neural-search
neural-search copied to clipboard
Plugin that adds dense neural retrieval into the OpenSearch ecosytem
### What is the bug? The total count is wrong when size is given in the search request. For example When I hit the search request with Hybrid query with...
### Description 1. Add new thread pool to schedule tasks that are related to hybrid query execution 2. Register executor builders with Plugin 3. Use Lucene's Task Executor to execute...
### What is the bug? The BWC tests get failed after changing the shard number in index. The error is due to "index not found" even if we assert the...
**Is your feature request related to a problem?** Hybrid Search always returns results in the descending order of score. Applying sorting as below has no affect on the results ```...
### Description This PR adds support for asymmetric embedding models such as https://huggingface.co/intfloat/multilingual-e5-small to the neural-search plugin. It builds on the work done in https://github.com/opensearch-project/ml-commons/issues/1799. Asymmetric embedding models behave differently...
### Description Add support for batch ingestion in TextEmbeddingProcessor & SparseEncodingProcessor to improve ingestion performance. https://github.com/opensearch-project/neural-search/issues/743 ### Issues Resolved https://github.com/opensearch-project/neural-search/issues/743 ### Check List - [x] New functionality includes testing. -...
### Description Update github workflow to fix text chunking BWC test in version 2.13.0. ### Issues Resolved https://github.com/opensearch-project/neural-search/issues/690 ### Check List - [ ] New functionality includes testing. - [...
### Description PLEASE DO NOT MERGE THIS PR! This PR is only used to test the index creation bug according to index shard number. ### Issues Resolved Bug test ###...
### Description This change implement for #646 - Enhance the speed of neuralsparse query by two-phase. - Now support top-level, boolean and boost compound query; for other compound query will...
### Is your feature request related to a problem? RFC: https://github.com/opensearch-project/OpenSearch/issues/12457 We have implemented batch ingestion logic in OpenSearch core in version 2.14, now we want to enable the batch...