Java Champion | CNCF DevEx Tech Lead | Agentic AI Foundation Ambassador | Senior Principal Developer Advocate at IBM Content and opinions are my own.
Press Enter to Search or ESC to Close
At the end of the previous post, I wrote that my custom routing code could probably be replaced by a built-in LangChain4j pattern soon that Mario Fusco and I had discussed after my initial blog post. On 2 October LangChain4j merged the resulting DecisionRouterPlanner, which selects and runs sub-agents with a DecisionModel. Time for me […]
In the first post I replaced the LLM supervisor in a Quarkus LangChain4j car-rental assistant with a System One decision model. A custom Planner asked one Choice question (“which specialist?”) and called that agent, and an OutputGuardrail asked a yes/no (Noul) question to check each reply. I could only test the hosted Jev path against […]
Lately, there’s been some buzz around Jev, TypeSafe’s “System One” model. The core idea is simple: instead of begging an LLM to output structured text and then writing a fragile parser to get that data back into your code, you send the model a state and some typed questions. It returns typed answers, complete with […]
I’m working on a new series of tutorials to help Java developers understand how they can work with AI models such as OpenAI’s ChatGPT and Dall-e, Deepseek, Granite, Llama3, and pretty much any other model out there. The stack of choice is LangChain4j and Quarkus, which are in my opinion the easiest tools to work […]
I recently recorded a video to demonstrate how to work with AI models on our local machine using a new feature of Podman Desktop called “Podman AI Lab”, and Quarkus with LangChain4j. To make it even more interesting, I used an InstructLab model which is an interesting project to open not only the using of […]
