Fast vs. accurate: Measuring the recall of quantized vector search
Explaining how to measure recall for vector search in Elasticsearch with minimal setup.
Adaptive early termination for HNSW in Elasticsearch
Introducing a new adaptive early termination strategy for HNSW in Elasticsearch.
Elasticsearch vector search is up to 8x faster than OpenSearch
Exploring filtered vector search benchmarks of OpenSearch vs. Elasticsearch and why vector search performance is critical for context-engineered systems.
Elasticsearch 9.3 adds bfloat16 vector support
Exploring the new Elasticsearch element_type: bfloat16, which can halve your vector data storage.
How to defend your RAG system from context poisoning
How context engineering techniques prevent context poisoning in LLM responses.
ES|QL dense vector search support
Using ES|QL for vector search on your dense_vector data.
Speed up vector ingestion using Base64-encoded strings
Introducing Base64-encoded strings to speed up vector ingestion in Elasticsearch.
Apache Lucene 2025 wrap-up
2025 was a stellar year for Apache Lucene; here are our highlights.
Comparing dense vector search performance with the Profile API in Elasticsearch
Learn how to use the Profile API in Elasticsearch to compare dense vector configurations and tune kNN performance with visual data from Kibana.
Up to 12x Faster Vector Indexing in Elasticsearch with NVIDIA cuVS: GPU-acceleration Chapter 2
Discover how Elasticsearch achieves nearly 12x higher indexing throughput with GPU-accelerated vector indexing and NVIDIA cuVS.
Multimodal search for mountain peaks with Elasticsearch and SigLIP-2
Learn how to implement text-to-image and image-to-image multimodal search using SigLIP-2 embeddings and Elasticsearch kNN vector search. Project focus: finding Mount Ama Dablam peak photos from an Everest trek.
Improving multilingual embedding model relevancy with hybrid search reranking
Learn how to improve the relevancy of E5 multilingual embedding model search results using Cohere's reranker and hybrid search in Elasticsearch.