Elasticsearch Labs Blog
All Articles
ML Research
•Evaluating scalar quantization in Elasticsearch
Learn how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch.
How ToIntegrations
•ES|QL queries to Java objects
How perform ES|QL queries with the Java client
Vector SearchGenerative AI
•Making Elasticsearch and Lucene the best vector database: up to 8x faster and 32x efficient
Recent features bring significant performance gains to Elasticsearch and Lucene vector database.
Vector SearchGenerative AI
•Elastic Cloud adds Elasticsearch Vector Database optimized instance to Google Cloud
Elasticsearch adds a new vector search optimized profile for GCP.
ML Research
•Scalar Quantization Optimized for Vector Databases
Optimizing scalar quantization for the vector database use case allows us to achieve significantly better performance for the same retrieval quality at high compression ratios.
LuceneML Research
•Int4: More Scalar Quantization in Lucene
Optimizing scalar quantization in Lucene and adding int4 support.
Lucene
•Making Lucene Faster with Vectorization and FFI/madvise
Moving Lucene forward with modern Java features
Vector Search
•Simplifying kNN search
Benchmarking & experimentation for simplifying kNN-search
How ToIntegrations
•Evolution of the Elasticsearch .NET Client
From NEST to Elastic.Clients.Elasticsearch