StackScholar

RAG & Agents

HNSW

Hierarchical Navigable Small World: a multi-layer proximity graph for approximate nearest-neighbour search.

Why interviewers ask about it

Best recall/latency but keeps every full vector plus graph links in RAM. At 100M×768 that is ~330 GB, which is why IVF-PQ (~10 GB) is standard at that scale.

Related terms

Product Quantization (PQ)

Splitting a vector into m subvectors and quantising each with its own 256-centroid codebook, storing m bytes per vector.

This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.