Model Registry

Record model versions, artifacts, signatures, evaluation evidence, and lifecycle stages before configuring serving.

Open Model Registry

Register a version

  1. Create a model with its type and owner team.
  2. Register a numeric version, framework, artifact URI, input and output signatures, and measured primary metric.
  3. Set the current version and lifecycle stage. A production-version reference must name a registered version.
  4. Inspect artifact access and runtime compatibility before using that version in a serving endpoint.

Metadata and executable models

Registering a framework or artifact URI records a model contract. Execution depends on the serving runtime’s supported format, artifact access, and tensor signature. The registry supports more framework labels than the built-in runtime can execute.

Upload an artifact using the model’s supported artifact control when appropriate. Verify the exact registered version and returned runtime readiness.

API endpoints

Use your Genorbex deployment’s origin followed by the path below. Replace IDs with resources accessible to your account. Authentication and permissions are checked by each endpoint.

GET /api/orbexdb/ai-ml/assets

Lists assets; use kind=MODEL for registered model metadata.

Authentication: Genorbex account token and service/resource access; API-key support follows the endpoint’s authentication guard.

Need help with your setup? Visit the Help Center or contact Genorbex.