hnsw

Every RAG system rests on a vector index, and the interviewer wants proof you grasp the recall/latency/memory tradeoff, not just 'use a vector DB.' The signal is why exact search will not scale and how HNSW and IVF place different bets.

At a billion vectors the index choice is a memory budget question before it's a recall question. Flat search is off the table, HNSW may not fit, and PQ swaps recall for RAM. Here is the call a staff engineer makes on the whiteboard.

Re-embedding 10M documents nightly is wasteful when only 0.5% changed. Interviewers want to see you upsert by stable id, handle deletes and tombstones in an ANN index, and compact before fragmentation tanks recall and latency.

Every RAG design says 'just filter by tenant_id.' Almost nobody can explain why that one line can quietly cut recall in half. The answer is in what the filter does to the ANN graph.