llm4s-core
API
Generated with
llm4s-core/org.llm4s/org.llm4s.vectorstore/AsyncHybridSearcher

AsyncHybridSearcher

org.llm4s.vectorstore.AsyncHybridSearcher
See theAsyncHybridSearcher companion object
final class AsyncHybridSearcher

Asynchronous Hybrid Searcher.

Provides unified, non-blocking search over both vector embeddings (semantic similarity) and keyword indexes (BM25 term matching). Features complete architectural concurrency—vector search and keyword search execute in parallel across independent blocking thread configurations, optimizing latency during RRF/Weighted queries.

Attributes

Companion
object
Graph
Supertypes
class Object
trait Matchable
class Any

Members list

Value members

Concrete methods

def close(): Unit
def search(queryEmbedding: Array[Float], queryText: String, topK: Int, strategy: FusionStrategy, filter: Option[MetadataFilter])(implicit ec: ExecutionContext): AsyncResult[Seq[HybridSearchResult]]
def searchKeywordOnly(queryText: String, topK: Int, filter: Option[MetadataFilter])(implicit ec: ExecutionContext): AsyncResult[Seq[HybridSearchResult]]
def searchVectorOnly(queryEmbedding: Array[Float], topK: Int, filter: Option[MetadataFilter])(implicit ec: ExecutionContext): AsyncResult[Seq[HybridSearchResult]]
def searchWithReranking(queryEmbedding: Array[Float], queryText: String, topK: Int, rerankTopK: Int, strategy: FusionStrategy, filter: Option[MetadataFilter], reranker: Option[Reranker])(implicit ec: ExecutionContext): AsyncResult[Seq[HybridSearchResult]]

Concrete fields

Generated with