@Marvin is it possible to get the Deployment object that was created through the CLI process?

Yes, it is possible to get the Deployment object that was created through the CLI process. You can load the settings from an existing deployment using the following code:

deployment = Deployment( name="a-name-you-used", flow_name="name-of-flow" ) 
deployment.load() # loads server-side settings

Once the existing deployment settings are loaded, you may update them as needed by changing deployment properties. You can view all of the parameters for the Deployment object in the Python API documentation. Please note that the infrastructure type of your Prefect deployment describes how you want Prefect agents to run flows for the deployment. For example, with DockerContainer infrastructure, the agent will try to use Docker to spin up a new container for each flow run. If you are starting your own container on ACI, you don't need Prefect to do it for you. Specifying process infrastructure on the deployment tells Prefect you want the agent to run flows by starting a process in your ACI container. You can use any storage type as long as you've configured it correctly. For more details, you can refer to the Prefect documentation.

@Marvin I wanted to view the Deployment object for a flow I deployed using the CLI because I was curious what the

storage

attribute would look like. I'm surprised to see it is

None

when I configured a git clone pull in the

prefect.yaml

on deployment. How does the cloning configuration get related to the Deployment object if not through

storage

?

The

storage

attribute of the Deployment object in Prefect does not directly relate to the git clone pull configured in the

prefect.yaml

file. Instead, the

storage

attribute is used for specifying where your flow's code is stored, such as Docker, S3, GCS, etc. The git clone pull configured in the

prefect.yaml

file is part of the deployment process, which is separate from the flow's storage configuration. When you run

prefect deploy

, the git clone pull is executed as part of the build process, which prepares your flow for deployment by pulling the latest code from your git repository. After the build process, the

push_to_s3

step is executed, which pushes your built flow to the specified S3 bucket. This is where the

storage

attribute comes into play - it tells Prefect where to retrieve your flow's code when it needs to run the flow. In summary, the git clone pull and the

storage

attribute serve different purposes. The git clone pull is part of the build process, which prepares your flow for deployment, while the

storage

attribute tells Prefect where to retrieve your flow's code when it needs to run the flow.

@Marvin what would I need to provide to the

storage

attribute of a Deployment so that it will retrieve the flow code from Github at runtime?

To retrieve the flow code from Github at runtime, you would need to use a custom storage class that supports Github. Prefect does not currently provide a built-in Github storage class, but you can create your own by extending the

Storage

base class. Here is a simple example of what a custom Github storage class might look like:

from prefect import Storage

class GithubStorage(Storage):
    def __init__(self, repo: str, path: str):
        self.repo = repo
        self.path = path

    def get_flow(self, flow_location: str) -> "Flow":
        # Implement logic to retrieve and return flow from Github

You would then use this custom storage class when creating your flow:

flow = Flow('my-flow', storage=GithubStorage(repo='my-repo', path='path/to/flow.py'))

Please note that this is a simplified example and the actual implementation would need to handle authentication with Github and retrieving the flow code from the specified repository and path. Alternatively, you can store your code in an AWS S3 bucket, Azure Blob Storage container, or GCP GCS bucket and specify the destination directly in the push and pull steps of your

prefect.yaml

file. For more details, you can refer to the Prefect documentation.