30x faster than Prometheus: How we rebuilt Elasticsearch as a leading columnar metrics datastore
Elasticsearch now stores OTel metrics at 3.75 bytes per data point and queries them up to 30x faster than Prometheus. Here's how we rebuilt TSDS and ES|QL.
Three indices walk into a FROM clause: ES|QL subqueries in Elasticsearch
ES|QL subqueries give each data source its own pipeline and filters, eliminating CASE chains, restoring predicate pushdown, and making multi-index queries extensible by design.
Elasticsearch ES|QL views: One query to rule twelve dashboards
With ES|QL views, you only need one query for multiple dashboards. Define it once and let Elasticsearch keep everything in sync.
Elasticsearch ES|QL query builder for JavaScript and TypeScript: Fluent, type-safe query construction
Exploring the Elasticsearch ES|QL query builder for JavaScript and TypeScript and explaining how to build ES|QL queries with practical examples.
Your Elasticsearch field mappings are lying to you — METRICS_INFO and TS_INFO tell the truth
Two new Elasticsearch ES|QL commands that turn time series discovery into a single-line query: METRICS_INFO and TS_INFO tell you which metrics and series actually exist in your data, not just what the mapping declares.
Fast approximate Elasticsearch ES|QL - part II
Explaining the approach we use to obtain fast approximate Elasticsearch ES|QL queries and the testing we did of error estimation.
Fast approximate Elasticsearch ES|QL - part I
Introducing the work we've done on a fast approximate querying mode for Elasticsearch ES|QL. In many cases, it allows us to achieve orders of magnitude latency reductions while providing accurate estimates.
New Elasticsearch ES|QL plugin for IntelliJ IDEA
Build and run Elasticsearch ES|QL queries in your IDE with the new plugin for IntelliJ IDEA.
LINQ to Elasticsearch ES|QL: Write C#, query Elasticsearch
Exploring the new LINQ to Elasticsearch ES|QL provider in the Elasticsearch .NET client, which allows you to write C# code that’s automatically translated to ES|QL queries.
ES|QL dense vector search support
Using ES|QL for vector search on your dense_vector data.
Faster ES|QL stats with Swiss-style hash tables
How Swiss-inspired hashing and SIMD-friendly design deliver consistent, measurable speedups in Elasticsearch Query Language (ES|QL).
Hybrid search and multistage retrieval in ES|QL
Explore the multistage retrieval capabilities of ES|QL, using FORK and FUSE commands to integrate hybrid search with semantic reranking and native LLM completions.