irvingzhang opened a new pull request #1169: LUCENE-9004: A minor feature and patch -- support deleting vector values and fix segments merging URL: https://github.com/apache/lucene-solr/pull/1169 I think this commit belongs to this issue (https://issues.apache.org/jira/browse/LUCENE-9004). I'm not sure if I need to create a new issue. Following are my specified considerations, 1. A minor feature: Regarding to the ANN search problems, it's dangerous to delete vectors according to similarity search result in HNSW. The selected docs are neither sorted nor reduced. The number of deleted vectors is proportional to the segment count and the parameter ef. And the deleted vectors is obviously uncertain. Hence, I created a new type of Query (KnnDelQuery) And Weight (KnnDelScoreWeight) for the dedicated deleting of the exact values that matching the query vector; 2. A minor patch: For fixing the merge process while some segments may contain deleted documents that must be filtered; The modified codes have been tested by the test cases.
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
