Where are auto-generated environments and scoring scripts for endpoints located?

Hi @Brad,

Thank you for reaching out to Microsoft Q&A forum!

To generate the scoring script and environment for a manually trained model. The scoring script is a Python file (.py) that contains the logic about how to run the model and read the input data submitted by the batch deployment executor. Each model deployment provides the scoring script (allow with any other dependency required) at creation time. It is usually indicated as follows:

deployment = ModelBatchDeployment(
    ...
    code_configuration=CodeConfiguration(
        code="src",
        scoring_script="batch_driver.py"
    ),
    ...
)

AZUREML_MODEL_DIR is an environment variable created during deployment.

Place your model in a global variable. Use global variables to make available any asset needed to perform inference to your scoring function.

For more details, see this documentation.

I hope you understand. Thank you!

Hi @santoshkc and thanks for the reply!

I'm sorry, I was unclear - I was referring to when you go through the wizard for deploying either a real-time or batch inference endpoint, you have the option for having the environment and scoring script 'auto-generated' instead of manually creating it yourself. Do you know how we can access that auto-generated scoring script and environment?

Hi @Brad, Following up to see if the above response was helpful. Thank you.