Red Hat OpenShift AI Operator installation
The Red Hat OpenShift AI Operator is a prerequisite for many IBM AI services and must be installed on the OpenShift cluster by a cluster administrator. To streamline the setup of IBM AI services, this article provides a straightforward introduction to installing the Red Hat OpenShift AI Operator.
The installation process varies depending on whether the OpenShift cluster is internet-connected or operates in an air-gapped environment. This article outlines the installation steps for both scenarios, ensuring compatibility across different OpenShift environments.
Internet-connected installation
The procedures in this documentation shows how to prepare Red Hat OpenShift AI for use in IBM Cloud Pak for Data version 5.0 or greater. These versions of Cloud Pak for Data include watsonx.ai.
Preparing OpenShift AI for use in IBM Cloud Pak for Data
Air-gapped installation
For the air-gapped installation, mirror images is required. Basically, you can follow the steps before the step "Create the RHOAI instance" in below documentation for mirroring the images and the Red Hat OpenShift AI operator installation.
Deploying Red Hat OpenShift Operators in a disconnected environment
After the Red Hat OpenShift AI operator installation done, then you can follow the steps in this documentation to prepare Red Hat OpenShift AI for use in IBM Cloud Pak for Data version 5.0 or greater
Preparing OpenShift AI for use in IBM Cloud Pak for Data
References
Installing operators for Cloud Pak for Data services that require GPUs
RHOAI disconnected install helper