This is a significantly different RAG we used to think of: https://chat.langchain.com/. Take a look at the sample questions and observe how agents from LangChain and LangGraph utilize them to construct responses. The process is also transparently visible for the user, from the initial query to the decomposition, document retrieval, context selection, and the final answer. It is an exceptionally effective method of presenting the flow.
The entire project is open-sourced, allowing anyone to experiment with it at home or incorporate it into their own projects. You can access it at the following link: https://github.com/langchain-ai/chat-langchain