VectorSearchCapable

Opt-in capability for proposition stores that support vector similarity search and clustering.

Only implement this if the store has a real embedder backing it. Consumers can check for the capability with an is/as? test rather than calling and guessing from an empty result.

Inheritors

Properties

Link copied to clipboard

Whether this particular instance can actually run vector search. Implementing the interface is a type-level promise; this is the runtime truth. A store that can be wired without an embedder (so it satisfies the type but has nothing to embed with) should override this to report whether it was given one. Lets a caller — e.g. PropositionStoreTemplate.supportsVector — distinguish "configured for vectors" from "vector search will quietly return empty".

Functions

Link copied to clipboard
open fun findClusters(similarityThreshold: <Error class: unknown class> = 0.7, topK: Int = 10, query: PropositionQuery = PropositionQuery()): List<<Error class: unknown class><Proposition>>

Find clusters of similar propositions.

Link copied to clipboard
open fun findSimilar(textSimilaritySearchRequest: <Error class: unknown class>): List<Proposition>

Find propositions similar to the given text using vector similarity.

Link copied to clipboard
abstract fun findSimilarWithScores(textSimilaritySearchRequest: <Error class: unknown class>): List<<Error class: unknown class><Proposition>>

Find propositions similar to the given text with similarity scores.

open fun findSimilarWithScores(textSimilaritySearchRequest: <Error class: unknown class>, query: PropositionQuery): List<<Error class: unknown class><Proposition>>

Vector similarity search with an additional PropositionQuery filter applied to results.

Link copied to clipboard
abstract fun query(query: PropositionQuery): List<Proposition>

Query propositions by specification. Required by findSimilarWithScores (filtered overload) and findClusters; satisfied automatically when a type also implements PropositionStore.