Delivering the next wave of innovation with OpenSearch
summary
OpenSearch now ships neural search v2.9 plus vector, hybrid, sparse, multimodal and conversational search, and an OpenSearch Assistant that turns natural language into PPL or visualizations. Project claims 15 releases, >2,000 external contributors and >500M downloads. Anomaly detection uses Random Cut Forest with no training required. SAP runs OpenSearch as a hosted observability backend with 7,400 Kubernetes clusters, ~5 PB ingested/month, ~3 PB stored, 1M events/sec at peak, and a control/operator layer for autoscaling, backups and content reconciliation.
AI-written summary · about
chapters (20)
- 0:00Introduction
- 0:33Mukul Karnik
- 1:23Search
- 3:04Basics
- 6:32Traditional Search
- 7:45Neural Search
- 8:54Hybrid Search
- 10:16Sparse Vector
- 12:15Conversational Search
- 14:48Observability Architecture
- 15:43Anomaly Detection
- 19:32OpenSearch Security Analytics
- 20:31Correlation Engine
- 22:21Sap
- 24:26Use Cases
- 26:22Size and scale
- 28:05Numbers
- 29:06Operations
- 30:26Control Components
- 35:08Open Telemetry
related talks
39mFrom Search to Insight: Leveraging OpenSearch for Scalable, AI-Driven Search Experiences
55mVector Search Made Simple: Getting Started with OpenSearch for AI Applications
42mBuilding Self-Healing Infrastructure: Agentic AI & Vector Search in OpenSearch
31mIntelligent Japanese Search With OpenSearch
38mAI-Ready Data Foundation Using Amazon OpenSearch
31mNext-Gen Search: How Uber and the OpenSearch Community Built a Cloud Native 3.0
13mSecuring the Data Frontier: Real-World Strategies With OpenSearch
43mOpenSearch & AI Driven Cloud Native Platforms: Adaptive & Agentic Microserv...