OpenSearchCon Europe 2026

The IPCEI-CIS program is shaping the next wave of European cloud-edge innovation by enabling secure and sovereign digital infrastructures.
In this context, Adeptic Reply demonstrates how natural language can be transformed into a fully structured deployment request. We built an open AI powered engine capable of structuring requests being able to be executed on federated cloud-edge sites, composed of a mix of direct-managed and third parties’ nodes.
To keep these complex and inter-connected scenarios under control, we developed an observability layer allowing users to track performance deviations across the federated cloud-edge sites, ensuring reliability and transparency in the application lifecycle.

This session illustrates how structured AI workflows and federated observability come together to support the IPCEI-CIS vision and enable seamless, trustworthy deployment across distributed cloud domains.

The Partner Roundtable is a great way to interact with OpenSearch leadership and have an open dialogue about the project. We will discuss strategy, challenges and opportunities, community and collaboration, future trends, training and enablement, and project growth. And of course, you are encouraged to openly exchange ideas and experiences, ask questions, share your thoughts, and engage in meaningful discussion.

By invitation only.

The current index authorization model in OpenSearch has a few quirks and weaknesses; these will be mostly noticeable when working in OpenSearch Dashboards or similar applications with users which have only limited access to indices. Thus, if you do not take care and forget to flip certain switches, you will encounter quite a few "Forbidden" errors in OpenSearch Dashboards.
Over the past year, we have been working on a new index authorization concept for OpenSearch. The goal is a more logical and intuitive authorization model that provides a smoother and more predictable user experience.

This new approach is expected to be introduced as an optional feature in an upcoming OpenSearch release and is planned to become the default in OpenSearch 4.

In this talk, we will explain the new authorization concept, highlight its advantages, and provide practical guidance for cluster administrators on how to roll it out safely without causing service interruptions.

OpenSearch is welcoming but the path from first PR to maintainer can feel opaque. This session provides a practical, step-by-step playbook for contributing to OpenSearch and growing as a trusted maintainer.

Learn where to start (repos, good-first-issue), how to pick right-sized work, set up your environment, align with coding and testing norms, and craft high-signal PRs that are easy to review. We’ll cover collaboration habits—scoping changes, attending triages, avoiding churn, handling async reviews, documenting decisions—and show how to build credibility fast.

We’ll outline the maintainer path: observable signals (consistency, quality reviews, ownership, reliability, judgment), responsibilities (triage, design guidance, merges, releases, community health), and how nominations happen. Leave with a 30/60/90-day plan, a review-friendly PR template, and a roadmap to grow consistent contributions into visible impact.

This is the sequel talk to the earlier OpenSearchCon talk on the topic “Budget Friendly Semantic Search With Neural Sparse Search”. This follow up talk we will explain shortcomings such as 1/ pre-trained lack the domain knowledge 2/ off-the-shelf-domain-specific-sparse-model are either expensive/proprietary or non-existent

Level 300-400 talk covering,
1/ Intro to Neural Sparse Search
2/ Pre-trained model shortcomings
3/ Fine-tuning pre-trained model using open-source tools
4/ Use Search Relevancy Workbench to compare pre-trained and fine-tuned sparse model search results

A recommended pre-requisite is to watch the earlier presentation on “Budget Friendly Semantic Search With Neural Sparse Search” - https://www.youtube.com/watch?v=kx71KFf-Nv0

Of course its a completely “optional” pre-requisite as the previous talk will be condensed to a 5 minute lightning talk and will serve as the introduction

This talk will be demo-heavy, showcasing the fine-tuning possibilities of sparse encoder models using data from an existing OpenSearch index, which also means that the approach is suitable for even for those niche domains for which even proprietary models are not available in the market

The Norwegian Labor and Welfare Administration (NAV) manages 1/3 of Norway’s state budget. Supporting their "product-first" paradigm for 20,000 employees required a shift from legacy monoliths to a centralized, self-service observability stack. NAV partnered with Aiven to migrate their logging infrastructure to a managed OpenSearch environment. Aiven has been a strategic partner of NAV by hosting some of NAV’s most critical data services for many years. As a founding member of the OpenSearch Foundation with active maintainers, Aiven provided a unique advantage in helping NAV adopt OpenSearch for their application logging.
This technical deep-dive covers:
* Migration Architecture: High-throughput logging from on-premise to a managed service with zero-downtime
* Scalability & Performance: Shard rebalancing, customized scaling, and automated snapshots
* Data Pipeline: 60TB of log data, and OpenTelemetry traces with Data Prepper
* Operational Stability: Self-healing nodes and alert integrations with Slack.
We will cover usage scenarios of OpenSearch dashboards and take a close look at how Aiven delivers and operates OpenSearch as a managed service at Nav’s scale.

Most production monitoring follows the same path: metrics fire an alert, engineers search logs for context, and human reasoning becomes the bottleneck. A global p95 alert triggers, and 10–15 minutes later someone realizes the issue is limited to ap-south-1. Metrics and logs are tightly coupled through manual toil.

This session proposes a simple shift: logs detect first.

Structured JSON logs become system signals. These are indexed into purpose-built OpenSearch indexes, where sliding-window aggregation queries continuously evaluate system state. Queries like “p95 latency by region over 5 minutes” yield precise outcomes such as “REGION_OUTAGE: ap-south-1” instead of noisy global alerts.

Through a live demo, we show how explicit log schemas, index mappings, and Query DSL enable context-rich, machine-driven evaluation without dashboards or ad hoc searches. OpenSearch evaluates signals; actions remain external and decoupled.

The result is reduced human toil, a clearer system state, and a practical pattern that complements existing monitoring stacks without overpromising scale.

Caching is essential for achieving low latency and high throughput in search systems, yet it’s often misunderstood or misused. OpenSearch and Lucene provide multiple caching layers—such as the request cache, field data cache, and Lucene query cache—each designed for different workloads and access patterns.

In this talk, we break down how OpenSearch caches work, when they help, and common pitfalls that lead to low hit rates or wasted memory. We share lessons from real production systems, showing how tuning, architectural choices, and benchmark-driven evaluation improve cache effectiveness, performance, and resiliency.

We then discuss optimizations across key cache layers — the request cache, field data cache, and Lucene query cache — and the impact they have on real workloads.

Finally, we introduce tiered caching, when it makes sense, how it integrates with existing cache layers, and the trade-offs involved.

This session is intended for engineers who want a practical understanding of caching in OpenSearch and Lucene and actionable guidance for improving search performance in production.