OpenSearchCon Korea 2025
2025-11-04
Seoul, South Korea
as the organisers put it
Watch all 11 sessions from OpenSearchCon Korea 2025. Explore talks on search, observability, AI, security, and more from the global OpenSearch community.
who it's for
platform engineers, search engineers, site reliability engineers, data engineers, machine learning engineers, devops engineers, security engineers, open-source maintainers
topics
OpenSearch Kubernetes operator; blue-green migration for clusters; neural sparse search (SPLADE); hybrid BM25 and vector search; local LLMs with LM Studio; KNN/HNSW vector indexes; segment replication with remote store; query insights dashboard metrics; OpenTelemetry OTLP ingestion; AI-powered observability anomaly detection; operation agent with multi-agent supervisor; searchable snapshots and remote snapshots
| title | author | length |
|---|---|---|
| Welcome & Opening Remarks | Dotan Horovits | 03m |
Morning housekeeping that matters: announces sponsors AWS, OpenSearch Software Foundation, Linux Foundation, points to a QR code for the full event schedule… | ||
| Keynote: OpenSearch on Kubernetes at Atlassian | Cameron Stewart | 14m |
At Atlassian OpenSearch runs across 300+ clusters, ~2,000 nodes and ~20 billion documents; the team builds on the OpenSearch Kubernetes Operator to automate… | ||
| Budget Friendly Semantic Search With Neural Sparse Search | Aswath Srinivasan | 32m |
Walks through a working Neural Sparse Search pipeline on OpenSearch: deploys a doc-only encoder and tokenizer (config copied from docs), indexes Amazon PQA… | ||
| Mastering the Query Insights Dashboard in OpenSearch | David Zane, Chenyang Ji | 17m |
Query Insights captures per-request latency CPU and memory, buffers completed searches and drains into three priority queues every 5 seconds, keeping the top N… | ||
| OpenSearch: From Code to Community | Andrew Ross | 21m |
OpenSearch joins the Linux Foundation, creates the OpenSearch Software Foundation, and moves to open governance with a 15‑member TSC representing 11… | ||
| OpenSearch as the Unified Backend: From Log Storage to Agentic Search Platform at LINE | Sun Ro Lee | 17m |
LINE runs about 1,280 clusters across 10,000+ nodes and grows from log storage to a high‑performance search and vector backend powering core services… | ||
| Beyond Keywords: Building an AI-Powered Search That Reads Your Mind | Prashant Agrawal | 30m |
Shows how an OpenSearch-based pipeline converts short queries into embeddings and expanded JSON filters using Model Context Protocol plus a Strands agent that… | ||
| Building Privacy-First Search With Containerized OpenSearch and Local LLMs | R. Karpe, S. Soni | 21m |
A privacy-first RAG pipeline runs entirely on-prem using containerized OpenSearch (KNN/HNSW vectors, hybrid BM25 support) plus local LLMs served from LM Studio… | ||
| Journey To Cost-Optimized OpenSearch: A Deep Dive Into Segment Replication | V. Bansal, A. Singh | 25m |
Claim: switching from document replication to segment replication plus remote store cuts redundant CPU/IO, raises sustained ingest (benchmarks show ~40% higher… | ||
| From Telemetry to Insight: Building AI-Powered Observability Pipelines with OpenSearch | Neel Shah | 22m |
Shows how to stream logs, traces and metrics from an OpenTelemetry collector via the OTLP exporter into OpenSearch, enrich and time‑roll indexes, and run… | ||
| Accelerating OpenSearch Service Operations With an Operation Agent | Sun Ro Lee | 33m |
Operates ~1300 OpenSearch clusters and reports monthly ~200–400 support tickets and over 200 incident alerts; builds an AI-driven Operation Agent that queries… | ||
| nothing matches | ||