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.
Low-memory benchmarking in DiskBBQ and HNSW BBQ
Benchmarking Elasticsearch latency, indexing speed, and memory usage for DiskBBQ and HNSW BBQ in low-memory environments.
Introducing a new vector storage format: DiskBBQ
Introducing DiskBBQ, an alternative to HNSW, and exploring when and why to use it.
Deploying a multilingual embedding model in Elasticsearch
Learn how to deploy an e5 multilingual embedding model for vector search and cross-lingual retrieval in Elasticsearch.