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

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?

Retrieval adds a "hop" before generation. How would you minimize the time-to-first-token (TTFT) for a user?

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