Elasticsearch Vector Database: Ship in minutes, scale affordably to hundreds of billions
The hard parts of hybrid retrieval, already done, with optimized defaults, third party and native Jina AI models, and managed GPU inference all out of the box. Build fast, scalable AI apps, not infrastructure.
No more allocation delays: Decoupling snapshots from shard relocation in stateless Elasticsearch
Clusters scale out under load without waiting for a snapshot to finish, because snapshots now read straight from the object store and no longer pin shards in place.
Avoiding and Correcting Hotspots: How Elasticsearch Serverless Balances Shards
Elasticsearch Serverless replaces the Elasticsearch node-weight based shard rebalancing algorithm with resource usage aware rebalancing that avoids index shard colocation, OOM events and write load hotspotting
Your AI agent doesn't need your API key: OAuth 2.1 for Elasticsearch MCP server authentication
OAuth 2.1 lets you connect AI agents to the Elasticsearch MCP server with a browser sign-in instead of an API key. Your agent gets a short-lived token tied to your permissions that you can revoke any time.
17% faster search, zero config: auto-calibrating vector quantization in Elasticsearch
Automatic calibration at merge time picks vector quantization parameters for each segment by predicting recall from a small sample. Here's how we built it into Elasticsearch's merge path.
Replica management: Inside the system that keeps Elasticsearch Serverless searches fast at scale
A technical walkthrough of how two replica systems (one for failover, one for load balancing) combine every five minutes into a single cache-aware recommendation per index in Elasticsearch Serverless.
Your Elastic agent, Google's ADK, and zero custom APIs: building “Lucky Planet” over A2A
Elastic Agent Builder's native A2A endpoint lets Google's ADK orchestrate a remote agent, with no custom REST API. Watch it work in 'Lucky Planet,' a random-exoplanet game built end-to-end.
Elasticsearch reindex now relocates across nodes automatically: zero user intervention, no lost progress
Elasticsearch reindex now survives node shutdowns, uses Point in Time for more efficient source iteration, and ships with dedicated management APIs. Reindex-from-remote is GA in Serverless.
One query, multiple Elasticsearch Serverless projects: introducing cross-project search
Cross-project search in Elastic Cloud Serverless lets you query data across isolated projects in a single Elasticsearch or ES|QL request: no duplication, no network peering, and no egress costs from copying logs.
Faster cross-project search in Elasticsearch Serverless with project tags and routing
Scope cross-project search in Elasticsearch Serverless with project routing to skip non-matching projects entirely, or with project tag fields to filter, aggregate, and sort by tag inside the query.
How cross-project search (CPS) works in Elasticsearch Serverless
Elastic Cloud Serverless cross-project search (CPS) treats index expressions as cross-project by default. This post explains how TransportSearchAction scopes projects, resolves index expressions, skips projects with no matches, and validates index resolution against allow_no_indices and ignore_unavailable.
Introducing unified API keys for Elastic Cloud Serverless and Elasticsearch
Learn how Elastic unified control plane and data plane authentication in Serverless with a globally distributed IAM architecture. Use one API key for Cloud and Elasticsearch APIs.