Story (Required)

As a PE, I can point the model catalog plugin to a remote server to ingest models/model servers on startup.

_As an AI developer, I can access models and model servers that have been ingested into RHDH from RHOAI MR
_

Background (Required)

As part of the initial investigation into catalog extensions in Backstage (RHDHPAI-505 and RHDHPAI-506), we found that using both entity providers and custom processors will allow for the most flexible range of operations needed on the catalog. 

The model catalog entity provider will allow for the model catalog plugin to ingest model catalog entities upon initial startup. It will also allow for model catalog entities to be deleted from the catalog, and for new locations to be discovered and added to the catalog.

In addition, provide an example dynamic plugins.yaml that can be used to load the plugin (and entity provider) into an RHDH instance

Out of scope

• The bridge service that the plugins will communicate with (RHDHPAI-606). Use the current WIP bridge provided by gmontero@redhat.com (https://github.com/gabemontero/rhdh-ai-catalog-cli/tree/http-endpoint-for-import/assets/bridge)

Approach (Required)

The current prototype implementation (https://github.com/redhat-ai-dev/rhdh-plugins/tree/main/workspaces/rhdh-ai) provides a good starting point.

Dependencies

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

Acceptance Criteria (Required)

<Describe edge cases to consider when implementing the story and defining tests>

<Provides a required and minimum list of acceptance tests for this story. More is expected as the engineer implements this story>

documentation updates (design docs, release notes etc)
demo needed
SOP required
education module update (Filled by RHDHPAI team only)
R&D label required (Filled by RHDHPAI team only)

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