How would you adjust your pipeline if the source documents contained both text and complex financial charts/tables?

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

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

Why is "fixed-length" chunking often insufficient? How would you handle a document where a single sentence contains a critical fact but spans a chunk boundary?