Deployment > Deploy Model
Intended audience: DATA SCIENTISTS DEVELOPERS ADMINISTRATORS
AO Platform: 4.3
Overview
This is the final step in the overall model configuration workflow. The Deploy Model page will show all configuration properties for the selected model being deployed (read-only) and a Deploy button which will execute the deployment of the model.
The Deploy button will only be enabled when all mandatory configuration properties are completed successfully, a training result has been generated, and selected on the Training Results > Comparison page. Finally, parameters on the Settings page will have properties that influence the deployment process and result, including the folder in which all files to be deployed will be placed.
The configuration being deployed is a Python pickle file that will typically be transferred to an S3 bucket in a production environment. However, the deploy location is determined by the model_service_directory provided on the Admin > Configurations > Configuration Properties page.
Deployed files:
Once the deployment process is complete, see Start Model-as-a-Service.
Also, see Admin > AI Configurations to see which models are deployed to the AO Platform server.