Deploy procedure

This documentation is valid for:

Deploys a custom model, making it available to be used for prediction.

Parameters

in:&model :: Model, GeneXusAI.Custom
The model information to be deployed.
in:&provider :: Provider, GeneXusAI.Configuration
Provider settings.
inout:&Messages :: Messages, GeneXus.Common
A collection of warning and error messages returned by the task. You should check in your code if an error was returned. Refer to error codes and descriptions for more information.
out:&Success :: Boolean
Indicates the success of the operation.

The following table resumes the configuration properties (access credentials) you must set in order to use this AI task.

	PropertyKey
ProviderType	Key	Deploy
Alibaba	-	-
Amazon	-	-
Baidu	-	-
Google	Service Account JSON	-
IBM	-	-
Microsoft	Custom Vision Training Key	Custom Vision Training Resource Id
SAP	-	-
Tencent	-	-

Calling this task makes sense after you call the Train procedure and the Check procedure returns a State.Ready state.
Once you call this task successfully, you will be able to call Predict procedure or the appropriate task by adding ModelId and ModelVersion properties to &provider configuration.
Some providers implicitly deploy your model after training (e.g. IBM). In other words, you do not need to call this task for deploying your model. If you call this task in this scenario, the operation returns True and a GXAI1001 informative message.

Platforms	Web(.NET,.NETCore,Java), SmartDevices(Android,iOS)
Connectivity	Online

This procedure is available as of GeneXus 16 upgrade 6.