computer science kubernetes ai, Schemes and Mind Maps of Computer Science

Download computer science kubernetes ai and more Schemes and Mind Maps Computer Science in PDF only on Docsity!

Red Hat OpenShift AI Self-Managed

Installing and uninstalling OpenShift AI Self-

Managed

Install and uninstall OpenShift AI Self-Managed

Last Updated: 2025-10-

Legal Notice

Copyright © 2025 Red Hat, Inc.

The text of and illustrations in this document are licensed by Red Hat under a Creative Commons

Attribution–Share Alike 3.0 Unported license ("CC-BY-SA"). An explanation of CC-BY-SA is

available at

http://creativecommons.org/licenses/by-sa/3.0/

. In accordance with CC-BY-SA, if you distribute this document or an adaptation of it, you must

provide the URL for the original version.

Red Hat, as the licensor of this document, waives the right to enforce, and agrees not to assert,

Section 4d of CC-BY-SA to the fullest extent permitted by applicable law.

Red Hat, Red Hat Enterprise Linux, the Shadowman logo, the Red Hat logo, JBoss, OpenShift,

Fedora, the Infinity logo, and RHCE are trademarks of Red Hat, Inc., registered in the United States

and other countries.

Linux ® is the registered trademark of Linus Torvalds in the United States and other countries.

Java ® is a registered trademark of Oracle and/or its affiliates.

XFS ® is a trademark of Silicon Graphics International Corp. or its subsidiaries in the United States

and/or other countries.

MySQL ® is a registered trademark of MySQL AB in the United States, the European Union and

other countries.

Node.js ® is an official trademark of Joyent. Red Hat is not formally related to or endorsed by the

official Joyent Node.js open source or commercial project.

The OpenStack ® Word Mark and OpenStack logo are either registered trademarks/service marks

or trademarks/service marks of the OpenStack Foundation, in the United States and other

countries and are used with the OpenStack Foundation's permission. We are not affiliated with,

endorsed or sponsored by the OpenStack Foundation, or the OpenStack community.

All other trademarks are the property of their respective owners.

Abstract

Install and uninstall OpenShift AI Self-Managed on your OpenShift cluster.

.......................................................................................................................... .......................................................................................................................... .......................................................................................................................... .......................................................................................................................... .......................................................................................................................... .......................................................................................................................... .......................................................................................................................... .......................................................................................................................... .......................................................................................................................... .......................................................................................................................... ..........................................................................................................................

Table of Contents

PREFACE CHAPTER 1. ARCHITECTURE OF OPENSHIFT AI SELF-MANAGED CHAPTER 2. UNDERSTANDING UPDATE CHANNELS CHAPTER 3. INSTALLING AND DEPLOYING OPENSHIFT AI 3.1. REQUIREMENTS FOR OPENSHIFT AI SELF-MANAGED 3.2. CONFIGURING CUSTOM NAMESPACES 3.3. INSTALLING THE RED HAT OPENSHIFT AI OPERATOR 3.3.1. Installing the Red Hat OpenShift AI Operator by using the CLI 3.3.2. Installing the Red Hat OpenShift AI Operator by using the web console 3.4. INSTALLING AND MANAGING RED HAT OPENSHIFT AI COMPONENTS 3.4.1. Installing Red Hat OpenShift AI components by using the CLI 3.4.2. Installing Red Hat OpenShift AI components by using the web console 3.4.3. Updating the installation status of Red Hat OpenShift AI components by using the web console 3.4.4. Viewing installed OpenShift AI components CHAPTER 4. CONFIGURING PIPELINES WITH YOUR OWN ARGO WORKFLOWS INSTANCE CHAPTER 5. INSTALLING THE DISTRIBUTED WORKLOADS COMPONENTS CHAPTER 6. INSTALLING THE SINGLE-MODEL SERVING PLATFORM 6.1. ABOUT THE SINGLE-MODEL SERVING PLATFORM 6.2. CONFIGURING AUTOMATED INSTALLATION OF KSERVE 6.3. MANUALLY INSTALLING KSERVE 6.3.1. Installing KServe dependencies 6.3.2. Creating an OpenShift Service Mesh instance 6.3.3. Creating a Knative Serving instance 6.3.4. Creating secure gateways for Knative Serving 6.3.5. Installing KServe 6.3.6. Configuring persistent volume claims (PVC) on KServe 6.3.7. Disabling KServe dependencies 6.4. ADDING AN AUTHORIZATION PROVIDER FOR THE SINGLE-MODEL SERVING PLATFORM 6.4.1. Manually adding an authorization provider 6.4.2. Installing the Red Hat Authorino Operator 6.4.3. Creating an Authorino instance 6.4.4. Configuring an OpenShift Service Mesh instance to use Authorino 6.4.5. Configuring authorization for KServe CHAPTER 7. INSTALLING THE MULTI-MODEL SERVING PLATFORM CHAPTER 8. ACCESSING THE DASHBOARD CHAPTER 9. ENABLING ACCELERATORS CHAPTER 10. WORKING WITH CERTIFICATES 10.1. UNDERSTANDING HOW OPENSHIFT AI HANDLES CERTIFICATES 10.2. ADDING CERTIFICATES 10.3. ADDING CERTIFICATES TO A CLUSTER-WIDE CA BUNDLE 10.4. ADDING CERTIFICATES TO A CUSTOM CA BUNDLE 10.5. USING SELF-SIGNED CERTIFICATES WITH OPENSHIFT AI COMPONENTS 10.5.1. Accessing S3-compatible object storage with self-signed certificates 10.5.2. Configuring a certificate for data science pipelines 4 5 7 9 9 12 14 15 17 19 19 22 26 28 30 32 35 35 35 41 41 41 43 47 51 52 53 54 54 55 55 57 59 62 63 64 66 66 67 68 69 70 70 71 Table of Contents

Table of Contents

PREFACE Learn how to use both the OpenShift CLI ( oc ) and web console to install Red Hat OpenShift AI Self- Managed on your OpenShift cluster. To uninstall the product, learn how to use the recommended command-line interface (CLI) method.

NOTE

Red Hat does not support installing more than one instance of OpenShift AI on your cluster. Red Hat does not support installing the Red Hat OpenShift AI Operator on the same cluster as the Red Hat OpenShift AI Add-on. Red Hat OpenShift AI Self-Managed 2.25 Installing and uninstalling OpenShift AI Self-Managed

engineers can obtain tailored, accurate, and verifiable answers to complex queries based on their own datasets within a data science project. At the management layer: The Red Hat OpenShift AI Operator A meta-operator that deploys and maintains all components and sub-operators that are part of OpenShift AI. When you install the Red Hat OpenShift AI Operator in the OpenShift cluster using the predefined projects, the following new projects are created: The redhat-ods-operator project contains the Red Hat OpenShift AI Operator. The redhat-ods-applications project includes the dashboard and other required components of OpenShift AI. The rhods-notebooks project is where basic workbenches are deployed by default. You can specify custom projects if needed. You or your data scientists must also create additional projects for the applications that will use your machine learning models. Do not install independent software vendor (ISV) applications in namespaces associated with OpenShift AI. Red Hat OpenShift AI Self-Managed 2.25 Installing and uninstalling OpenShift AI Self-Managed

CHAPTER 2. UNDERSTANDING UPDATE CHANNELS You can use update channels to specify which Red Hat OpenShift AI minor version you intend to update your Operator to. Update channels also allow you to choose the timing and level of support your updates have through the fast , stable , stable-x.y eus-x.y , and alpha channel options. The subscription of an installed Operator specifies the update channel, which is used to track and receive updates for the Operator. You can change the update channel to start tracking and receiving updates from a newer channel. For more information about the release frequency and the lifecycle associated with each of the available update channels, see the Red Hat OpenShift AI Self-Managed Life Cycle Knowledgebase article. Chann el Support Releas e freque ncy Recommended environment fast One month of full support Every month Production environments with access to the latest product features. Select this streaming channel with automatic updates to avoid manually upgrading every month. stable Three months of full support Every three months Production environments with stability prioritized over new feature availability. Select this streaming channel with automatic updates to access the latest stable release and avoid manually upgrading. stable -x.y Seven months of full support Every three months Production environments with stability prioritized over new feature availability. Select numbered stable channels (such as stable-2.10 ) to plan and upgrade to the next stable release while keeping your deployment under full support. eus- x.y Seven months of full support followed by Extended Update Support for eleven months Every nine months Enterprise-grade environments that cannot upgrade within a seven month window. Select this streaming channel if you prioritize stability over new feature availability. CHAPTER 2. UNDERSTANDING UPDATE CHANNELS

CHAPTER 3. INSTALLING AND DEPLOYING OPENSHIFT AI Red Hat OpenShift AI is a platform for data scientists and developers of artificial intelligence (AI) applications. It provides a fully supported environment that lets you rapidly develop, train, test, and deploy machine learning models on-premises and/or in the public cloud. OpenShift AI is provided as a managed cloud service add-on for Red Hat OpenShift or as self-managed software that you can install on-premise or in the public cloud on OpenShift. For information about installing OpenShift AI as self-managed software on your OpenShift cluster in a disconnected environment, see Installing and uninstalling OpenShift AI Self-Managed in a disconnected environment. For information about installing OpenShift AI as a managed cloud service add-on, see Installing and uninstalling OpenShift AI Cloud Service. Installing OpenShift AI involves the following high-level tasks:

1. Confirm that your OpenShift cluster meets all requirements. See Requirements for OpenShift AI Self-Managed.
2. Install the Red Hat OpenShift AI Operator. See Installing the Red Hat OpenShift AI Operator.
3. Install OpenShift AI components. See Installing and managing Red Hat OpenShift AI components.
4. Configure user and administrator groups to provide user access to OpenShift AI. See Adding users to OpenShift AI user groups.
5. Access the OpenShift AI dashboard. See Accessing the OpenShift AI dashboard.
6. Optionally, configure and enable your accelerators in OpenShift AI to ensure that your data scientists can use compute-heavy workloads in their models. See Enabling accelerators. 3.1. REQUIREMENTS FOR OPENSHIFT AI SELF-MANAGED You must meet the following requirements before you can install Red Hat OpenShift AI on your Red Hat OpenShift cluster: Product subscriptions You must have a subscription for Red Hat OpenShift AI Self-Managed. If you want to install OpenShift AI Self-Managed in a Red Hat-managed cloud environment, you must have a subscription for one of the following platforms: Red Hat OpenShift Dedicated on Amazon Web Services (AWS) or Google Cloud Platform (GCP) Red Hat OpenShift Service on Amazon Web Services (ROSA classic) Red Hat OpenShift Service on Amazon Web Services with hosted control planes (ROSA HCP) Microsoft Azure Red Hat OpenShift Contact your Red Hat account manager to purchase new subscriptions. If you do not yet have an account manager, complete the form at https://www.redhat.com/en/contact to request one. CHAPTER 3. INSTALLING AND DEPLOYING OPENSHIFT AI

Cluster administrator access to your OpenShift cluster You must have an OpenShift cluster with cluster administrator access. Use an existing cluster, or create a cluster by following the steps in the relevant documentation: OpenShift Container Platform 4.16 or later: OpenShift Container Platform installation overview OpenShift Dedicated: Creating an OpenShift Dedicated cluster ROSA classic: Install ROSA classic clusters ROSA HCP: Install ROSA with HCP clusters Your cluster must have at least 2 worker nodes with at least 8 CPUs and 32 GiB RAM available for OpenShift AI to use when you install the Operator. To ensure that OpenShift AI is usable, additional cluster resources are required beyond the minimum requirements. To use OpenShift AI on single node OpenShift, the node has to have at least 32 CPUs and 128 GiB RAM. Your cluster is configured with a default storage class that can be dynamically provisioned. Confirm that a default storage class is configured by running the oc get storageclass command. If no storage classes are noted with (default) beside the name, follow the OpenShift Container Platform documentation to configure a default storage class: Changing the default storage class. For more information about dynamic provisioning, see Dynamic provisioning. Open Data Hub must not be installed on the cluster. For more information about managing the machines that make up an OpenShift cluster, see Overview of machine management. An identity provider configured for OpenShift Red Hat OpenShift AI uses the same authentication systems as Red Hat OpenShift Container Platform. See Understanding identity provider configuration for more information on configuring identity providers. Access to the cluster as a user with the cluster-admin role; the kubeadmin user is not allowed. To assign cluster-admin privileges to a user, follow the steps in the relevant OpenShift documentation: OpenShift Container Platform: Creating a cluster admin OpenShift Dedicated: Managing OpenShift Dedicated administrators ROSA: Creating a cluster administrator user for quick cluster access Internet access Along with Internet access, the following domains must be accessible during the installation of OpenShift AI Self-Managed: cdn.redhat.com subscription.rhn.redhat.com Red Hat OpenShift AI Self-Managed 2.25 Installing and uninstalling OpenShift AI Self-Managed

You have GPU-enabled nodes available on your cluster and you have installed the Node Feature Discovery Operator and NVIDIA GPU Operator. For more information, see Installing the Node Feature Discovery Operator and Enabling NVIDIA GPUs. You have access to storage for your model artifacts. You have met the KServe installation prerequisites. Access to object storage Components of OpenShift AI require or can use S3-compatible object storage such as AWS S3, MinIO, Ceph, or IBM Cloud Storage. An object store is a data storage mechanism that enables users to access their data either as an object or as a file. The S3 API is the recognized standard for HTTP-based access to object storage services. Object storage is required for the following components: Single- or multi-model serving platforms, to deploy stored models. See Deploying models on the single-model serving platform or Deploying a model by using the multi-model serving platform. Data science pipelines, to store artifacts, logs, and intermediate results. See Configuring a pipeline server and About pipeline logs. Object storage can be used by the following components: Workbenches, to access large datasets. See Adding a connection to your data science project. Distributed workloads, to pull input data from and push results to. See Running distributed data science workloads from data science pipelines. Code executed inside a pipeline. For example, to store the resulting model in object storage. See Overview of pipelines in Jupyterlab. 3.2. CONFIGURING CUSTOM NAMESPACES By default, OpenShift AI uses the following predefined namespaces: redhat-ods-operator contains the Red Hat OpenShift AI Operator redhat-ods-applications includes the dashboard and other required components of OpenShift AI rhods-notebooks is where basic workbenches are deployed by default If needed, you can define custom namespaces to use instead of the predefined ones before installing OpenShift AI. This flexibility supports environments with naming policies or conventions and allows cluster administrators to control where components such as workbenches are deployed. Namespaces created by OpenShift AI typically include openshift or redhat in their name. Do not rename these system namespaces because they are required for OpenShift AI to function properly. Prerequisites You have access to an OpenShift AI cluster with cluster administrator privileges. Red Hat OpenShift AI Self-Managed 2.25 Installing and uninstalling OpenShift AI Self-Managed

You have installed the OpenShift CLI ( oc ) as described in the appropriate documentation for your cluster: Installing the OpenShift CLI for OpenShift Container Platform Installing the OpenShift CLI for Red Hat OpenShift Service on AWS You have not yet installed the Red Hat OpenShift AI Operator. Procedure

1. In a terminal window, if you are not already logged in to your OpenShift cluster as a cluster administrator, log in to the OpenShift CLI ( oc ) as shown in the following example: oc login <openshift_cluster_url> -u <admin_username> -p
2. Optional: To configure a custom operator namespace: a. Create a namespace YAML file named operator-namespace.yaml. Defines the operator namespace. b. Create the namespace in your OpenShift cluster. $ oc create -f operator-namespace.yaml You see output similar to the following: namespace/ <operator-namespace> created c. When you install the Red Hat OpenShift AI Operator, use this namespace instead of redhat- ods-operator.
3. Optional: To configure a custom applications namespace: a. Create a namespace YAML file named applications-namespace.yaml. Defines the applications namespace. Adds the required label. apiVersion: v kind: Namespace metadata: name: <operator-namespace> 1 apiVersion: v kind: Namespace metadata: name: <applications-namespace> 1 labels: opendatahub.io/application-namespace: 'true' 2 CHAPTER 3. INSTALLING AND DEPLOYING OPENSHIFT AI

3.3.1. Installing the Red Hat OpenShift AI Operator by using the CLI

The following procedure shows how to use the OpenShift CLI ( oc ) to install the Red Hat OpenShift AI Operator on your OpenShift cluster. You must install the Operator before you can install OpenShift AI components on the cluster. Prerequisites You have a running OpenShift cluster, version 4.16 or greater, configured with a default storage class that can be dynamically provisioned. You have cluster administrator privileges for your OpenShift cluster. You have installed the OpenShift CLI ( oc ) as described in the appropriate documentation for your cluster: Installing the OpenShift CLI for OpenShift Container Platform Installing the OpenShift CLI for Red Hat OpenShift Service on AWS If you are using custom namespaces, you have created and labeled them as required.

NOTE

The example commands in this procedure use the predefined operator namespace. If you are using a custom operator namespace, replace redhat-ods- operator with your namespace. Procedure

1. Open a new terminal window.
2. Follow these steps to log in to your OpenShift cluster as a cluster administrator: a. In the upper-right corner of the OpenShift web console, click your user name and select Copy login command. b. After you have logged in, click Display token. c. Copy the Log in with this token command and paste it in your terminal. $ oc login --token= --server= <openshift_cluster_url>
3. Create a namespace for installation of the Operator by performing the following actions:

NOTE

If you have already created a custom namespace for the Operator, you can skip this step. a. Create a namespace YAML file named rhods-operator-namespace.yaml. apiVersion: v kind: Namespace metadata: CHAPTER 3. INSTALLING AND DEPLOYING OPENSHIFT AI

Defines the operator namespace. b. Create the namespace in your OpenShift cluster. $ oc create -f rhods-operator-namespace.yaml You see output similar to the following: namespace/redhat-ods-operator created

4. Create an operator group for installation of the Operator by performing the following actions: a. Create an OperatorGroup object custom resource (CR) file, for example, rhods-operator- group.yaml. Defines the operator namespace. b. Create the OperatorGroup object in your OpenShift cluster. $ oc create -f rhods-operator-group.yaml You see output similar to the following: operatorgroup.operators.coreos.com/rhods-operator created
5. Create a subscription for installation of the Operator by performing the following actions: a. Create a Subscription object CR file, for example, rhods-operator-subscription.yaml. Defines the operator namespace. name: redhat-ods-operator 1 apiVersion: operators.coreos.com/v kind: OperatorGroup metadata: name: rhods-operator namespace: redhat-ods-operator 1 apiVersion: operators.coreos.com/v1alpha kind: Subscription metadata: name: rhods-operator namespace: redhat-ods-operator 1 spec: name: rhods-operator channel: 2 source: redhat-operators sourceNamespace: openshift-marketplace startingCSV: rhods-operator.x.y.z 3 Red Hat OpenShift AI Self-Managed 2.25 Installing and uninstalling OpenShift AI Self-Managed