Johannes Bechberger is a JVM developer working on profilers and their underlying technology in the SapMachine team at SAP. This includes improvements to async-profiler and its ecosystem, a website to view the different JFR event types, and improvements to the FirefoxProfiler, making it usable in the Java world. His work today comprises many open-source contributions and his blog, where he regularly writes on in-depth profiling and debugging topics. He also works on hello-ebpf, the first eBPF library for Java. His most recent contribution is the new CPU Time Profiler in JDK 25.
Let’s create a tiny LLM library together
– Room 2
Foredragsholder
Om sesjonen
When you want to integrate AI into your tools, what do you do? You add langchain4j or spring-ai and run with it. These fairly big libraries work well. But do you know how these libraries interact with the AI service providers or your local LLM instance? These libraries aren't magic; they are just abstractions of the underlying REST APIs.
In this talk, we'll peek behind the curtain, write a tiny LLM library together live on stage, and use it to build a tiny chatbot with tool support.
Passer for
People interested in learning the fundamentals of common LLM APIs
Samtidig i programmet
- Bootiful Spring Boot 4 Room 1
- My Year with Claude: Building Midimeria - music production analytics Room 3
- Talk to me Java! Room 4
- What RSCs can do in Next.js today Room 5
- Sunset as a Service: Når målet er EOL Room 6
- The best way to fetch multi-level hierarchies from a RDBMS using Java Room 7
- The 1% Problem: An Introduction to AI Security Room 8
- Conways lov i praksis Room 6
- Metodikk som tvangstrøye Room 6