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

Why might you use a "Cross-Encoder" re-ranker after your initial vector retrieval? What is the trade-off in terms of latency?

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

If a user asks a vague question like "Tell me more about that," how do you ensure the retriever finds relevant documents from past conversation history?