neural-search
https://github.com/opensearch-project/neural-search
Java
Plugin that adds dense neural retrieval into the OpenSearch ecosytem
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Java not yet supported0 Subscribers
Add a CodeTriage badge to neural-search
Help out
- Issues
- [Hybrid Query] Allow `sort: [_score, <field>]` without collapse and page it with `search_after`
- [AUTOCUT] Integration Test Failed for neural-search-3.10.0
- Propose moving @zane-neo to Emeritus status
- Make batch size configurable for semantic field ingest processor
- [BUG] text_chunking fixed_char_length splits surrogate pairs, producing chunks with unpaired surrogates
- [BUG] neural_sparse query with the default analyzer silently returns no hits for many Japanese queries (query becomes only [UNK])
- [FEATURE] Allow CJK tokenizers (icu_tokenizer, kuromoji_tokenizer, smartcn_tokenizer) in the fixed_token_length chunking algorithm
- [Hybrid Query] Extract shared fusion math cores
- [BUG] sparse_vector (SEISMIC): after #1926 query token IDs >= 32768 are folded but document tokens are not — documents become unreachable and queries silently return another token's documents (lucene and native engines, 3.9.0)
- [PROPOSAL] Pass fusion weights with hybrid query request
- Docs
- Java not yet supported