Re:Why HNSW is not the answer and disk-based alternatives mi...
by VoVAllen on Monday December 23, 2024 @10:43PM
(#42499576)
Hi, I'm the author of the article. In our product, VectorChord, we use a quantization algorithm called RaBitQ, which doesn’t require a separate codebook. Unlike IVFPQ, it avoids the need to maintain and update the corresponding codebook, so the update issue you mentioned is not a problem. Regarding filtering, I’m not sure which specific scenario you’re referring to, but we currently support iterative post-filtering and are technically capable of perfectly supporting pre-filtering as well.
[ Parent
| on HN ]
Re:Why HNSW is not the answer and disk-based alternatives mi...
by binarymax on Tuesday December 24, 2024 @05:33AM
(#42501017)
Pre and post filtering are both not great. Some HNSW implementations in products like Vespa and Qdrant have filter-during-search.
This remains an unsolved problem in cluster-based indices.