Quarkus at DevConf.cz 2024

[insectengine]

Event Description: DevConf.CZ is a community conference for developers, admins, DevOps engineers, testers, documentation writers and other contributors to open source technologies.

Date: June 13-15, 2024
Location: Brno, Czech Republic
Event Type: In Person

https://www.devconf.info/cz/

Quarkus meets AI: Developing AI applications in Java with Quarkus and Langchain4j
Speaker(s): Jan Martiška
Day/Time: 06-13, 13:15–13:50 (Europe/Prague), D0206
Abstract: In this practical session, I will demonstrate how Quarkus, the cloud-native Java development framework, and its Langchain4j extension can be used for working with AI models like GPT and others, including image-generating models, opening the door to endless possibilities.
I will show how to use Quarkus to:

• Build a chatbot application that allows you to supply data from your own custom data store and feed it to the AI model, enabling it to answer questions using this data (this technique is called Retrieval Augmented Generation).
• Build a highly autonomous agent by supplying the model with various tools, that means locally implemented functions that the model can decide to execute when necessary (for example, send something via email, or write to a database), and then letting the agent determine the appropriate sequence of steps to accomplish the given high-level goal using these tools.
• Demonstrate the Quarkus goodies that make the development process easier, like the interface for manually chatting with the model directly through the application and for exploring image-generating capabilities of image models.

The development joy of Quarkus with all its goodies and incredible productivity now also extends to creating AI applications. Join me and see for yourself!

Is Loom really the future of enterprise Java?
Speaker(s): Martin Štefanko
Day/Time: 06-13, 14:00–14:35 (Europe/Prague), D0206
Abstract: Project Loom, or virtual threads, promised fast, lightweight user-space threads that are very cheap to block. While this is true, everything in life comes at a price. Virtual threads allow users to not care about it. It is the job of the underlying libraries that all our applications use. Issues that can still occur with virtual threads, such as pinning, monopolization, or large thread-local objects, still present real-world problems many libraries still need to account for. Especially in enterprises, these issues might only be noticed once the system reaches the peak loads, which is usually too late. In this session, we explain the virtual thread model execution and compare it to the event loop/reactive model utilized in Quarkus. We will also dive into individual problems that virtual threads might encounter and demonstrate how you can verify that your code doesn’t run into them. By the end of the talk, you’ll understand these (from the user point of view invisible) potential issues with Project Loom.