Category: Inside Elastic
Articles tagged Inside Elastic
How we doubled vector search throughput on Elasticsearch Serverless
How we brought Elasticsearch's native SIMD scoring engine to serverless, and why serverless is where vector search innovation happens next.
How Elasticsearch cuts time-series storage by 34% with synthetic _id and bloom filters
Learn how synthetic _id uses bloom filters to cut time-series storage by 34% while maintaining full API compatibility.
Elasticsearch downsampling methods: last-value vs. aggregate sampling
Elasticsearch downsampling now gives you a choice: last-value sampling for maximum storage savings or aggregate sampling for precise rate calculations and counter resets, both fully queryable in ES|QL.
Elasticsearch query logs: One coordinator-level line per query for ES|QL, DSL, SQL, and EQL
Easily understand query impact on cluster performance with Elasticsearch query logs. One coordinator-level line records ES|QL, DSL, SQL, and EQL per request and provides full query text, tracing, optional user context, and CCS hints
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.
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.
Stop guessing which query is burning your cluster: Query activity in Kibana
Pinpoint long-running Elasticsearch searches from Kibana: live tasks, origin context, and cancel when the cluster allows without living in low-level APIs.
Preconditioning Vectors: Making Elasticsearch VectorDB Better Binary Quantization work for every vector
Modern quantization techniques can hurt recall when using older models or embeddings that aren’t normally distributed. Learn how preconditioning fixes these vectors through random orthogonal projection, making BBQ more effective and recovering recall.
How we built Elasticsearch simdvec to make vector search one of the fastest in the world
How we built Elasticsearch simdvec, the hand-tuned SIMD kernel library behind every vector search query in Elasticsearch.
Announcing read-only permissions for Kibana dashboards
Introducing read-only dashboards in Kibana, giving dashboard creators granular sharing controls to keep results accurate and protected from unwanted changes.
Building effective database retrieval tools for context engineering
Best practices for writing database retrieval tools for context engineering. Learn how to design and evaluate agent tools for interacting with Elasticsearch data.
Build task-aware agents with an expanded model catalog on Elastic Inference Service (EIS)
Elastic Inference Service (EIS) expands its managed model catalog, enabling teams to build production-ready agents with flexible model choice across retrieval, generation, and reasoning, without managing GPUs or infrastructure.