Retraining a model does not automatically update the online service that serves it. This guide shows you how to connect the Update EAS Service (Beta) component to your Machine Learning Designer pipeline and schedule it in DataWorks so that your Elastic Algorithm Service (EAS) model service is updated automatically on a recurring basis — without manual intervention.
In this guide, you will:
Connect the Update EAS Service (Beta) component to a model component in your pipeline
Configure the component parameters
Run the update once to verify it works
Submit the pipeline to DataWorks for periodic scheduling
Prerequisites
Before you begin, ensure that you have:
A model trained in Machine Learning Designer and deployed to EAS as an online model service in Running state. See Deploy a model as an online service
A DataWorks workspace with access to schedule pipeline tasks. See Use DataWorks tasks to schedule pipelines in Machine Learning Designer
Update the model service
Step 1: Connect the Update EAS Service (Beta) component
Drag the Update EAS Service (Beta) component onto the canvas.
Connect the model output port of your upstream model component directly to the input port of the Update EAS Service (Beta) component. The input port accepts models stored in an Object Storage Service (OSS) bucket. Supported model types include Predictive Model Markup Language (PMML) models from machine learning algorithms and models produced by vision, text processing, and XGBoost training algorithms.
Step 2: Configure the component parameters
Click the Update EAS Service (Beta) component to open its settings panel.
On the Parameters Settings tab, configure the following parameters.
Parameter Description EAS Service Name The name of the EAS service to update. The service must be in Running state. EAS service description json A JSON file describing the service configuration. Leave this blank in most cases. To add custom settings, enter them in the code editor. See Run commands to use the EASCMD client. 
Step 3: Run the update node
Right-click the Update EAS Service (Beta) component and select Run Current Node.
After the node runs successfully, an online model service is created.
Step 4: Schedule periodic updates with DataWorks
To keep the model service updated automatically, submit the pipeline to DataWorks for periodic scheduling. See Use DataWorks tasks to schedule pipelines in Machine Learning Designer.
What's next
View the status of your deployed model services or manage them from the EAS page. See Manage EAS services.