Quarkus at Devoxx Belgium 2024

[insectengine]

Event Description: Devoxx Belgium 2024 (21st edition), a 5-day technology conference, is expected to draw over 3,500 attendees. This year’s event will showcase some of the most innovative and inspiring speakers in the industry, with a special focus on Java 23 and Generative AI. Attendees will experience a diverse range of local and global talent, presenting groundbreaking developments in programming such as Java, Cloud, AI & Big Data, Security,

Dates: October 7-11, 2024
Location: Antwerp, Belgium
Event Type: In Person

https://devoxx.be/

MONDAY

Project Leyden & Quarkus
Speaker(s): Sanne Grinovero
Day/Time: Monday from 12:35 - 13:20 in Room 6
Abstract: As one of the engineers who helped create Quarkus and designed its support for GraalVM native images, I've been eager to explore Project Leyden's potential.
We'll explore what the Quarkus team is doing to make Leyden shine and how to unlock its benefits without adding new inconvenient development processes: free lunch!
While Project Leyden is still in its early stages, we can already reflect on how it will relate to GraalVM native images: is it a complementary or a competing technology? Whatever the answer, very significant efficiency improvements are coming your way and you should prepare to take advantage of them.

Squeezing Performance out of Quarkus
Speaker(s): Julio Faerman
Day/Time: Monday from 16:50 - 18:50 in BOF 2
Abstract: Could we make it to the top 5 with QuarkusIO and GraalVM?
That was my question when the competition started. "Rinha de Backend" is a popular engineering challenge in the Brazillian community, where we had to implement a simple transaction processing backend and make it as fast as possible, with severe resource limitations. With only 1.5 CPU units and 550MB RAM for the entire architecture, we had to squeeze performance anywhere imaginable.
In this session, we'll dive deep into the solution and how to build extremely lightweight containers using QuarkusIO, GraalVM, PostgreSQL, and NGINX. We'll explore the code, run the Gatling load simulation, share the results, and everything else. Join us and let's have fun squeezing performance out of applications!

TUESDAY

Java meets AI: Build LLM-Powered Apps with LangChain4j
Speaker(s): Georgios Andrianakis & Clement Escoffier
Day/Time: Tuesday from 09:30 - 12:30 in Room 5
Abstract: Join us for a guided tour through the possibilities of the LangChain4j framework! Chat with virtually any LLM provider (OpenAI, Gemini, HuggingFace, Azure, AWS, ...)? Generate AI images straight from your Java application with Dall-E and Gemini? Have LLMs return POJOs? Interact with local models on your machine? LangChain4j makes it a piece of cake! We will explain the fundamental building blocks of LLM-powered applications, show you how to chain them together into AI Services, and how to interact with your knowledge base using advanced RAG.
Then, we take a deeper dive into the Quarkus LangChain4j integration. We'll show how little code is needed when using Quarkus, how live reload makes experimenting with prompts a breeze and finally we'll look at its native image generation capabilities, aiming to get your AI-powered app deployment-ready in no time. By the end of this session, you will have all the technical knowledge to get your hands dirty, along with plenty of inspiration for designing the apps of the future.

Create AI-Infused Apps with LangChain4j: Insights from the Quarkus Developers
Speaker(s): Kevin Dubois, Georgios Andrianakis, Eric Deandrea, Clement Escoffier, & Lize Raes
Day/Time: Tuesday from 13:30 - 16:30 in BOF 1
Abstract: Generative AI has taken the world by storm over the last year, and it seems like every executive leader out there is telling us “regular” Java application developers to “add AI” to our applications. Does that mean we need to drop everything we’ve built and become data scientists instead now?
Fortunately, we can infuse AI models built by actual AI experts into our applications in a fairly straightforward way, thanks to some new projects out there. We promise it’s not as complicated as you might think! Thanks to the ease of use and superb developer experience of Quarkus and the nice AI integration capabilities that the LangChain4j libraries offer, it becomes trivial to start working with AI and make your stakeholders happy 🙂
In this lab, you’ll explore a variety of AI capabilities. We’ll start from the Quarkus DevUI where you can try out AI models even before writing any code. Then we’ll get our hands dirty with writing some code and exploring LangChain4j features such as prompting, chaining, and preserving state; agents and function-calling; enriching your AI model’s knowledge with your own documents using retrieval augmented generation (RAG); and discovering ways to run (and train) models locally using tools like Ollama and/or Podman AI Lab. In addition, you’ll add observability and fault tolerance to the AI integration and compile the app to a native binary. You might even try new features, such as generating images or audio!
Come to this session to learn how to build AI-infused applications in Java from the actual Quarkus experts and engineers working on the Quarkus LangChain4j extensions. This is also an opportunity to provide feedback to the maintainers of these projects and contribute back to the community.

WEDNESDAY

Crafting intelligent GitHub Bots | View the Session Video

Speaker(s): Georgios Andrianakis & Guillaume Smet
Day/Time: Wednesday from 12:00 - 12:50 in Room 4
Abstract: One of the sometimes overlooked strengths of GitHub is how much power it gives us developers in creating and augmenting our development workflows.
When combined with the capabilities that Large Language Models now offer us, our workflows can now become truly intelligent and provide us a much needed productivity boost!
A non exhaustive list of use cases that can now be implemented are the following:
Extract the summary from long GitHub conversations
Automate label handling
Provide automatic help for common use cases
Automate reviewer assignment
Issue triaging
Convert screenshots into code
Suggestions for better commit messages
If you would like to know how to implement these, this session is for you. It will explain and demonstrate with live coding how to develop AI infused GitHub bots using the unrivaled combination of Quarkus GitHub App Framework and Quarkus LangChain4j.

Pushing LLMs over the Edge: Exploring the Limits of the Possible
Speaker(s): Mario Fusco & Lize Raes
Day/Time: Wednesday from 16:40 - 17:30 in Room 6
Abstract: Ever wondered just how far you can push things with LLMs? We will explore the limits of the possible by building some outrageous applications and navigating the fine line between pure genius and epic fail. Using LangChain4j and Quarkus, we will create agents that can perform very complex tasks but also wreak havoc on your bank account and database. We will let LLMs run their own code, evaluate each other, pit them against one another (welcome uncensored models), and have them perform prompt injection on themselves. Join us for a fun and crazy ride full of oohs and ouches!

Quarkus Community BOF
Speaker(s): Dimitris Andreadis & Max Rydahl Andersen
Day/Time: Wednesday from 19:00 - 20:00 in BOF 2
Abstract: Quarkus keeps growing and keeps evolving while keeping its focus on efficient runtime and developer time productivity.
We'll have member of the Quarkus core team and extensions contributors present to ask and discuss anything around Quarkus ecosystem.
Bring your questions, share your challenges, and contribute your ideas to shape the future of Quarkus. Discover how you can become an active part of this vibrant community and take advantage of this unique opportunity to Ask Us Anything. Don’t miss out on being part of the conversation that’s setting the direction for Java’s next big leap.

THURSDAY

Crafting Intelligent Applications with Quarkus/LangChain4j
Speaker(s): Dimitris Andreadis
Day/Time: Thursday from 12:50 - 13:35 in Room 10
Abstract: Quarkus/LangChain4j extension. Next morning they showed the Alpha version of that work to the LangChain4j team, and the rest is history.
Quarkus provides an ideal runtime for coding intelligent applications in Java. It builds on top of LangChain4j, offering seamless integration with CDI, build time optimizations, performance and production enhancements, effortless creation of native images using GraalVM and an unmatched developer experience and joy! The Quarkus DevMode makes iterative development and prompt engineering a breeze, Quarkus DevServices can spin up containers for you behind the scenes, and the Quarkus DevUI offers insights into your intelligent applications.
Come to this talk to find out how Quarkus embraces the AI/LLM universe through LangChain4j, and get ideas for crafting your own intelligent applications, starting from simple examples accessing local or remote LLMs, to implementing AI Services and advanced RAG scenarios!

Introduction to Quarkus Security | View the Session Video
Speaker(s): Sergey Beryozkin
Day/Time: Thursday from 15:00 - 15:50 in Room 9
Abstract: In this session, we will introduce Quarkus and Quarkus Security Architecture and explain how it can help solve real world security requirements with Developer Joy remaining a Priority for the Quarkus Security team. We will show how you can develop and test services secured with OpenId Connect in Dev mode. You will learn how to customize a verified security identity, how to use both role and permission based access control, and combine multiple authentication mechanisms with annotations. You will be introduced to one of the most compact ways of generating signed, encrypted or both inner-signed and encrypted JSON Web Tokens, currently available to Quarkus but also SmallRye JWT users. We will finish the session with a demo showing how you can authenticate users with multiple OpenId Connect (OIDC) and OAuth2 providers with a simple configuration only, with many tricky provider specific requirements taken care of under the hood automatically, explain how many different OIDC tenant resolution policies work in Quarkus allowing users build the most complex OIDC provider combinations, and more. Hopefully you will agree after this talk that working with security in Quarkus is the new cool.

Pure Java Enterprise AI/LLM Integration (EAI 2.0) | View the Session Video
Speaker(s): Adam Bien
Day/Time: Thursday from 16:30 - 17:20 in Room 8
Abstract: From REST API and SDKs to langchain4j to fully managed cloud solutions to local integration of open source foundation models.
In this session I will present architectures, ideas, hacks, and workarounds for integrating LLM with Java enterprise applications.
I will illustrate the concepts with Java 21 and Quarkus / MicroProfile code and integrate the latest Claude, ChatGPT, Llama and AWS Bedrock models. Your questions will be given priority and answered interactively.

Zero Waste, Radical Magic, and Italian Graft – Quarkus Efficiency Secrets | View the Session Video
Speaker(s): Holly Cummins
Day/Time: Thursday from 17:40 - 18:30 in Room 6
Abstract: What makes software efficient? Is it how quickly code executes, or is it how quickly developers can use it to solve problems? Quarkus makes both people and hardware more efficient. That’s cool, but how does it work? Usually, we expect to trade-off developer experience against runtime efficiency. In this session, Holly will dive into some of the technical underpinnings of Quarkus’s efficiency. She’ll give advice for those using or considering Quarkus - Do native binaries run fastest? Are verbose programs more efficient? She’ll also share general principles and transferrable discoveries from the engineering team, such as knowing what you’re optimising for, avoiding cache pollution, and how to be static-but-dynamic.