Product quantization for vector search | Hacker News
In general though PQ is a pretty good baseline. I'm glad all these vector DB companies seem to have decided that the best form of marketing is high-quality summaries/tutorials about fundamental concepts, it's a good contribution to the community.
There are a lot of directions people try to go, making different tradeoffs in the complexity of the clustering, the loss from the quantization, the impact on performance (esp. trying to get some subset of the tables to fit in cache). Readers might be interested in [1], which gives a survey of some of the directions. In general though PQ is a pretty good baseline. I'm glad all these vector DB companies seem to have decided that the best form of marketing is high-quality summaries/tutorials about fundamental concepts, it's a good contribution to the community. [1] Fig. 1 in…
related reading
- Announcing ScaNN: Efficient Vector Similarity Searchai.googleblog.com
- TurboQuant: Redefining AI efficiency with extreme compressionresearch.google
- Product Quantization: Compressing high-dimensional vectors by 97% | Pineconepinecone.io
- [2504.19874] TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratearxiv.org
- TurboQuant: Redefining AI efficiency with extreme compressionresearch.google
- Faiss indexes · facebookresearch/faiss Wiki · GitHubgithub.com
- Faiss: A library for efficient similarity search - Engineering at Metaengineering.fb.com
- Welcome to Faiss Documentation - Faiss documentationfaiss.ai
- Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
- Hierarchical Navigable Small Worlds (HNSW) | Pineconepinecone.io
- GitHub - facebookresearch/faiss: A library for efficient similarity search and clustering of dense vectors.github.com
- Lower memory footprint · facebookresearch/faiss Wiki · GitHubgithub.com