GURPREETKAURJETHRA/RAG-with-LlamaIndex-and-NVIDIA ? reverse-engineered prompt

Build me a simple notebook demo that shows how to do retrieval augmented generation with LlamaIndex and NVIDIA.

I want it to load the sample files in the toy_data folder, turn them into a searchable knowledge base, and then answer questions from that content in a clear chat style. Please make it easy to run from top to bottom in one notebook, with short explanations in between cells so I can follow what is happening. If you need current setup details, look up the latest docs online.

Please include a few example questions at the end so I can see it working right away, and show where the answer came from when possible. Keep it lightweight and beginner friendly, since this is mainly for learning and testing the basic RAG flow rather than building a full app.