// ⌕ RAG & Vector Retrieval
Product Quantization (PQ)
Splits vectors into chunks, each coded by a small codebook, for compressed fast search.
乘积量化 PQ 2011 Intermediate core
IN PLAIN WORDS
Each sub-vector is replaced by its k-means codebook index, compressing vectors to tens of bytes with table-lookup distances; combined with IVF for billion-scale search.
Used in: FAISS IVF-PQ, large vector stores
TIMELINE · prerequisites → this → what builds on it
01Original paper
Product Quantization for Nearest Neighbor Search
Jégou et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2011
DOI ↗ ✓ Verified · Crossref API doi:10.1109/TPAMI.2010.57
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
Related:HNSW (Hierarchical Navigable Small World)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
On learning paths:AI Application Engineer
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
product-quantization)