benwtrent commented on code in PR #3468: URL: https://github.com/apache/solr/pull/3468#discussion_r2336886498
########## solr/solr-ref-guide/modules/query-guide/pages/dense-vector-search.adoc: ########## @@ -316,6 +316,70 @@ preserved when `stored` is true. + Accepted values: `BOOLEAN` +=== BinaryBitQuantizedDenseVectorField + +Binary bit quantization is a different quantization technique that is even more aggressive in its compression and is able +to reduce each dimension from a 32 bit float down to a single bit. This is done by normalizing each dimension of a vector +relative to a centroid (mid-point pre-calculated against all vectors in the index) with the stored bit +representing whether the actual value is positive or negative of the centroid's value. A further "corrective factor" is computed +and stored to help compensate accuracy in the estimated distance. For more details, the original white paper can be viewed +https://arxiv.org/pdf/2405.12497[here]. Review Comment: Yeah, its a very large set of combination of techniques and net new techniques. Lucene's various attributions purposefully try to attribute different inspirations to each of the appropriate papers while also trying to call out what makes Lucene's technique unique. Its not a pure copy, but it does evolve on the various techniques listed. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
