RAG & retrieval pipelines
21 questions
- Explain parent-child (small-to-big) retrieval. What problem does it solve and what does it cost you?mid
- Explain HNSW. What do M, ef_construction and ef_search each control, and which can you change in production?mid
- How would you tune HNSW for 10 million vectors when the product needs p95 retrieval under 100 ms?staff
- IVF, HNSW, product quantisation — pick an index for 500M vectors under a hard memory budget and defend it.senior
- Each user can see under 1% of a 50M-document corpus. What happens if you apply the permission filter after ANN search, and what do you do instead?staff
- Pasting an order ID like ORD-88213 returns generic refund-policy chunks after a move from keyword to vector search. Diagnose and fix.mid
- Weighted min-max fusion with an alpha versus reciprocal rank fusion — which do you ship, and how do you tune it?senior
- The vector database already returns similarity scores. Why add a reranker, and how deep do you rerank?mid
- When does reranking not help, or actively hurt, a production RAG system?senior
- How do you evaluate retrieval separately from generation, and which metric do you fix first?mid
- Your offline recall is 0.91 but production recall is 0.40. What went wrong in the evaluation, and how do you fix it?staff
- You want an LLM judge to gate deploys on faithfulness. How do you validate it before you trust it?senior
- Your recall@5 is 95%. Does that mean the system answers 95% of questions correctly?senior
- Latency, throughput and retrieval health all look normal, but users say answers are subtly out of date. Diagnose.staff
- A junior analyst gets an answer that quotes a privileged memo they are not staffed on. Firewalls and DLP saw nothing. What failed?staff
- Answers cite real documents that do not actually contain the claim. How do you detect and fix bad citations?senior
- After adding query rewriting and a reranker, p95 went from 900 ms to 4 s. Where do you look and what do you cut?senior
- Walk me through a production RAG pipeline end to end. Where do these systems actually fail?senior
- A question needs facts from three documents, like "compare UK and Netherlands parental leave". How does retrieval change?senior
- What does the retriever do when a query has no relevant documents at all? Design the abstain path.senior
- Your RAG system works on 10k documents but degrades at 1M. What changes besides the index?staff