Lately, for my Generative AI powered Java apps, I’ve used the Gemini multimodal large language model from Google. But there’s also Gemma, its little sister model. Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. Gemma is available in two sizes: 2B and 7B. Its weights are freely available, and its small size means you can run it on your own, even on your laptop. Read more...

Generative AI exists because of the transformer I confess I rarely read the Financial Times, but they have a really neat articles with animations on how large language models work, thanks to the transformer neural network architecture, an architecture invented by Google in 2017. They talk about text vector embeddings, how the self-attention makes LLM understand the relationship between words and the surrounding context, and also doesn’t forget to mention hallucinations, how “grounding” and RLHF (Reinforcement Learning with Human Feedback) can help mitigate them to some extent. Read more...

Inspired my by super boss Richard Seroter with his regular daily reading list, I decided to record and share my tech watch, every week (or so). I always take notes of interesting articles I read for my own curiosity and to remember them when I need those references later on. But also to share them with Les Cast Codeurs podcast! So I hope it’ll be interesting to my readers too! Read more...

I wanted to track the number of views, and also likes, of some YouTube videos I was featured in. For example, when I present a talk at a conference, often the video becomes available at a later time, and I’m not the owner of the channel or video. At first, I wanted to use the YouTube Data API, but I had the impression that I could only see the stats of videos or channels I own, however I think I might be wrong, and should probably revisit this approach later on. Read more...

In this article, let’s revisit the topic of deploying Java apps on Cloud Run. In particular, I’ll deploy a Micronaut app, written with Java 17, and built with Gradle. With a custom Dockerfile On Cloud Run, you deploy containerised applications, so you have to decide the way you want to build a container for your application. In a previous article, I showed an example of using your own Dockerfile, which would look as follows with an OpenJDK 17, and enabling preview features of the language: Read more...

Confined at home, because of the corona-virus pandemic, I’m also doing sport at home. I have a small treadmill for light walks (mostly during conf calls!) and also an elliptical bike. I’d much rather run outside though, but I have to use what I have, even if I hate that stationary elliptical bike in my basement. It’s so boring! So to avoid feeling like wasting my time, I decided to watch videos during my sessions! Read more...

Hot on the heels of the announcement of the general availability of JDK 14, I couldn’t resist taking it for a spin. Without messing up my environment — I’ll confess I’m running 11 on my machine, but I’m still not even using everything that came past Java 8! — I decided to test this new edition within the comfy setting of a Docker container. Minimal OpenJDK 14 image running JShell Super easy to get started (assuming you have Docker installed on your machine), create a Dockerfile with the following content: Read more...

A few weeks ago, I had the chance to be at Devoxx Belgium once again, to meet developers and learn about new things from awesome speakers. Google Cloud Platform had its own booth on the exhibition floor, and the team was running codelabs: 10 laptops were at the disposal of attendees to go through various hands-on tutorials on several GCP products. I took a chance at crafting my own codelab: deploying a Micronaut application, containerized with Jib, to Google Kubernetes Engine. Read more...