AI engineering glossary · RAG vector search
What is PQ (product quantisation)?
Product quantisation (also called PQ): A compression method that splits each vector into equal sub-vectors and replaces each with the id of its nearest entry in a small learned codebook. It shrinks vectors many times over and allows fast approximate distance calculations, with some loss of accuracy.
Product quantisation: an example
A 768-dimension float vector of 3,072 bytes is stored as 96 one-byte codes, a 32-fold reduction.
Related terms
More RAG vector search terms
- Proposition indexing
- Query decomposition
- Query expansion
- Query rewriting
- RAG evaluation
- Ragas
- RAPTOR
- Re-embedding
Where you learn it
Product quantisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.