mirror of
https://github.com/elastic/elasticsearch.git
synced 2025-04-25 15:47:23 -04:00
f23b906891
This adds a new parameter to `knn` that allows filtering nearest neighbor results that are outside a given similarity. `num_candidates` and `k` are still required as this controls the nearest-neighbor vector search accuracy and exploration. For each shard the query will search `num_candidates` and only keep those that are within the provided `similarity` boundary, and then finally reduce to only the global top `k` as normal. For example, when using the `l2_norm` indexed similarity value, this could be considered a `radius` post-filter on `knn`. relates to: https://github.com/elastic/elasticsearch/issues/84929 && https://github.com/elastic/elasticsearch/pull/93574 |
||
|---|---|---|
| .. | ||
| common-options.asciidoc | ||
| common-parms.asciidoc | ||
| cron-expressions.asciidoc | ||
| defs.asciidoc | ||
| index.asciidoc | ||
| info.asciidoc | ||
| rest-api-compatibility.asciidoc | ||
| usage.asciidoc | ||