Product Documentation for Red Hat OpenShift AI Self-Managed 2.25

Switch to the managed Cloud Service documentation

Switch to the AI Inference Server documentation

Switch to the Enterprise Linux AI documentation

Features, enhancements, resolved issues, and known issues associated with this release

OpenShift AI is a platform for data scientists and developers of artificial intelligence and machine learning (AI/ML) applications

Supported software platforms and architecture

Understand the product life cycle to plan deployments and support applications using the product

Explore a curated collection of learning resources designed to help you accomplish key tasks with Red Hat AI products and services

Let Red Hat know how we can make our documentation better

Install and uninstall OpenShift AI Self-Managed

Install and uninstall OpenShift AI Self-Managed in a disconnected environment

Upgrade OpenShift AI on OpenShift

Upgrade Red Hat OpenShift AI on OpenShift in a disconnected environment

Create a workbench and a custom image by using Custom Resource Definitions (CRDs) and the command-line.

Cluster administrator tasks for managing OpenShift AI

Enabling the model registry component in Red Hat OpenShift AI Self-Managed

Manage and monitor models in Red Hat OpenShift AI Self-Managed

Store, manage, and serve features to machine learning models with Feature Store

Learn about data collected in relation with your usage of the software

Manage administration tasks from the OpenShift AI dashboard

Configure your model-serving platform in Red Hat OpenShift AI Self-Managed

Working with Llama Stack in Red Hat OpenShift AI Self-Managed

Working with accelerators from Red Hat OpenShift AI Self-Managed

Managing model registries in Red Hat OpenShift AI Self-Managed

Learn how to work in an OpenShift AI environment

Use OpenShift AI to train and deploy an example fraud detection model

Work with data stored in an S3-compatible object store from your workbench

Organize your work in projects and workbenches, create and collaborate on notebooks, train and deploy models, configure model servers, and implement pipelines

Working in your data science IDE from Red Hat OpenShift AI Self-Managed

Work with data science pipelines from Red Hat OpenShift AI Self-Managed

Monitor your OpenShift AI models for fairness

Use distributed workloads for faster and more efficient data processing and model training

Connect to applications from Red Hat OpenShift AI Self-Managed

Working with model registries in Red Hat OpenShift AI Self-Managed

Working with the model catalog in Red Hat OpenShift AI Self-Managed

Deploy models in Red Hat OpenShift AI Self-Managed

View a list of API tiers and API version examples for OpenShift AI