08How does approximate nearest-neighbor search work, and how do you choose a vector index (HNSW vs IVF)?▼medium★ EssentialGleanCohereDatabricks2 repliesunlockedEvery RAG system rests on a vector index, and the interviewer wants to know you understand the recall/latency/memory tradeoff, not just 'use a vector DB.' The signal is why exact search does not scale and how HNSW and IVF make different bets.Open full answer →
49Your vector index won't fit in RAM at a billion vectors. How do you choose between HNSW, IVF-PQ, and disk-based ANN?▼hardGleanPineconeAWS1 replies◆ premiumAt a billion vectors the index choice is a memory budget problem before it's a recall problem. Flat search is out, HNSW may not fit, and PQ trades recall for RAM. Here is the decision a staff engineer makes on the whiteboard.Open full answer →
68How do you do incremental indexing for a RAG system with constant document churn, without a nightly full rebuild?▼hardGleanDatabricksMicrosoft1 replies◆ premiumRe-embedding 10M documents nightly is wasteful when only 0.5% changed. The signal is upserting by stable id, handling deletes and tombstones in an ANN index, and compacting before fragmentation tanks recall and latency.Open full answer →
