[
https://issues.apache.org/jira/browse/SOLR-18267?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18092886#comment-18092886
]
ASF subversion and git services commented on SOLR-18267:
--------------------------------------------------------
Commit 07036ab1c700a1ead8282482d495b17b17bf0387 in solr's branch
refs/heads/main from Adam Quigley
[ https://gitbox.apache.org/repos/asf?p=solr.git;h=07036ab1c70 ]
SOLR-18267: Add flat vector index with no HNSW (#4492)
> Skip HSNW graph construction for exact vector search
> ----------------------------------------------------
>
> Key: SOLR-18267
> URL: https://issues.apache.org/jira/browse/SOLR-18267
> Project: Solr
> Issue Type: New Feature
> Components: vector-search
> Reporter: Alessandro Benedetti
> Assignee: Alessandro Benedetti
> Priority: Minor
> Labels: pull-request-available, vector-based-search
> Time Spent: 1h 40m
> Remaining Estimate: 0h
>
> The idea we are exploring is not building the HNSW graph in the case of a
> highly selective filter search use case, and performing brute force KNN
> comparison as a post-filter.
> The goal behind the feature is to not pay the cost of HNSW building during
> ingestion when ANN search isn't used.
>
> A collaborator of ours already created a proof-of-concept on a branch of
> upstream Solr that adds knnAlgorithm="flat" to DenseVectorField using
> Lucene99FlatVectorsFormat. This stores vectors in the index (.vec/.vemf
> files) without building the HNSW graph (.vex/.vem files).
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
