find
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.
Each cluster has an anchor proposition and a list of similar propositions above the similarity threshold. Clusters are deduplicated so that each pair appears only once (the proposition with the lower ID is the anchor).
Return
Clusters ordered by size (largest first), excluding empty clusters
Parameters
similarity
Minimum cosine similarity to include in a cluster
top
Maximum number of similar items per cluster
query
Optional query to pre-filter which propositions participate