Skip to main content
Cloud & AI Hub
Browse
Glossary AI Directory Playgrounds Models Prompts Explainers Strategy Matrix Benchmark Decoder

Product Quantization (PQ)

A lossy vector compression technique that reduces database RAM footprints.

PQ splits high-dimensional vectors into smaller sub-vectors, quantizing each sub-vector into codebook values. This compresses vector footprints, allowing massive datasets to reside in memory.

Historical figures and technical concepts for informational purposes only. Not technical, professional, legal, or financial advice. Sources: Official Documentation.