• Icon: Story Story
    • Resolution: Done
    • Icon: Major Major
    • None
    • None
    • None
    • RHDHPAI Sprint 3266, RHDHPAI Sprint 3267

      Story (Required)

      As a Platform Engineer, there should be an easy way for me to quickly generate AI catalog resources, without needing to manually edit catalog files.

      Background (Required)

      As part of DEVAI-153, a way to quickly generate model catalog resources from a template will be provided. This issue will be focusing on provided a templated repository that contains:

      • A Backstage catalog-info.yaml, wit
      • Templated techdocs to communicate information about 1 to N models and model servers

       

      Any information that the user needs to provide to generate a model catalog should be parameterized. There should be no limits on the number of models or model servers that can be created from the template. 

       

      The templating should use a common format (e.g. go-templates) so that it’s easy for multiple tools (including, but not limited to Backstage software templates) to generate model catalogs from it

      Out of scope

      • Methods to generate AI catalogs from the template, this issue is strictly focusing on the templating.

      Approach (Required)

      • Create a templated repository based on the previously defined model catalog structure
      • Parameterize any values that users would need to input
      • Ensure 1 .. N models and model servers can be generated form the template

      Dependencies

      <Describes what this story depends on. Dependent Stories and EPICs should be linked to the story.>

      Acceptance Criteria (Required)

      • Templated model catalog created, providing a catalog-info.yaml and techdocs, based on the published catalog structure
      • The current model catalog reference examples should be generated from it, to validate its feasibility.

      Done Checklist

      Code is completed, reviewed, documented and checked in
      Unit and integration test automation have been delivered and running cleanly in continuous integration/staging/canary environment
      Continuous Delivery pipeline(s) is able to proceed with new code included
      Customer facing documentation, API docs, design docs etc. are produced/updated, reviewed and published
      Acceptance criteria are met
      If the Grafana dashboard is updated, ensure the corresponding SOP is updated as well

              Unassigned Unassigned
              johnmcollier John Collier
              RHIDP - AI
              Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

                Created:
                Updated:
                Resolved: