mirror of
https://github.com/elastic/elasticsearch.git
synced 2025-04-25 23:57:20 -04:00
8555b350cc
* Add new experimental rank_vectors mapping for late-interaction second order ranking (#118804) Late-interaction models are powerful rerankers. While their size and overall cost doesn't lend itself for HNSW indexing, utilizing them as second order "brute-force" reranking can provide excellent boosts in relevance. At generally lower inference times than large cross-encoders. This commit exposes a new experimental `rank_vectors` field that allows for maxSim operations. This unlocks the initial, and most common use of late-interaction dense-models. For example, this is how you would use it via the API: ``` PUT index { "mappings": { "properties": { "late_interaction_vectors": { "type": "rank_vectors" } } } } ``` Then to index: ``` POST index/_doc { "late_interaction_vectors": [[0.1, ...],...] } ``` For querying, scoring can be exposed with scripting: ``` POST index/_search { "query": { "script_score": { "query": { "match_all": {} }, "script": { "source": "maxSimDotProduct(params.query_vector, 'my_vector')", "params": { "query_vector": [[0.42, ...], ...] } } } } } ``` Of course, the initial ranking should be done before re-scoring or combining via the `rescore` parameter, or simply passing whatever first phase retrieval you want as the inner query in `script_score`. * Update docs/changelog/119601.yaml |
||
|---|---|---|
| .. | ||
| dynamic | ||
| fields | ||
| params | ||
| types | ||
| dynamic-mapping.asciidoc | ||
| explicit-mapping.asciidoc | ||
| fields.asciidoc | ||
| mapping-settings-limit.asciidoc | ||
| params.asciidoc | ||
| removal_of_types.asciidoc | ||
| runtime.asciidoc | ||
| types.asciidoc | ||