GenAI & BeyondHands-on Lab180min
Build your own Java-powered Agentic Apps
This session demonstrates building Java-based Agentic AI applications using Quarkus and LangChain4j. It covers creating LLM clients, adding agentic features, exploring alternative AI patterns, and practical techniques, offering hands-on experience and direct interaction with the engineers behind Quarkus AI and LangChain4j.
Georgios AndrianakisIBM
Mario FuscoIBM
Kevin DuboisIBM
Clement EscoffierRed Hat
Guillaume SmetIBM
talkDetail.whenAndWhere
Tuesday, October 7, 13:30-16:30
BOF 2
You’ve likely heard it everywhere lately: “This is the year of Agentic AI”!! Well, then why not roll up your sleeves and try creating your own Java-based Agentic AI app?
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 Agentic AI.
In this session, you’ll explore a variety of Agentic AI capabilities. We’ll start by creating a simple AI client to interact with an LLM. We’ll then explore how we can make this app “agentic” by adding a variety of agentic capabilities, such as local function calling, MCP, Agent2Agent, and more.
In addition, we’ll also try out different techniques and patterns to get your LLM leveled up to leverage these Agentic capabilities. We’ll also attempt to show that agents are in fact not always needed, and show alternative patterns to accomplish AI tasks.
Come to this session to learn how to build Agentic AI applications in Java from the experts and engineers actively working on Quarkus AI and LangChain4j. This is also an opportunity to provide feedback to the maintainers of these projects and contribute back to the community.
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 Agentic AI.
In this session, you’ll explore a variety of Agentic AI capabilities. We’ll start by creating a simple AI client to interact with an LLM. We’ll then explore how we can make this app “agentic” by adding a variety of agentic capabilities, such as local function calling, MCP, Agent2Agent, and more.
In addition, we’ll also try out different techniques and patterns to get your LLM leveled up to leverage these Agentic capabilities. We’ll also attempt to show that agents are in fact not always needed, and show alternative patterns to accomplish AI tasks.
Come to this session to learn how to build Agentic AI applications in Java from the experts and engineers actively working on Quarkus AI and LangChain4j. This is also an opportunity to provide feedback to the maintainers of these projects and contribute back to the community.
Georgios Andrianakis
Georgios works for IBM as a Senior Principal Software Engineer and is currently one of the most active contributors of Quarkus, where he works in all sorts of areas, including but not limited to LangChain4j, RESTEasy Reactive, Spring compatibility, Kubernetes support, testing, Kotlin and more.
He is also an enthusiastic promoter of Quarkus that never misses a chance to spread the Quarkus love!
He is also an enthusiastic promoter of Quarkus that never misses a chance to spread the Quarkus love!
Mario Fusco
Mario is a senior principal software engineer at IBM working as Drools project lead. Among his interests there are also high performance systems and generative AI, being an active contributor of widely adopted projects like Quarkus and LangChain4j. He is also a Java Champion, the JUG Milano coordinator, a frequent speaker and the co-author of "Modern Java in Action" published by Manning.
Kevin Dubois
Kevin Dubois is often featured as a (keynote) speaker at conferences around the world, where he shares his passion and knowledge about developer experience, open source, cloud native development and Java. He is also an author, java Champion, and an accomplished software architect and platform engineer. Kevin currently works as a Senior Principal Developer Advocate at Red Hat / IBM.
Clement Escoffier
Clement Escoffier (@clementplop) is a distinguished engineer at Red Hat and co-lead of the Quarkus project. He is a Java Champion. Before joining Red Hat, Clement had several professional lives, from academic positions to management. He contributed to projects and products, touching many domains and technologies such as OSGi, mobile, continuous delivery, and DevOps. Clement has always been interested in software engineering, distributed systems, and event-driven architecture. He recently focused on Reactive Systems, Cloud-Native applications, and Kubernetes. Clement contributed to many open-source projects, such as Apache Felix, Eclipse Vert.x, SmallRye, Mutiny, and Quarkus. He also authored the "Reactive Systems in Java" book.
Guillaume Smet
Guillaume is Senior Principal Software Engineer at Red Hat.
He has spent his career (20+ years, he doesn't get any younger...) working with and on Open Source Software.
Major contributor and release manager of Quarkus, he puts a lot of effort into improving the automation for the project and initiated the Quarkus GitHub App and Quarkus GitHub Action extensions.
On his spare time, he reads a lot of contemporary French literature.
He has spent his career (20+ years, he doesn't get any younger...) working with and on Open Source Software.
Major contributor and release manager of Quarkus, he puts a lot of effort into improving the automation for the project and initiated the Quarkus GitHub App and Quarkus GitHub Action extensions.
On his spare time, he reads a lot of contemporary French literature.
comments.speakerNotEnabledComments