SeededKnnVectorQuery

This is a version of knn vector query that provides a query seed to initiate the vector search. NOTE: The underlying format is free to ignore the provided seed

See "Lexically-Accelerated Dense Retrieval" (Kulkarni, Hrishikesh and MacAvaney, Sean and Goharian, Nazli and Frieder, Ophir). In SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval Pages 152 - 162

Types

Link copied to clipboard
object Companion
Link copied to clipboard
open inner class SeededCollectorManager(knnCollectorManager: KnnCollectorManager) : KnnCollectorManager

Properties

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
val k: Int

Functions

Link copied to clipboard
open fun createWeight(searcher: IndexSearcher, scoreMode: ScoreMode, boost: Float): Weight

Expert: Constructs an appropriate Weight implementation for this query.

Link copied to clipboard
open operator override fun equals(o: Any?): Boolean

Override and implement query instance equivalence properly in a subclass. This is required so that QueryCache works properly.

Link copied to clipboard
open override fun hashCode(): Int

Override and implement query hash code properly in a subclass. This is required so that [ ] works properly.

Link copied to clipboard
open override fun rewrite(indexSearcher: IndexSearcher): Query

Expert: called to re-write queries into primitive queries. For example, a PrefixQuery will be rewritten into a BooleanQuery that consists of TermQuerys.

Link copied to clipboard
open override fun toString(): String

Prints a query to a string.

open override fun toString(field: String?): String

Prints a query to a string, with field assumed to be the default field and omitted.

Link copied to clipboard
open override fun visit(visitor: QueryVisitor)

Recurse through the query tree, visiting any child queries.