RAG & Agents
Product Quantization (PQ)
Splitting a vector into m subvectors and quantising each with its own 256-centroid codebook, storing m bytes per vector.
Why interviewers ask about it
8–64× compression with distances from lookup tables. Pair with an exact rescoring stage over the top ~200 to recover most of the lost accuracy.
Related terms
This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.