Uploaded image for project: 'Red Hat Internal Developer Platform'
  1. Red Hat Internal Developer Platform
  2. RHIDP-10560

get ODH Model Registry deploy and reconciliation with KServe inference services working again

    • Icon: Task Task
    • Resolution: Done
    • Icon: Undefined Undefined
    • None
    • None
    • model-registry-bridge
    • None
    • 2
    • False
    • Hide

      None

      Show
      None
    • False
    • RHDHPAI Sprint 3270

      Task Description (Required)

      back with RHDHPAI-64 in Dec 2024 after about 3 or so days of prolonged collaboration on slack, after about 8 separate patches we got enough linkage between kubeflow model registry and k8s kserve resources on a OCP cluster that the 'bac' CLI could be used to build catalog-info.yaml files with proscribed RHDH AI Model Catalog settings that included the actual route URLs to the running model.

      That catalog-info.yaml file could then be checked into github and imported into RHDH.

      However, the RHOAI / ODH / Kubeflow space is rapidly evolving and changing.  Initial attempts to use the December recipe did not work.

      This task will capture our re-engagement with RHOAI to get a working recipe again.

      Current collaboration occurring in slack thread https://redhat-internal.slack.com/archives/C05QB0A582E/p1738858370777909 

              gmontero@redhat.com Gabe Montero
              gmontero@redhat.com Gabe Montero
              RHIDP - AI
              Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

                Created:
                Updated:
                Resolved: