OpenSearch

Vectors vs. hallucinations: How OpenSearch keeps GenAI grounded

At OpenSearchCon Europe 2026, Laysa Uchoa argued that generative AI hallucinations are primarily a retrieval problem rather than an inherent limitation of Large Language Models. Sh…

Introducing LLM as a Judge: Scaling search relevance evaluation with AI

OpenSearch 3.5 introduces "LLM as a Judge," a new feature that leverages large language models to automatically and at scale evaluate search result relevance. This approach provide…

Bringing intelligence to OpenSearch: Introducing the OpenSearch agent server

The OpenSearch agent server is an experimental multi-agent orchestration platform that enables users to build and deploy specialized AI agents for specific tasks within OpenSearch.…

Zero-Downtime Modernization: Norwegian Labor and Welfare Administration’s Path to Open Source Observability with OpenSearch

To align with its "open source first" strategy and cloud modernization goals, the Norwegian Labour and Welfare Administration (NAV) migrated its 400GB-per-day logging infrastructur…

Explore OpenSearch 3.7

OpenSearch 3.7 introduces significant enhancements for observability and AI-powered search, focusing on unifying telemetry and accelerating performance. Key updates include native …

OpenSearch in the Agentic Era: What Carl Meadows announced at OpenSearchCon Europe 2026

At OpenSearchCon Europe 2026, Carl Meadows announced three key innovations—OpenSearch Launchpad, the Relevance Agent, and a unified Observability Stack—to position OpenSearch as a …

How a single space broke OpenSearch backups—and how Aiven fixed it

Aiven engineers identified a bug where a single space in a KNN field name caused OpenSearch snapshot backups to fail because the snapshot repository rejected the resulting filename…

Asymmetric model support: Optimizing semantic search for queries and documents

OpenSearch 3.5 introduces support for asymmetric embedding models, which enhance semantic search relevance by applying distinct encoding strategies to short queries and long, infor…

Unpacked at Open Source Summit NA 2026: Inside OpenSearch’s Massive Leap into the Agentic Era

OpenSearch 3.6 introduces a significant shift from traditional search to supporting autonomous, agentic AI architectures through new features like pre-packaged Agent Skills and nat…

Agentic SDLC: How OpenSearch accelerates engineering with its own engine

The OpenSearch team has developed four AI agents—Atlas, Ralph, Nitro, and Sentinel—to automate repetitive tasks throughout the software development lifecycle, ranging from knowledg…

Personalizing your contact center agent using OpenSearch agentic memory

OpenSearch agentic memory addresses the lack of conversational context in AI contact center agents by providing persistent, personalized memory across multiple interactions. By uti…

Introducing OpenSearch Relevance Agent: AI-powered search tuning

The OpenSearch Relevance Agent is an automated, multi-agent system designed to replace slow, manual search tuning with data-driven precision. By analyzing user behavior and automat…