I've been working on a Python package to enable Agentic RAG with Vectara (disclosure: I work there). It uses LlamaIndex behind the scenes, and provides a quick and easy way to build Agentic RAG assistants.<p>I hope you find it useful, and please share any questions or feedback.
Oh, and there's a demo of an AI assistant for hacker news here: <a href="https://huggingface.co/spaces/vectara/hacker-news-chat" rel="nofollow">https://huggingface.co/spaces/vectara/hacker-news-chat</a>