Editing a Model Deployment
The options that can be edited (updated) depend on the
lifecycleState of the Data Science model deployment.
When the model deployment is in an Active state, you can change these option groups one at a time with zero downtime to a model deployment:
Name or description: Change the name or description.
Default configuration: Change or add custom environment variable keys and values.
Models: Change the compartment, project, or model.
Compute: Change the shape series, number of CPUs, or amount of memory for each CPU in gigabytes.
Logging: Change the logging configuration for access and predict logs.
Load Balancer or BYOC: Change the load balancing bandwidth or the bring your own container.
You can't edit all of the options at once when the model deployment resource is active.
When the model deployment is in an Inactive state, you can change all of the options at once.
- Use the Console to sign in to a tenancy with the necessary policies.
- Open the navigation menu and click Analytics & AI. Under Machine Learning, click Data Science.
Select the compartment that contains the project with the model deployments.
All projects in the compartment are listed.
Click the name of the project.
The project details page opens and lists the notebook sessions.
Under Resources, click Model deployments.
A tabular list of model deployments in the project is displayed.
- Click the name of the model deployment.
- Click Edit.
- Change the options one at a time by using Select, Change shape or Show advanced options. For a description of the fields, see creating a model deployment.
Each individual option change must be submitted before another option is changed using the same steps.
Use the oci data-science model-deployment update command and required parameters to edit (update) a model deployment:
oci data-science model-deployment update --model-deployment-id
For a complete list of flags and variable options for CLI commands, see the CLI Command Reference.
Use the UpdateModelDeployment operation to edit (update) a model deployment.