• Icon: Epic Epic
    • Resolution: Done
    • Icon: Undefined Undefined
    • None
    • None
    • model-catalog
    • None
    • Model Catalog Schema
    • False
    • Hide

      None

      Show
      None
    • False
    • Done
    • RHDHPLAN-27 - RHDH AI Catalog - Model Registry Data Bridge
    • 0% To Do, 0% In Progress, 100% Done

      Epic Goal

      The AI catalog plugin will utilize a standardized format to aggregate model and model server metadata from various sources (e.g. from RHOAI Model Registry). It should be possible to then use the schema to generate model catalog entities for ingestion into the RHDH / Backstage catalog,  through the use of a generation library.

      We've previously defined a mapping of model/model server metadata to Backstage catalog entities (see https://docs.google.com/document/d/1ArB8w-TawZ_DuMbZoukk4inVsAgqHntB8yN2lttwjyo/edit), and this should form a good starting point for an implementation.

      Why is this important?

      • This will provide a consistent way to generate model catalog entities from a given list of metadata
      • The generator library will allow us to leave the catalog entity generation to the backend RHDH plugin, without needing the normalizer services to do so

      Scenarios

      1. Model Catalog Schema Definition: Define a schema that can be used to generate model catalogs
      2. Generator Library: Catalog Generator library for generating model catalog entities 

      Acceptance Criteria (Mandatory)

      • CI - MUST be running successfully with tests automated
      • Release Technical Enablement - Provide necessary release enablement details and documents.
      • ...

      Dependencies (internal and external)

      1. ...

      Previous Work (Optional):

      1.  

      Open questions::

      •  

      Done Checklist

      • Acceptance criteria are met
      • Non-functional properties of the Feature have been validated (such as performance, resource, UX, security or privacy aspects)
      • User Journey automation is delivered
      • Support and SRE teams are provided with enough skills to support the feature in production environment

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

                Created:
                Updated:
                Resolved: