Blog
From Proprietary Data to Expert AI with Lamini and KitOps - Jozu MLOps
From Proprietary Data to Expert AI with Lamini and KitOps
Critical LLM Security Risks and Best Practices for Teams - Jozu MLOps
Critical LLM Security Risks and Best Practices for Teams
Enhance LLMs and streamline MLOps using InstructLab and KitOps | Red Hat Developer
Enhance LLMs and streamline MLOps using InstructLab and KitOps
Turn DevOps to MLOps Pipelines With This Open-Source Tool - Jozu MLOps
Turn DevOps to MLOps Pipelines With This Open-Source Tool
Turn Your Existing DevOps Pipeline Into an MLOps Pipeline With ModelKits - Jozu MLOps
Turn Your Existing DevOps Pipeline Into an MLOps Pipeline With ModelKits
From Jupyter Notebook to deployed application in 4 steps - Jozu MLOps
From Jupyter Notebook to deployed application in 4 steps.
10 Open Source MLOps Projects You Didn’t Know About - Jozu MLOps
10 Open Source MLOps Projects You Didn’t Know About.
How to Tune and Deploy Your First Small Language Model (sLLM) - Jozu MLOps
How to Tune and Deploy Your First Small Language Model (sLLM).
Tools to ease collaboration between data scientists and application developers - Jozu MLOps
Tools to ease collaboration between data scientists and application developers.
25 Open Source AI Tools to Cut Your Development Time in Half - Jozu MLOps
25 Open Source AI Tools to Cut Your Development Time in Half.
In this article, we build a Retrieval-Augmented Generation (RAG) pipeline using KitOps, integrating tools like ChromaDB for embeddings, Llama 3 for language models, and SentenceTransformer for embedding models.
How to turn a Jupyter Notebook into a deployable artifact - Jozu MLOps
From Jupyter Notebook to production-ready artifact: explore our guide to using KitOps and ModelKit for seamless deployment.
How to turn a Jupyter Notebook into a deployable artifact - Jozu MLOps
How to turn a Jupyter Notebook into a deployable artifact.
A step-by-step guide to building an MLOps pipeline - Jozu MLOps
Exploring the steps and processes of building an MLOps pipeline.
- YouTube
Let's dive into the dynamic relationship between enterprises and AI/ML teams with Brad Micklea, Founder & CEO of Jozu and project lead for Kitops.ml. Brad shares valuable insights on bridging the gap and improving the collaboration between these entities. From common challenges to effective strategies, Brad sheds light on the crucial role of communication, alignment, and AI/ML literacy in driving successful collaborations.
I fine-tuned my model on a new programming language. You can do it too! 🚀
I have been using OpenAI ChatGPT-4 for a while now. I don't have a lot of bad stuff to say about... Tagged with webdev, javascript, beginners, programming.
Why enterprise AI projects are moving too slowly
This post lists the challenges with getting an AI/ML project from development into production and offers suggestions on organizational and tooling changes (like KitOps' ModelKits) that can help. Tagged with devops, ai, opensource, aiops.
KitOps: The Bridge Between AI/ML Models and DevOps
Yesterday, Brad Micklea, Jozu CEO and KitOps maintainer, was a guest on the Partially Redacted podcast hosted by Sean Falconer. The 45-minute conversation covered a lot of ground. Specifically, the current state of the KitOps project, where the project is headed, and some of our early ideas for productizing and releasing Jozu, which builds on top of KitOps. In this post I dive a bit deeper into a few of these topics.
Strategies for Tagging ModelKits
ModelKits, much like other OCI artifacts, can be identified using tags that are comprehensible to humans. This blog explores various strategies for effectively tagging your ModelKits.
Balancing Innovation and Responsibility in AI/ML Deployment with Jozu's Brad Micklea
Listen to this episode from Partially Redacted: Data Privacy, Security & Compliance on Spotify. In this episode, we dive into the world of MLOps, the engine behind secure and reliable AI/ML deployments. MLOps focuses on the lifecycle of machine learning models, ensuring they are developed and deployed efficiently and responsibly. With the explosion of ML applications, the demand for specialized tools has skyrocketed, highlighting the need for improved observability, auditing, and reproducibility. This shift necessitates an evolution in ML toolchains to address gaps in security, governance, and reliability. Jozu is a platform founded to tackle these very challenges by enhancing the collaboration between AI/ML and application development teams. Jozu aims to provide a comprehensive suite of tools focusing on efficiency throughout the model development and deployment process. This conversation discusses the importance of MLOps, the limitations of current tools, and how Jozu is paving the way for the future of secure and reliable ML deployments.
Beyond Git: A New Collaboration Model for AI/ML Development
Git is optimized to work with large numbers of small files, like text files. This alone makes Git impractical for managing such datasets.
The transitory nature of MLOps: Advocating for DevOps/MLOps coalescence
AI/ML is a wildfire of a trend. It’s being integrated into just about every application you can think... Tagged with ai, devops, opensource, machinelearning.
Do data scientists really like Git?
I have a theory: data scientists do not like Git.