).