Blog

Unlocking agentic AI experiences with OpenSearch

Jun 09, 2025 • technical-posts

As search evolves from text-based inputs to conversational, interactive experiences, the power of agentic AI is unlocking new ways to connect with systems, applications, and large language models (LLMs). Recently,...

Enhanced log analysis with OpenSearch PPL: Introducing lookup, join, and subsearch

May 30, 2025 • technical-posts

OpenSearch 3.0 introduced powerful new capabilities to the Piped Processing Language (PPL) with the addition of the lookup, join, and subsearch commands. These commands help you enrich, correlate, and filter...

Optimizing inference processors for cost efficiency and performance

May 29, 2025 • technical-posts

Inference processors, such as text_embedding, text_image_embedding, and sparse_encoding, enable the generation of vector embeddings during document ingestion or updates. Today, these processors invoke model inference every time a document is...

Improve OpenSearch cluster performance by separating search and indexing workloads

May 27, 2025 • technical-posts

All OpenSearch indexes consist of shards, with each document in an index stored in a shard.

Introducing common filter support for hybrid search queries

May 23, 2025 • technical-posts

Hybrid search in OpenSearch enables you to combine different query types, such as lexical (keyword) and semantic (vector) queries, to produce one result set. This powerful capability is ideal for...

Do more with less: Save up to 3x on storage with derived vector source

May 20, 2025 • technical-posts

If you’re working with modern applications, from semantic search to recommendation systems, you’re likely implementing vector search. While you might focus on the accuracy and speed of vector similarity searches,...

Finding a replacement for JSM in OpenSearch 3.0

May 19, 2025 • technical-posts

OpenSearch 3.0.0 introduced many innovative features that provide significant advancements in performance, data management, vector database functionality, and more. In the release announcement, we shared that OpenSearch has replaced the...

Intelligent troubleshooting using OpenSearch 3.0's plan-execute-reflect agent

May 19, 2025 • technical-posts

OpenSearch 3.0 introduces the plan–execute–reflect agent—a powerful new capability that breaks down complex problems, selects and executes tools autonomously, and adapts through reflection. In this post, we’ll show you how...

Introducing MCP in OpenSearch

May 15, 2025 • technical-posts

Model Context Protocol (MCP) is a standardized communication framework that reduces the integration complexity between AI agents and external tools. Without MCP, you may face significant technical overhead because each...

OpenSearch Project update: Performance progress in OpenSearch 3.0

May 14, 2025 • technical-posts, community

Learn more about the strategic enhancements and performance features that OpenSearch has delivered up to version 3.0.

OpenSearch Benchmark: An update

May 12, 2025 • community

OpenSearch Benchmark is the performance benchmarking tool for OpenSearch.

Real-time query monitoring with live queries in OpenSearch 3.0

May 09, 2025 • technical-posts

OpenSearch Query Insights has become an important tool for understanding search query performance, offering visibility into how queries execute and consume cluster resources. Building on our commitment to helping you...

Introducing the z-score normalization technique for hybrid search

Apr 28, 2025 • technical-posts

In search engines and machine learning, data normalization is essential for making fair and accurate comparisons between different features or scores.

Recipes to vectors: Building a hybrid search app with OpenSearch

Apr 25, 2025 • technical-posts

Ever wondered if OpenSearch can double as a vector database? Spoiler: it absolutely can. Whether you’re building a modern search experience, exploring hybrid retrieval, or just curious about embeddings, OpenSearch...

OpenSearch version 3.0: New features, breaking changes from Apache Lucene 10, and what to expect

Apr 24, 2025 • technical-post

OpenSearch version 3.0: New features, breaking changes from Apache Lucene™ 10, and what to expect