Explain how you would combine BM25 (keyword) and Vector (semantic) search. What kind of queries would fail if you only used vector search?

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

If the retriever returns zero relevant documents, how do you prevent the LLM from making up an answer?

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