Blogs
Developer insights and practical how-to articles from our experts to inspire and empower your search experience.
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.
56% faster, up to 50% better retrieval performance: What's inside Jina's new 600 million parameter listwise reranker
Jina Reranker 3.5 beats v3 by 50%+ on case law, closes the gap with models 7x its size on legal, medical, and financial benchmarks, and beats them outright on structured data. It's a drop-in replacement for v3, with no API changes.
How Elasticsearch detects multiple change points in time series with 0.99 recall
ES|QL's CHANGE_POINT command finds structural shifts, variance changes and spikes in any metric in ~1ms, without tuning anything per series.
On-prem in under 5 minutes: Jina embedding models now available for on-prem deployment
All 28 Jina AI models, including rerankers, as ready-to-deploy Docker containers, with zero telemetry and no license server. Drop-in compatible with OpenAI, Cohere, Voyage AI and Elastic Inference Service APIs.
Faster Elasticsearch issue triage with redesigned AutoOps
AutoOps introduces clearer severity, updated page layouts, and simpler issue triage for Elastic Cloud Hosted deployments and Cloud Connect clusters.
How to instrument your search API with OpenTelemetry and query it with ES|QL
Add custom attributes to OpenTelemetry spans and run six ES|QL queries that reveal your top searches, zero-result rate and slowest queries.
How Elasticsearch auto-tunes vector quantization to hit your recall target
Learn the geometric model that lets Elasticsearch predict recall with R² > 0.98 accuracy and auto-select vector quantization parameters from a small data sample.
4 NVIDIA AI tasks, 1 Elasticsearch API: Embeddings, chat, completion, and rerank
Set up NVIDIA hosted models in Elasticsearch with one API key and a model ID. No custom integration code needed.
AI shopping agents: Why context comes before the query
AI shopping agents that guess at your vocabulary make expensive mistakes. Pre-computed catalog context stops the guessing before the first tool call.
A picture is worth 1.5x the words: What we learned benchmarking product search embeddings
We benchmarked two embedding models on 5,000 real products and found that combining image and text beats either alone by up to 50%. Here's the data and the model that won.
98.9% faster queries, 4x more indexing throughput: a systematic Elasticsearch performance diagnosis
Use AutoOps, the Profile API and ES Rally together to find cluster hotspots, slow queries and index bottlenecks, with real benchmarks showing a 98.9% latency cut and 4x indexing gain.
