Installing OpenShift AI Operator
Follow this procedure to install OpenShift AI 3.x.
Create the namespace, operator group, and operator subscription. The
stable-3.xchannel tracks the latest 3.x release, 3.5.1 at the time of validation.apiVersion: v1 kind: Namespace metadata: name: redhat-ods-operator --- apiVersion: operators.coreos.com/v1 kind: OperatorGroup metadata: name: rhods-operator namespace: redhat-ods-operator spec: {} --- apiVersion: operators.coreos.com/v1alpha1 kind: Subscription metadata: name: rhods-operator namespace: redhat-ods-operator spec: channel: stable-3.x name: rhods-operator source: redhat-operators sourceNamespace: openshift-marketplace installPlanApproval: Automatic
Check which channels your catalog offers before you commit to one:
oc get packagemanifest rhods-operator -n openshift-marketplace \ -o jsonpath='{range .status.channels[*]}{.name}{"="}{.currentCSVDesc.version}{"\n"}{end}'
Channel
Use for
stable-3.xLatest 3.x release. The default channel and the recommended choice for new installations.
stable-3.5Pins to one minor release so upgrades do not move you across minor versions.
eus-3.5Extended Update Support for that minor release.
betaPre-release builds. Not for production.
Important
Always name a
3.xor3.ychannel explicitly. The unsuffixedstable,fast, andalphachannels still track an older release train, so subscribing to them installs a release that this chapter does not describe.Verify that the operator is installed.
oc get csv -n redhat-ods-operator oc get pods -n redhat-ods-operator
Confirm that
DSCInitializationreconciled. The operator createsdefault-dsciautomatically and it reachesReadywithout any input.oc get dsci
NAME AGE PHASE CREATED AT default-dsci 71s Ready 2026-09-24T11:30:18Z
The resource uses
dscinitialization.opendatahub.io/v2, whose spec has onlyapplicationsNamespace,monitoring,trustedCABundle, anddevFlags. There is no service mesh configuration to supply. Customize it only if you need to change the applications namespace or monitoring:apiVersion: dscinitialization.opendatahub.io/v2 kind: DSCInitialization metadata: name: default-dsci spec: applicationsNamespace: redhat-ods-applications monitoring: managementState: Managed namespace: redhat-ods-monitoring trustedCABundle: managementState: Managed
Create the
DataScienceClusterresource to enable the required RHOAI components. This example enables the minimum needed for GPU-accelerated model serving and notebooks.apiVersion: datasciencecluster.opendatahub.io/v2 kind: DataScienceCluster metadata: name: default-dsc spec: components: dashboard: managementState: Managed kserve: managementState: Managed workbenches: managementState: Managed workbenchNamespace: rhods-notebooks aipipelines: managementState: Removed feastoperator: managementState: Removed kueue: managementState: Removed llamastackoperator: managementState: Removed mlflowoperator: managementState: Removed modelregistry: managementState: Removed ogx: managementState: Removed ray: managementState: Removed sparkoperator: managementState: Removed trainer: managementState: Removed trainingoperator: managementState: Removed trustyai: managementState: Removed
List the full set of components your release supports with:
oc get crd datascienceclusters.datasciencecluster.opendatahub.io -o json | \ jq -r '.spec.versions[]|select(.name=="v2")|.schema.openAPIV3Schema.properties.spec.properties.components.properties|keys[]'
Note
The
kservecomponent takes noservingstanza, because KServe runs inRawDeploymentmode. Its fields coverRawDeploymentbehavior, the OAuth proxy sidecar, model caching, and theLLMInferenceServicefeature flags.To enable queue-based scheduling, install the Red Hat build of Kueue Operator and set
kueue.managementState: Unmanagedso that the Kueue Operator owns the Kueue installation. Then setrayandtrainingoperatortoManagedas needed.Apply the manifest and wait for the cluster to become ready.
oc apply -f dsc.yaml oc wait --for=condition=Ready datasciencecluster/default-dsc --timeout=900s
Verify the deployed components.
oc get dsc oc get pods -n redhat-ods-applications
Review the per-component conditions if the cluster does not reach
Ready:oc get dsc default-dsc -o json | jq -r '.status.conditions[] | "\(.type)=\(.status) \(.reason): \(.message)"'
Conditions reporting
reason: Removedare expected for the components you disabled. Conditions such asKserveLLMInferenceServiceDependencies=False PreConditionFailed: Red Hat Connectivity Link not installedare informational and do not blockReady; they only matter if you intend to use distributed inference with llm-d.Find the dashboard URL. The dashboard is published through a Gateway API
Gateway.oc get gateway -n openshift-ingress oc get route data-science-gateway -n openshift-ingress -o jsonpath='{.spec.host}{"\n"}'
The dashboard is served at
https://rh-ai.apps.<cluster-domain>, which is the host on thedata-science-gatewayroute inopenshift-ingress. Two further routes,rhods-dashboardand a seconddata-science-gateway, exist inredhat-ods-applicationsand redirect to that host, so older bookmarks keep working.