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.
From Jupyter Notebook to production-ready artifact: explore our guide to using KitOps and ModelKit for seamless deployment.
Exploring the steps and processes of building an MLOps pipeline.
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 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.
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.
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.
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.
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.
Git is optimized to work with large numbers of small files, like text files. This alone makes Git impractical for managing such datasets.
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.
I have a theory: data scientists do not like Git. I think they did not adopt Git because they needed to version control their notebooks. They adopted Git because when they approached the software developers and DevOps engineers for collaboration that is what they were forced to do.