OpenSearch 3.8 streamlines observability workflows

OpenSearch is releasing OpenSearch 3.8, expanding the platform’s search, AI, and observability capabilities with enhanced vector performance, broader agent integrations, and new tools to help users simplify analytics workflows from ingestion to investigation.

Whether connecting agents to external systems, optimizing search relevance with AI, or navigating logs and metrics using new query tools, this release delivers real-world improvements for OpenSearch users, according to the company.

New capabilities in OpenSearch 3.8 include:

• Extending Model Context Protocol (MCP) integration to more agent types.
• Streaming ML predictions with lower latency using gRPC transport.
• Ingesting vectors up to 4.16x faster and improving radial search throughput by up to 2.1x.
• Scaling search relevance evaluation with access to more large language model (LLM) providers.
• Streamlining log analysis using a visual Piped Processing Language (PPL) builder, SQL queries, and an onboarding canvas.
• Shaping, pivoting, and comparing time-series data with new PPL commands.

The latest version of OpenSearch is available for download now.

AI-powered search applications demand fast ingestion, flexible agent architectures, and scalable evaluation. OpenSearch 3.8 delivers all three with up to 4x faster vector ingestion, MCP support across all agent types, and LLM-as-a-Judge expanded to work with any provider, the company said. 

OpenSearch 3.8 introduces Base64-encoded vector ingestion for knn_vector fields, eliminating JSON array serialization overhead on both client and server. Float vectors use little-endian byte encoding—symmetric with the doc values binary output format—while byte and binary vectors use raw byte encoding.

OpenSearch 3.8 also introduces a redesigned graph traversal for radial search by bounding graph exploration for expensive queries to eliminate the wide latency spread that previously affected radial workloads. This improvement works out of the box and requires no mapping, query, or configuration changes, said the vendor.

OpenSearch 3.8 extends MCP support to flow and conversational flow agents, enabling additional agent architectures to connect to external MCP-compliant tool servers. Previously, only conversational and plan-execute-reflect agents supported MCP integrations. Now, all four agent types can access an MCP system using a consistent connector configuration, so users can design the workflow that best fits their use case while making the most of their organization’s tooling, OpenSearch said.

Agentic memory containers now support configurable retention policies that automatically delete expired sessions, long-term memories, and history entries based on time or count limits, eliminating the need for manual cleanup scripts. Operators can set cluster-wide defaults for fleet-level management or configure policies per container, and critical memories can be pinned to exempt them from eviction.

LLM-as-a-Judge in Search Relevance Workbench is no longer limited to OpenAI. You can now generate automated relevance judgments through any ML Commons connector by configuring a provider-specific connector blueprint. Ready-to-use blueprints ship for OpenAI, Azure OpenAI, DeepSeek, Ollama (and other local OpenAI-compatible servers), Google Gemini, Anthropic Claude on Amazon Bedrock, and the Amazon Bedrock Converse API.  

OpenSearch 3.8 streamlines the workflow with a visual PPL builder, in-editor linting, SQL support in Discover logs, and one-click alert creation from metric exploration.

A new Grok Debugger in Dev Tools lets users build and validate Grok patterns directly in OpenSearch Dashboards, no external tools required. This streamlines ingest pipeline development by keeping pattern iteration in the interface where users develop and test configurations, said the vendor.

OpenSearch 3.8 is available for download across all supported distributions and ready to try on OpenSearch Playground.

For more information about this news, visit https://opensearch.org.