How we built Elasticsearch simdvec to make vector search one of the fastest in the world
Elasticsearch Labs
How we built Elasticsearch simdvec to make vector search one of the fastest in the world
How we built Elasticsearch simdvec, the hand-tuned SIMD kernel library behind every vector search query in Elasticsearch.
Elasticsearch 9.3 adds bfloat16 vector support
Elasticsearch Labs
Elasticsearch 9.3 adds bfloat16 vector support
Exploring the new Elasticsearch element_type: bfloat16, which can halve your vector data storage.
HNSW graph: How to improve Elasticsearch performance
Elasticsearch Labs
HNSW graph: How to improve Elasticsearch performance
Learn how to use the HNSW graph M and ef_construction parameters to improve search performance.
Using Direct IO for vector searches
Elasticsearch Labs
Using Direct IO for vector searches
Using rescoring for kNN vector searches improves search recall, but can increase latency. Learn how to reduce this impact by leveraging direct IO.