Version 3.1.0.0 Release Notes
Compatible with OpenSearch 3.1.0.0
Features
- Introduce memory optimized search for Faiss binary index types #2735
- Create RescoreKnnVectorQuery to support rescore after executing inner vector search query #2709
Enhancements
- Removing redundant type conversions for script scoring for hamming space with binary vectors #2351
- Apply mask operation in preindex to optimize derived source #2704
- [Remote Vector Index Build] Add tuned repository upload/download configurations per benchmarking results #2662
- [Remote Vector Index Build] Add segment size upper bound setting and prepare other settings for GA #2734
- [Remote Vector Index Build] Make
index.knn.remote_index_build.enableddefault to true #2743 - Update rescore context for 4X Compression #2750
Bug Fixes
- [BUGFIX] Fix KNN Quantization state cache have an invalid weight threshold #2666
- [BUGFIX] Fix enable rescoring when dimensions > 1000. #2671
- [BUGFIX] Honors slice counts for non-quantization cases #2692
- [BUGFIX] Block derived source enable if index.knn is false #2702
- Block mode and compression for indices created before version 2.17.0 #2722
- [BUGFIX] Avoid opening of graph file if graph is already loaded in memory #2719
- [BUGFIX] [Remote Vector Index Build] End remote build metrics before falling back to CPU, exception logging #2693
- [BUGFIX] Fix RefCount and ClearCache in some race conditions #2728
- [BUGFIX] Fix nested vector query at efficient filter scenarios #2641
- [BUGFIX] Fix memory optimized searcher to use a sliced index input #2739
Infrastructure
- Add testing support to run all ITs with remote index builder #2659
- Fix KNNSettingsTests after change in MockNode constructor #2700
Refactoring
- Refactor Knn Search Results to use TopDocs #2727