You can use Machine Learning Designer of Platform for AI (PAI) to train a model and deploy the trained model as an online service in Elastic Algorithm Service (EAS). This topic describes how to deploy a model service by using Machine Learning Designer.
Algorithms that can be deployed to EAS
For information about the algorithms that can be deployed to EAS by using Machine Learning Designer, see Deploy a model as an online service.
Deploy a model service
You can also use CLIs to deploy models trained by using Machine Learning Designer as online services. For example, you can use EASCMD or Data Science Workshop (DSW) to deploy models. For more information, see Deploy model services by using EASCMD or DSW.
Log on to the PAI console and go to the details page of the pipeline that you created in Machine Learning Designer.
In this topic, the Heart Disease Prediction pipeline is used as an example. For more information about how to create a pipeline and go to the configuration tab of the pipeline, see Predict heart disease.
After you run the pipeline, click Models in the upper part of the canvas.
In the Models dialog box, select the model that you want to deploy and click Deploy in EAS.
On the Create Service page, the Model File and Processor Type parameters are automatically configured. You can follow the on-screen instructions to configure other parameters based on your requirements. For more information, see Model service deployment by using the PAI console and Machine Learning Designer.
Click Deploy. The deployment requires several seconds to complete. When the Service Status changes to Running, the service is deployed.
Reference
You can use online debugging to test whether the service runs as expected. For more information, see Debug a service online.
EAS provides multiple methods that you can use to deploy model services based on your business requirements. For more information, see Overview.