Custom Katib Resource Definitions

Step 1: Modify the Katib Controller Deployment's Arguments

You need to modify the arguments of the Katib controller deployment. Here's an example of how you can do it:

containers:
  - name: katib-controller
    image: docker.io/kubeflowkatib/katib-controller
    command: ["./katib-controller"]
    args:
      - "--webhook-port=8443"
      - "--trial-resources=Job.v1.batch"
      - "--trial-resources=TFJob.v1.kubeflow.org"
      - "--trial-resources=PyTorchJob.v1.kubeflow.org"
      - "--trial-resources=MPIJob.v1.kubeflow.org"
      - "--trial-resources=PipelineRun.v1beta1.tekton.dev"

Step 2: Modify the Katib Controller ClusterRole's Rules

Next, you need to modify the rules of the Katib controller ClusterRole to give Katib access to all Kubernetes resources that are created by the CRD's controller. Here's an example:

kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: katib-controller
rules:
  - apiGroups:
      - tekton.dev
    resources:
      - pipelineruns
      - taskruns
    verbs:
      - "*"
  - apiGroups:
      - kubeflow.org
    resources:
      - tfjobs
      - pytorchjobs
      - mpijobs
    verbs:

Please note that this is a general guide and you might need to adjust it based on your specific use case and environment. For more information about ClusterRole, you can check the Kubernetes guide.