Skip to content

Latest commit

 

History

History
58 lines (54 loc) · 5.54 KB

CHANGELOG.md

File metadata and controls

58 lines (54 loc) · 5.54 KB

CHANGELOG

All notable changes to this project are documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning. See the CONTRIBUTING guide for instructions on how to add changelog entries.

Unreleased 3.0

Features

Enhancements

Bug Fixes

Infrastructure

  • Removed JDK 11 and 17 version from CI runs #1921
  • Upgrade min JDK compatibility to JDK 21 #2422

Documentation

Maintenance

Refactoring

Unreleased 2.x

Features

  • Add Support for Multi Values in innerHit for Nested k-NN Fields in Lucene and FAISS (#2283)[#2283]
  • Add binary index support for Lucene engine. (#2292)[#2292]
  • Add expand_nested_docs Parameter support to NMSLIB engine (#2331)[#2331]
  • Add a new build mode, FAISS_OPT_LEVEL=avx512_spr, which enables the use of advanced AVX-512 instructions introduced with Intel(R) Sapphire Rapids (#2404)[#2404]
  • Add cosine similarity support for faiss engine (#2376)[#2376]

Enhancements

  • Introduced a writing layer in native engines where relies on the writing interface to process IO. (#2241)[#2241]
  • Allow method parameter override for training based indices (#2290) https://github.com/opensearch-project/k-NN/pull/2290]
  • Optimizes lucene query execution to prevent unnecessary rewrites (#2305)[#2305]
  • Add check to directly use ANN Search when filters match all docs. (#2320)[#2320]
  • Use one formula to calculate cosine similarity (#2357)[#2357]
  • Add WithFieldName implementation to KNNQueryBuilder (#2398)[#2398]
  • Make the build work for M series MacOS without manual code changes and local JAVA_HOME config (#2397)[#2397]
  • Remove DocsWithFieldSet reference from NativeEngineFieldVectorsWriter (#2408)[#2408]

Bug Fixes

  • Fixing the bug when a segment has no vector field present for disk based vector search (#2282)[#2282]
  • Fixing the bug where search fails with "fields" parameter for an index with a knn_vector field (#2314)[#2314]
  • Fix for NPE while merging segments after all the vector fields docs are deleted (#2365)[#2365]
  • Allow validation for non knn index only after 2.17.0 (#2315)[#2315]
  • Fixing the bug to prevent updating the index.knn setting after index creation(#2348)[#2348]
  • Release query vector memory after execution (#2346)[#2346]
  • Fix shard level rescoring disabled setting flag (#2352)[#2352]
  • Fix filter rewrite logic which was resulting in getting inconsistent / incorrect results for cases where filter was getting rewritten for shards (#2359)[#2359]
  • Fixing it to retrieve space_type from index setting when both method and top level don't have the value. #2374
  • Fixing the bug where setting rescore as false for on_disk knn_vector query is a no-op (#2399)[#2399]
  • Fixing bug where mapping accepts both dimension and model-id (#2410)[#2410]

Infrastructure

  • Updated C++ version in JNI from c++11 to c++17 #2259
  • Upgrade bytebuddy and objenesis version to match OpenSearch core and, update github ci runner for macos #2279

Documentation

Maintenance

  • Select index settings based on cluster version2236
  • Added periodic cache maintenance for QuantizationStateCache and NativeMemoryCache #2308
  • Added null checks for fieldInfo in ExactSearcher to avoid NPE while running exact search for segments with no vector field (#2278)[#2278]
  • Added Lucene BWC tests (#2313)[#2313]
  • Upgrade jsonpath from 2.8.0 to 2.9.02325
  • Bump Faiss commit from 1f42e81 to 0cbc2a8 to accelerate hamming distance calculation using _mm512_popcnt_epi64 intrinsic and also add avx512-fp16 instructions to boost performance #2381
  • Enabled indices.breaker.total.use_real_memory setting via build.gradle for integTest Cluster to catch heap CB in local ITs and github CI actions #2395

Refactoring