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?

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?

How do you programmatically measure Faithfulness, Answer Relevance, and Context Precision?