In this tutorial, we will deploy ml model as a real-time managed endpoint in Azure ML Studio using GitHub Action.
- Azure Subscription ID & Tenant ID
- Azure service principles (Application Client ID & Secret)
- Azure Machine Learning Workspace
Azure Machine Learning Studio is a GUI-based integrated development environment for constructing and operationalizing Machine Learning workflow on Azure. It's a cloud service for accelerating and managing the machine learning project lifecycle. Please see this azure official documentation for more information.
- includes conda environment yaml file to install dependencies to run ml model
- includes trained model
- python file that contains the logic about how to run the model and read the input data. please see this for more information.
- includes model_deployment.yaml: yaml file for github action automation
- test input data to score by using model
- python dependency to run deployment script from your local or GitHub runner
- python file to deploy to azure machine learning studio
Kindly take a moment to review the comments in the files.
- Secrets for this tutorial.
- You can learn more about GitHub Action Secrets in this documentation.
....
# define an endpoint and deployment name
endpoint_name = <your endpoint name>
deployment_name = <your deployment name>
....
- Only manual trigger for main branch includes in this repo.
- You can learn more about Triggering GitHub Action Workflow in this documentation.