Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Release Notes for 2.18.0.0 #2227

Merged
merged 2 commits into from
Oct 22, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 1 addition & 20 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -14,30 +14,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
### Maintenance
### Refactoring

## [Unreleased 2.x](https://github.com/opensearch-project/k-NN/compare/2.17...2.x)
## [Unreleased 2.x](https://github.com/opensearch-project/k-NN/compare/2.18...2.x)
### Features
* Add AVX512 support to k-NN for FAISS library [#2069](https://github.com/opensearch-project/k-NN/pull/2069)
### Enhancements
* Introducing a loading layer in FAISS [#2033](https://github.com/opensearch-project/k-NN/issues/2033)
* Add short circuit if no live docs are in segments [#2059](https://github.com/opensearch-project/k-NN/pull/2059)
* Optimize reduceToTopK in ResultUtil by removing pre-filling and reducing peek calls [#2146](https://github.com/opensearch-project/k-NN/pull/2146)
* Update Default Rescore Context based on Dimension [#2149](https://github.com/opensearch-project/k-NN/pull/2149)
* KNNIterators should support with and without filters [#2155](https://github.com/opensearch-project/k-NN/pull/2155)
* Adding Support to Enable/Disble Share level Rescoring and Update Oversampling Factor[#2172](https://github.com/opensearch-project/k-NN/pull/2172)
* Add support to build vector data structures greedily and perform exact search when there are no engine files [#1942](https://github.com/opensearch-project/k-NN/issues/1942)
* Add CompressionLevel Calculation for PQ [#2200](https://github.com/opensearch-project/k-NN/pull/2200)
* Remove FSDirectory dependency from native engine constructing side and deprecated FileWatcher [#2182](https://github.com/opensearch-project/k-NN/pull/2182)
### Bug Fixes
* Add DocValuesProducers for releasing memory when close index [#1946](https://github.com/opensearch-project/k-NN/pull/1946)
* KNN80DocValues should only be considered for BinaryDocValues fields [#2147](https://github.com/opensearch-project/k-NN/pull/2147)
* Score Fix for Binary Quantized Vector and Setting Default value in case of shard level rescoring is disabled for oversampling factor[#2183](https://github.com/opensearch-project/k-NN/pull/2183)
* Java Docs Fix For 2.x[#2190](https://github.com/opensearch-project/k-NN/pull/2190)
### Infrastructure
### Documentation
* Fix sed command in DEVELOPER_GUIDE.md to append a new line character '\n'. [#2181](https://github.com/opensearch-project/k-NN/pull/2181)
### Maintenance
* Remove benchmarks folder from k-NN repo [#2127](https://github.com/opensearch-project/k-NN/pull/2127)
* Fix lucene codec after lucene version bumped to 9.12. [#2195](https://github.com/opensearch-project/k-NN/pull/2195)
### Refactoring
* Does not create additional KNNVectorValues in NativeEngines990KNNVectorWriter when quantization is not needed [#2133](https://github.com/opensearch-project/k-NN/pull/2133)
* Minor refactoring and refactored some unit test [#2167](https://github.com/opensearch-project/k-NN/pull/2167)
29 changes: 29 additions & 0 deletions release-notes/opensearch-knn.release-notes-2.18.0.0.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
## Version 2.18.0.0 Release Notes

Compatible with OpenSearch 2.18.0

### Features
* Add AVX512 support to k-NN for FAISS library [#2069](https://github.com/opensearch-project/k-NN/pull/2069)
### Enhancements
* Introducing a loading layer in FAISS [#2033](https://github.com/opensearch-project/k-NN/issues/2033)
* Add short circuit if no live docs are in segments [#2059](https://github.com/opensearch-project/k-NN/pull/2059)
* Optimize reduceToTopK in ResultUtil by removing pre-filling and reducing peek calls [#2146](https://github.com/opensearch-project/k-NN/pull/2146)
* Update Default Rescore Context based on Dimension [#2149](https://github.com/opensearch-project/k-NN/pull/2149)
* KNNIterators should support with and without filters [#2155](https://github.com/opensearch-project/k-NN/pull/2155)
* Adding Support to Enable/Disble Share level Rescoring and Update Oversampling Factor[#2172](https://github.com/opensearch-project/k-NN/pull/2172)
* Add support to build vector data structures greedily and perform exact search when there are no engine files [#1942](https://github.com/opensearch-project/k-NN/issues/1942)
* Add CompressionLevel Calculation for PQ [#2200](https://github.com/opensearch-project/k-NN/pull/2200)
* Remove FSDirectory dependency from native engine constructing side and deprecated FileWatcher [#2182](https://github.com/opensearch-project/k-NN/pull/2182)
### Bug Fixes
* Add DocValuesProducers for releasing memory when close index [#1946](https://github.com/opensearch-project/k-NN/pull/1946)
* KNN80DocValues should only be considered for BinaryDocValues fields [#2147](https://github.com/opensearch-project/k-NN/pull/2147)
* Score Fix for Binary Quantized Vector and Setting Default value in case of shard level rescoring is disabled for oversampling factor[#2183](https://github.com/opensearch-project/k-NN/pull/2183)
* Java Docs Fix For 2.x[#2190](https://github.com/opensearch-project/k-NN/pull/2190)
### Documentation
* Fix sed command in DEVELOPER_GUIDE.md to append a new line character '\n'. [#2181](https://github.com/opensearch-project/k-NN/pull/2181)
### Maintenance
* Remove benchmarks folder from k-NN repo [#2127](https://github.com/opensearch-project/k-NN/pull/2127)
* Fix lucene codec after lucene version bumped to 9.12. [#2195](https://github.com/opensearch-project/k-NN/pull/2195)
### Refactoring
* Does not create additional KNNVectorValues in NativeEngines990KNNVectorWriter when quantization is not needed [#2133](https://github.com/opensearch-project/k-NN/pull/2133)
* Minor refactoring and refactored some unit test [#2167](https://github.com/opensearch-project/k-NN/pull/2167)
Loading