Kevin is a Java Champion, software engineer, author and international speaker with a passion for open source, Java, and cloud native development & deployment practices. He currently works as developer advocate at Red Hat where he gets to enjoy working with open source projects and improving the developer experience.
Kevin is actively involved in open source communities, contributing to projects such as Quarkus, Knative, Apache Camel, and Podman (Desktop). He is also a member of the Belgian CNCF and the Belgian Java User Group.
Kevin speaks English, Dutch, French and Italian fluently and is currently based in Belgium, having lived in Italy and the USA as well.
In his free time you can find Kevin somewhere in the wild hiking, gravel biking, snowboarding or packrafting.
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.
(Generative) AI has taken the world by storm and acted as an accelerant to business transformation. Sure, it can potentially increase efficiency and productivity, but doesn’t it feel a little bit like the Wild, Wild West out there? Many “regular” application developers are overwhelmed with having to deal with yet another paradigm shift and a new set of things to learn. Even Data Scientists, creating models themselves, are often not sure where to go once they’ve experimented, trained and refined models.
Fortunately, the open source world offers a wonderful opportunity to standardize and democratize the way developers and data scientists work with AI.
Join this session for a series of live demos featuring innovative open source projects that accelerate development cycles and optimize release performance for AI applications. You’ll discover how to build and deliver AI models and AI-infused applications in a repeatable, secure, and enterprise way using tried-and-true technologies and methodologies such as containers, Java, Kubernetes, CI/CD, and GitOps. You will also learn how to integrate open source models into Java applications in a fully local development environment.
Projects covered include OpenDataHub, Backstage, LangChain4j, Kserve, Podman AI Lab, and more.
Searching for speaker images...