Striatum v0.3.0 ships two new artifact kinds, Prompts and Workflows, and the dependency model that already handled Skill-to-Skill dependencies now works across all three. A Workflow can declare Prompt dependencies that are resolved, fetched, and bundled automatically during packaging, then placed exactly where Claude expects them at install time.
AI skills are the new unit of reusable expertise for coding assistants, but sharing them still means copy-pasting files and hoping nothing breaks. Striatum brings real package management to AI skills: versioned manifests, transitive dependency resolution, and distribution through the OCI registries your organization already runs.
Excited to share a new Go library I’ve built to make fetching Kubernetes resources a breeze: go-kube-get! If you’ve worked with client-go to build internal tools or CLI applications, you know that mapping simple user inputs like po or deploy to the precise API group and version (core/v1/pods, apps/v1/deployments) can introduce a lot… Read More »Fetch Kubernetes Resources by Short Name in Go (Like kubectl Does)
Running ONNX models with KServe on macOS—especially ARM64—can be tricky without GPU support from runtimes like NVIDIA Triton. I created a simple demo to make it work.
In the ever-evolving landscape of artificial intelligence (AI), large language models (LLMs) have emerged as a game-changer, transforming how we interact with and derive insights from textual data. As a Java developer, diving into the world of AI might seem intimidating, but it’s not! This tutorial is your gateway to use the power of LLMs through the integration of LangChain4j and Quarkus.
Open Data Hub is an open source AI platform designed for the hybrid cloud. In this video, I show how to install Data Science Pipelines on Open Data Hub 2.4 and above. Leave a comment if you have any questions 😉
Open Data Hub is an open source AI platform designed for the hybrid cloud. In this video, I show how to expose the Object Storage of a Data Science Pipelines application. Open Data Hub source code: https://github.com/opendatahub-io Data Science Pipelines Operator source code: https://github.com/opendatahub-io/data-science-pipelines-operator Leave… Read More »Exposing the Object Storage of a Data Science Pipelines Application in Open Data Hub
Welcome to the world of machine learning, where computers learn from data and make predictions without explicit programming. At the heart of this technology lies the concept of a “model.”
Open source projects have revolutionized the world of software development. They rely on a collaborative approach, with developers from all around the globe coming together to create and improve software that’s freely available for anyone to use. This guide will walk you through the steps to make your first contribution.
In modern software development, it’s common to encounter scenarios where a task or operation takes a significant amount of time to complete. Managing the synchronization and timing of such long-running executions can be challenging. Thankfully, Awaitility, a powerful Java library, provides an elegant solution. In this blog post, we will explore how Awaitility can be used to wait for a long-running execution to finish.