After you deploy an AI service, you can manage the deployment by updating details, scaling, or deleting the deployment from the user interface or programmatically.
Managing AI services deployment from the user interface
You can access, update, scale, delete your AI service asset from the user interface of your deployment space.
Accessing details for AI service deployments
You can access details about your AI services deployment, such as deployment ID, software specification, associated asset, and more from the deployment details page.
Updating details for AI service deployments
You can update the details for your AI services deployment, such as name, serving name, description, and hardware specifications. For more information, see Updating a deployment.
Scaling AI service deployments
You can scale your AI services deployment by increasing the number of copies that are created for your deployment. For more information, see Scaling a deployment.
Deleting AI service deployments
You can delete your AI services deployment when you don't require it to free up the resources. For more information, see Deleting a deployment.
Managing AI service deployments with watsonx.ai Python client library
You can access, update, revise or delete your AI services deployment by using the watsonx.ai Python client library.
Accessing AI service deployment
To get the ID of your stored AI service, use the get_ai_service_id function. For more information, see watsonx.ai Python client library documentation.
To access the metadata about your AI service deployment, use the get_ai_service_details function. For more information, see watsonx.ai Python client library documentation.
Updating AI service deployment
To update the details of your AI service deployment, use the update_ai_service function. For more information, see watsonx.ai Python client library documentation.
Revising AI service deployment
To create a new AI service revision by using the watsonx.ai Python client library, use the create_ai_service_revision function. For more information, see watsonx.ai Python client library documentation.
To get a list of all revisions of your AI service in a table format, use the list_ai_service_revisions function. For more information, see watsonx.ai Python client library documentation.
Deleting AI service deployment
Use the delete function to delete an AI service deployment by using the watsonx.ai Python client library. For more information, see watsonx.ai Python client library documentation.
Managing AI service deployments with REST API
You can access, update, manage or delete your AI services deployment by using the watsonx.ai REST API.
Retrieving AI service deployment
You can retrieve the AI services in a specified project or deployment space by sending a GET request to the /ml/v4/ai_services endpoint. For more information, see watsonx.ai REST API documentation for AI services.
To retrieve an AI service with a specific idenfier, send a GET request to the /ml/v4/ai_services/{id} endpoint and provide a project or space ID. For more information, see watsonx.ai REST API documentation for AI services.
Updating AI service deployment
To update the AI service with the provided data, use the PATCH operation with the /ml/v4/ai_services/{id} endpoint. For more information, see watsonx.ai REST API documentation for AI services.
Delete AI service deployment
To update the AI service with the provided data, send a DELETE request to the /ml/v4/ai_services/{id} endpoint. For more information, see watsonx.ai REST API documentation for AI services.
Revising AI service deployment
To create a new revision of an AI service, send a POST request to the /ml/v4/ai_services/{id}/revisions endpoint. For more information, see watsonx.ai REST API documentation for AI services.
To retrieve the AI service revisions, send a GET request to the revisions endpoint /ml/v4/ai_services/{id}/revisions. For more information, see watsonx.ai REST API documentation for AI services.
Parent topic: Deploying AI services