Building and deploying AI infused apps with Elasticsearch

Join us for a meetup on April 29th together with Elastic and Red Hat! Doors open at 17.45 and we share some pizzas and drinks before the presentations begin at 18.30. We wrap up around 20.45.

Address: Greencubator Nørrebrogade 20, 1. Sal, 2200 København N (website)

Agenda:
17.45 Doors open
18.00: Pizzas, drinks and networking
18.30: The inner workings of ES|QL
19.10: Building and deploying AI infused apps with Elasticsearch using Podman and OpenShift AI
19.40: Break
19.55: Stateless Elasticsearch inner workings
20.35: Q&A
20.45: Wrap up

Talks:
The inner workings of ES|QL
Last year Elasticsearch added support for an all-new, composable, declarative query language called "ES|QL". Unlike any of the previous query languages supported by Elasticsearch, this is not a wrapper on the original 'Query DSL', but instead a full-stack re-implementation, which allows for some remarkable performance optimizations. On the outside it is a piped query language, allowing for easy composability and convenience. On the inside it is a parallelized, and vectorized query engine providing very high performance for both search and analytics workloads. We even have support for JOIN! In this talk we will take a peek under the hood to see how we built this remarkable new way of querying Elasticsearch.

Speaker: Craig Taverner, Principal Software Engineer I @Elastic

Building and deploying AI infused apps with Elasticsearch using Podman and OpenShift AI
The talk explores how to build and deploy a Retrieval Augmented Generation (RAG) application using OpenShift AI and Podman AI Lab. He will introduce the Podman AI Lab extension, demonstrating how it enables local model testing before deploying into production environments. The session covers vector search fundamentals, demonstrating how Elasticsearch handles vector embeddings for efficient information retrieval. He will also discuss RAG use cases, showcasing how this approach enhances chatbot responses by combining LLMs with real-time data. Finally, he will walk through a live demo of deploying a chatbot on OpenShift AI, integrating Elasticsearch for vector search using LangChain. Attendees will gain a practical understanding of vector-based applications and how to bring them to production environments.

Speaker: Syed M Shaaf, Principal Architect @Red Hat

Stateless Elasticsearch inner workings
Stateless Elasticsearch separates compute from storage while still adhering to the same well-known Elasticsearch APIs. In this talk you will learn the principles of the new architecture including how we ensured data safety, how we optimize for cloud costs in serverless and how this is just a plugin to Elasticsearch. If you like hearing about lock-freedom, concurrency, distributed systems, consistency, trade-offs and more, you'll find this interesting. We'll also cover some of the higher level benefits of this new architecture.

Speaker: Henning Andersen, Distinguished Software Engineer I @Elastic