If your retriever finds 50 relevant "top" chunks but your LLM context window only fits 10, how do you decide which ones to keep?

If a company has a 1,000-page internal wiki that updates daily, would you recommend RAG or fine-tuning? Why?

Walk me through the lifecycle of a user query, from the moment they hit "Enter" to the final response generation.

How would you design a cache that returns a result even if the user's question isn't a 100% string match to a previous query?