Installing Red Hat OpenShift AI

Several IBM® Software Hub services require Red Hat OpenShift AI. If you plan to install services that use Inference foundation models, you must install Red Hat OpenShift AI to start and serve the models.

Installation phase

Setting up a client workstation
Setting up a cluster
Collecting required information
Preparing to run installs in a restricted network
Preparing to run installs from a private container registry
Preparing the cluster for IBM Software Hub
Preparing to install an instance of IBM Software Hub
Installing an instance of IBM Software Hub
Setting up the control plane
Installing solutions and services

Who needs to complete this task?

Cluster administrator A cluster administrator must complete this task.

When do you need to complete this task?

One-time setup Complete this task if you plan to install one or more of the following services:

IBM Knowledge Catalog Premium
IBM Knowledge Catalog Standard
watsonx.ai™
watsonx Assistant (required to use optional GPU features)
watsonx Code Assistant™
watsonx Code Assistant for Red Hat Ansible® Lightspeed
watsonx Code Assistant for Z
watsonx Code Assistant for Z Code Explanation
watsonx™ Orchestrate

Important: If you are running Red Hat OpenShift on IBM Cloud, complete Installing Red Hat OpenShift AI on Red Hat OpenShift on IBM Cloud instead of completing this task.

About this task

The commands in this task install Red Hat OpenShift AI with the minimum components needed to support IBM Software Hub services.

Service	Red Hat OpenShift AI
IBM Knowledge Catalog Premium	✓
IBM Knowledge Catalog Standard	✓
watsonx.ai	✓
watsonx Assistant	Required to use optional GPU features.
watsonx Code Assistant	✓
watsonx Code Assistant for Red Hat Ansible Lightspeed	✓
watsonx Code Assistant for Z	✓
watsonx Code Assistant for Z Code Explanation	✓
watsonx Orchestrate	✓

Use the following table to determine which version of Red Hat OpenShift AI you need to install:

Release	Red Hat OpenShift AI
5.1.3 (April 2025)	Version 2.16
5.1.2 (March 2025)	Version 2.16
5.1.1 (February 2025)	Version 2.16
5.1.0 (December 2024)	Version 2.13

Procedure

Log in to Red Hat OpenShift Container Platform as a cluster administrator.
```
${OC_LOGIN}
```
Remember: OC_LOGIN is an alias for the oc login command.
Create the redhat-ods-operator project:
```
oc new-project redhat-ods-operator
```
The command returns the following response:
```
namespace/redhat-ods-operator created
```

Create the rhods-operator operator group in the redhat-ods-operator project:

cat <<EOF |oc apply -f -
apiVersion: operators.coreos.com/v1
kind: OperatorGroup
metadata:
  name: rhods-operator
  namespace: redhat-ods-operator
EOF

The command returns the following response:

operatorgroup.operators.coreos.com/rhods-operator created

Set the CHANNEL_VERSION environment variable based on the version of Red Hat OpenShift AI that you are installing:
Version 2.13
```
export CHANNEL_VERSION=stable-2.13
```
Version 2.16
```
export CHANNEL_VERSION=stable-2.16
```

Create the rhods-operator operator subscription in the redhat-ods-operator project:

cat <<EOF |oc apply -f -
apiVersion: operators.coreos.com/v1alpha1
kind: Subscription
metadata:
  name: rhods-operator
  namespace: redhat-ods-operator
spec:
  name: rhods-operator
  channel: ${CHANNEL_VERSION}
  source: redhat-operators
  sourceNamespace: openshift-marketplace
  config:
     env:
        - name: "DISABLE_DSC_CONFIG"
EOF

The command returns the following response:

subscription.operators.coreos.com/rhods-operator created

Check the status of the rhods-operator-* pod in the redhat-ods-operator project:

oc get pods -n redhat-ods-operator

Confirm that the pod is Running. The command returns a response with the following format:

NAME                              READY   STATUS    RESTARTS   AGE
rhods-operator-56c85d44c9-vtk74   1/1     Running   0          3h57m

Create a DSC Initialization (DSCInitialization) object named default-dsci in the redhat-ods-monitoring project:

cat <<EOF |oc apply -f -
apiVersion: dscinitialization.opendatahub.io/v1
kind: DSCInitialization
metadata:
  name: default-dsci
spec:
  applicationsNamespace: redhat-ods-applications
  monitoring:
    managementState: Managed
    namespace: redhat-ods-monitoring
  serviceMesh:
    managementState: Removed
  trustedCABundle:
    managementState: Managed
    customCABundle: ""
EOF

Check the phase of the DSC Initialization (DSCInitialization) object:
```
oc get dscinitialization
```
Confirm that the object is Ready. The command returns a response with the following format:
```
NAME           AGE     PHASE
default-dsci   4d18h   Ready
```

Create a Data Science Cluster (DataScienceCluster) object named default-dsc:

cat <<EOF |oc apply -f -
apiVersion: datasciencecluster.opendatahub.io/v1
kind: DataScienceCluster
metadata:
  name: default-dsc
spec:
  components:
    codeflare:
      managementState: Removed
    dashboard:
      managementState: Removed
    datasciencepipelines:
      managementState: Removed
    kserve:
      managementState: Managed
      defaultDeploymentMode: RawDeployment
      serving:
        managementState: Removed
        name: knative-serving
    kueue:
      managementState: Removed
    modelmeshserving:
      managementState: Removed
    ray:
      managementState: Removed
    trainingoperator:
      managementState: Managed
    trustyai:
      managementState: Removed
    workbenches:
      managementState: Removed
EOF

The Red Hat OpenShift AI Operator installs and manages the services that are listed as Managed. Services that are Removed are not installed.

Wait for the Data Science Cluster object to be Ready.
To check the status of the object, run:
```
oc get datasciencecluster default-dsc -o jsonpath='"{.status.phase}" {"\n"}'
```

Confirm that the status of the following pods in the redhat-ods-applications project are Running:

kserve-controller-manager-* pod
kubeflow-training-operator-* pod
odh-model-controller-* pod

oc get pods -n redhat-ods-applications

The command returns a response with the following format:

NAME                                         READY   STATUS      RESTARTS   AGE
kserve-controller-manager-57796d5b44-sh9n5   1/1     Running     0          4m57s
kubeflow-training-operator-7b99d5584c-rh5hb  1/1     Running     0          4m57s

Edit the inferenceservice-config configuration map in the redhat-ods-applications project:
1. Log in to the Red Hat OpenShift Container Platform web console as a cluster administrator.
2. From the navigation menu, select Workloads > Configmaps.
3. From the Project list, select redhat-ods-applications.
4. Click the inferenceservice-config resource. Then, open the YAML tab.
5. In the metadata.annotations section of the file, add opendatahub.io/managed: 'false':
```
metadata:
  annotations:
    internal.config.kubernetes.io/previousKinds: ConfigMap
    internal.config.kubernetes.io/previousNames: inferenceservice-config
    internal.config.kubernetes.io/previousNamespaces: opendatahub
    opendatahub.io/managed: 'false'
```
6. Find the following entry in the file:
```
"domainTemplate": "{{ .Name }}-{{ .Namespace }}.{{ .IngressDomain }}",
```
7. Update the value of the domainTemplate field to "example.com":
```
"domainTemplate": "example.com",
```
8. Click Save.

What to do next

Now that you've installed Red Hat OpenShift AI, you're ready to complete Installing and setting up Multicloud Object Gateway for IBM Software Hub.