Files
elasticsearch-js/docs/reference/api/KnnSearch.md
2025-05-27 15:30:21 -05:00

1.1 KiB

Interface KnnSearch

Name Type Description
boost float Boost value to apply to kNN scores
field Field The name of the vector field to search against
filter QueryDslQueryContainer QueryDslQueryContainer[]
inner_hits SearchInnerHits If defined, each search hit will contain inner hits.
k integer The final number of nearest neighbors to return as top hits
num_candidates integer The number of nearest neighbor candidates to consider per shard
query_vector_builder QueryVectorBuilder The query vector builder. You must provide a query_vector_builder or query_vector, but not both.
query_vector QueryVector The query vector
rescore_vector RescoreVector Apply oversampling and rescoring to quantized vectors
similarity float The minimum similarity for a vector to be considered a match