Technical

Scaling Kubernetes Workloads with the OpenSearch KEDA Scaler

The new OpenSearch KEDA scaler, introduced in KEDA 2.20, allows Kubernetes workloads to scale directly based on any arbitrary query result from OpenSearch, such as error rates or l…

Retrieve vectors 5x faster with docvalue_fields in OpenSearch

OpenSearch 3.7 introduces the ability to retrieve vectors via `docvaluefields` rather than the traditional `source` path, allowing for direct reading from the columnar store. This …

Single pane of glass for all your telemetry: The OpenSearch Observability Stack

The OpenSearch Observability Stack is an OpenTelemetry-native platform that unifies metrics, traces, and logs into a single correlated store to streamline root cause analysis. The …

No more zero results with vector query relaxing in OpenSearch

This article discusses how vector search in OpenSearch acts as a semantic safety net to prevent zero-result pages when traditional lexical search strategies fail to match user inte…

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.…

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…

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 the OpenSearch Hadoop connector 2.0: Spark 4 support, OpenSearch Serverless, and more

The OpenSearch Hadoop connector 2.0 has been released, introducing support for Apache Spark 3.5 and 4, as well as official compatibility for OpenSearch 3.x. The update also adds su…

Benchmarking multimodal document search in OpenSearch: Three approaches compared

This article benchmarks three approaches for multimodal document search in OpenSearch—ColPali, BDA modality-aware embedding, and text-only chunking—evaluating their trade-offs in s…

Solving context overflow: How OpenSearch agents stay smart in long conversations

OpenSearch 3.5 introduces a new context management system for OpenSearch Agents designed to prevent context window overflow and performance degradation during long AI conversations…

Advancing OpenSearch with gRPC and Protocol Buffers

OpenSearch is adopting gRPC as a high-performance alternative to its traditional REST APIs, addressing limitations with JSON's parsing overhead and payload size for data-intensive …