Your question is Metadata Filtering vs Vector Similarity. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
You are building retrieval for an LLM feature that searches a mixed corpus of documents, tickets, and notes. Some queries need exact constraints like source, date, tenant, or document type, while others depend on semantic meaning.
Walk me through metadata filtering versus vector similarity. When would you use which?