[ https://issues.apache.org/jira/browse/LUCENE-9845?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17302631#comment-17302631 ]
Michael Sokolov commented on LUCENE-9845: ----------------------------------------- It does sound tempting to attack the "dense" case, although the main case I care about is actually the opposite: we have indexes with parent/child documents, and only the parents have vectors. > Improve encoding of HNSW graph offsets > -------------------------------------- > > Key: LUCENE-9845 > URL: https://issues.apache.org/jira/browse/LUCENE-9845 > Project: Lucene - Core > Issue Type: Wish > Reporter: Michael Sokolov > Priority: Major > > Today we use a simple {{long[]}} to encode the offset of each document's > array of neighbors in the HNSW graph. Instead we should use a data structure > that is optimized for encoding an increasing numeric array, like monotonic > {{PackedInts}} -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org