

Vector search capabilities in Apache Solr with HNSW indexing, early termination optimization, and integrated text-to-vector capabilities for hybrid search applications.
Apache Solr's Dense Vector Search adds support for indexing and searching dense numerical vectors, enabling k-nearest neighbor (kNN) searches with various similarity functions and advanced filtering capabilities.
Apache Solr 10.0.0 introduces PatienceKnnVectorQuery that allows searches to exit early when the HNSW queue remains saturated over a saturation threshold, reducing query latency and resource usage with minimal impact on recall.
Solr 9.8 introduced a module enabling transparent end-to-end semantic search by integrating with LLM providers (OpenAI, Cohere, HuggingFace, Mistral AI) via LangChain4j library.
ACORN is an algorithm designed to make hybrid searches consisting of a filter and a vector search more efficient, based on research from 2024.
Free and open-source under Apache 2.0 license. No licensing costs for any use case.
Loading more......