agents-features-longterm-memory/ai.koog.agents.longtermmemory.retrieval/KeywordSearchStrategy

KeywordSearchStrategy

class KeywordSearchStrategy(val topK: Int = 10, val similarityThreshold: Double = 0.0, val filterExpression: String? = null) : SearchStrategy(source)

Keyword search mode using full-text/lexical matching.

This mode uses traditional text matching instead of vector similarity, which can be useful for exact term matching or when semantic search is not needed.

Constructors

constructor(topK: Int = 10, similarityThreshold: Double = 0.0, filterExpression: String? = null)

Types

Builder

class Builder

Builder for KeywordSearchStrategy.

Properties

filterExpression

val filterExpression: String?

Optional metadata filter expression for pre-filtering

similarityThreshold

val similarityThreshold: Double

Minimum similarity score (0.0 to 1.0)

topK

val topK: Int

Maximum number of results to return

Functions

create

open override fun create(query: String): SearchRequest

Maps a query string into a SearchRequest for the storage.