Deployment types
There are three types of Deployments: standard, external, and registration.
Standard Deployments
A model, along with an optional explainer and/or transformer, is deployed on Deeploy using one of the available deployment services (KServe, SageMaker, or Azure Machine Learning). Standard Deployments must be connected to a Repository and come with an endpoint, allowing communication with the model to retrieve predictions and explanations. All functionalities are available for Standard Deployments.
External Deployments
A model deployed on external infrastructure is accessed through an external endpoint. External Deployments can optionally be connected to a Repository. While an endpoint is available to retrieve predictions, some functionalities, specifically explanation requests and container logs, are not supported for external Deployments.
Registration Deployments
Serves as documentation for a model. Registration Deployments can optionally be connected to a Repository. Select functionalities are available for registration Deployments, including model and data cards, metadata, and compliance documentation.
Available features per type
The following table provides an overview of which features are available for each Deployment type:
| Standard | External | Registration | |
|---|---|---|---|
| Documentation | ✓ | ✓ | ✓ |
| Model & data card | ✓ | ✓ | ✓ |
| Metadata | ✓ | ✓ | ✓ |
| Events | ✓ | ✓ | ✓ |
| Predict endpoint | ✓ | ✓ | |
| Evaluations | ✓ | ✓ | |
| Actuals | ✓ | ✓ | |
| Monitoring | ✓ | ✓ | |
| Alerts | ✓ | ✓ | |
| Tokens | ✓ | ✓ | |
| Test | ✓ | ✓ | |
| Prediction logs | ✓ | ✓ | |
| Code snippets | ✓ | ✓ | |
| Explain endpoint | ✓ | ||
| Job schedules | ✓ | ||
| Checklists | ✓ |