Machine Learning Designer allows you to connect the Update EAS Service (Beta) component as a downstream node to a model component for online model service updates. Machine Learning Designer also allows you to submit a pipeline to DataWorks for periodic scheduling. This way, model services can be periodically updated.
Prerequisites
A model generated by Machine Learning Designer is deployed to Elastic Algorithm Service (EAS) as an online model service and runs as expected. For more information, see Deploy a model as an online service.
Procedure
Drag the Update EAS Service (Beta) component to the canvas and connect this component as a downstream node to a model component. Make sure that the model output port of the upstream component is directly connected to the input port of the Update EAS Service (Beta) component.
The input port of the Update EAS Service (Beta) component can be connected to the path of a model that is stored in an Object Storage Service (OSS) bucket. For example, you can use Predictive Model Markup Language (PMML) models generated by machine learning algorithms or models generated by vision, text processing, and XGBoost training algorithms.
Click the Update EAS Service (Beta) component. In the panel that appears, configure the parameters on the Parameters Settings tab.
EAS Service Name: the name of the deployed EAS service. The service is in the Running state.
EAS service description json: the JSON file that describes the service. In most cases, this parameter is left empty. If you want to add settings for this parameter, enter the settings in the code editor. For more information, see Run commands to use the EASCMD client.
Right-click the Update EAS Service (Beta) component and select Run Current Node. After the node is successfully run, an online model service is created.
Update the online model service on a regular basis by using DataWorks.
If you want to periodically update the online model services, submit the preceding pipeline to DataWorks for periodic scheduling. For more information, see Use DataWorks tasks to schedule pipelines in Machine Learning Designer.
References
You can go to the Elastic Algorithm Service (EAS) page to view the statuses of the deployed model services or manage the model services. For more information, see Manage EAS services.