OpenSearch Project Blog

Discover the new Live Queries API in OpenSearch Query Insights 3.0, enabling real-time visibility into currently executing search queries to identify and debug performance issues as they happen.

Learn about derived source for vectors, introduced in OpenSearch 3.0: why it matters, how it works, and how to start using it to improve performance and reduce storage costs.

The Java Security Manager (JSM) has long been a foundational security mechanism in OpenSearch. With its deprecation underway, this blog post explores the alternative technologies adopted to replace JSM.

Learn how to optimize inference processors in OpenSearch to reduce redundant model calls, lower costs, and improve ingestion performance.

Optimize OpenSearch cluster performance by separating indexing and search operations. Discover write/search replicas and dedicated search nodes, with benchmark data showing 34% lower query latency through workload separation.

Learn how to build a hybrid search application using OpenSearch as a vector database. Bookmark this step-by-step guide to implementing semantic and keyword search with a recipe dataset.

Explore how the plan-execute-reflect agent in OpenSearch 3.0 transforms troubleshooting by automatically investigating system issues. See this AI agent in action as it analyzes data and provides solutions through a real-world debugging example.

OpenSearch now supports Model Context Protocol (MCP), a framework simplifying AI agent integration with search tools. Learn how MCP reduces development complexity and enables seamless AI-powered data access for enhanced search solutions.

OpenSearch 3.0 delivers major performance improvements, including 10x faster search queries, 2.5x vector search boost, and GPU acceleration. Learn about key enhancements and the future roadmap.

OpenSearch Benchmark is the de-facto performance benchmarking tool for OpenSearch.

Learn how star-tree index improves the performance of aggregations in OpenSearch.

Explore z-score normalization in OpenSearch 3.0-beta1 for hybrid search. Learn how this technique compares to min-max normalization through benchmarks on search relevance and performance.

Dive into the major updates in OpenSearch 3.0, including Lucene 10 integration, JVM 21 adoption, and performance improvements. Learn about breaking changes, critical upgrades, and enhanced capabilities.

Data Prepper 2.11.0 offers better OpenTelemetry support and new integrations with external sources.

In this blog post, we'll explore why pagination depth is necessary for hybrid queries, show you how to use this feature, and share benchmarking results.

OpenSearch Query Insights gives you essential visibility into how search queries perform, helping you understand how queries run and how they use cluster resources. Since introducing Query Insights, we’ve aimed...

OpenSearch provides a wide range of capabilities to support modern search needs, including traditional keyword-based techniques like lexical search using BM25 and more advanced methods like semantic and hybrid search....

Vector search plays a crucial role in many machine learning (ML) and data science pipelines. In the context of large language models (LLMs), vector search powers retrieval-augmented generation (RAG), a technique...

Introduced in OpenSearch 2.18, Intel Advanced Vector Extensions 512 (Intel AVX-512) is a set of new instructions that can accelerate vector workload performance. Vector search benchmarks using OpenSearch Benchmark showed...