neural-search
neural-search copied to clipboard
opensearch-project
Plugin that adds dense neural retrieval into the OpenSearch ecosytem
Hybrid query has high latency comparing to other compound queries like Boolean query. Based on results collected for 2.13 and depending on the dataset and exact query it may be...
# Overview **OpenSearch Neural Search** is an OpenSearch plugin that adds semantic retrieval into the OpenSearch ecosystem. The plugin provides the capability for indexing documents and doing neural search on...
As part of performance optimization for Hybrid query we need to find a way to minimize time taken by getting next matching doc for sun query and collection sun query...
**What is the bug?** When user use map type configuration in several processors, the validation can fail since validation is been done on extra fields in that map. **How can...
### Describe the bug Passing the filter parameter causes the search query to fail when the plain highlighter is enabled. I did a query with the filter parameter following the...
The integration test failed at distribution level for component neural-searchVersion: 2.14.0Distribution: tarArchitecture: arm64Platform: linuxPlease check the logs: https://build.ci.opensearch.org/job/integ-test/8107/display/redirect * Test-report manifest:* - https://ci.opensearch.org/ci/dbc/integ-test/2.14.0/9713/linux/arm64/tar/test-results/8107/integ-test/test-report.yml _Note: Steps to reproduce, additional logs and...
### Is your feature request related to a problem? Currently individual queries of Hybrid query (aka sub-queries) are executed sequentially (Initial implementation that is done under https://github.com/opensearch-project/neural-search/issues/123). That may be...
### What is the bug? Here is the discussion from the forum: https://forum.opensearch.org/t/set-up-default-model-id-for-neural-query-enricher-with-nested-knn-field/19217 ### How can one reproduce the bug? Follow steps in: https://forum.opensearch.org/t/set-up-default-model-id-for-neural-query-enricher-with-nested-knn-field/19217 ### What is the expected behavior?...
Hi all, How to use cross-encoder model to rerank a nested text field? I tried the below but it seems like rerank does not have any effect! PUT /_search/pipeline/ms-marco-MiniLM-L-12-v2_rerank {...
### What is the bug? When configured with deep nested map type configuration in text_embedding processor, the embedding result will override the original value of document key: pipeline configuration: ```...
Metadata
Owner
Metadata
Plugin that adds dense neural retrieval into the OpenSearch ecosytem