@Marvin To run a Prefect flow, does the flow always have to be in a subdirectory of the current directory? If so, why is that?

No, a Prefect flow does not have to be in a subdirectory of the current directory to run. The flow can be located in any directory, as long as you properly specify the path to the flow's entry point when deploying or running it. Prefect allows you to load flows from local directories or even from remote sources like GitHub. For example, you can specify the entry point of a flow using the

from_source

method, which allows you to define the source directory and the specific Python file and function where the flow is defined:

python
from pathlib import Path
from prefect import flow

@flow(log_prints=True)
def my_flow(name: str = "world"):
    print(f"Hello {name}! I'm a flow from a Python script!")

if __name__ == "__main__":
    my_flow.from_source(
        source=str(Path(__file__).parent),
        entrypoint="from_local_source.py:my_flow",
    ).deploy(
        name="my-deployment",
        parameters=dict(name="Marvin"),
        work_pool_name="local",
    )

This flexibility allows you to organize your codebase as you see fit, without being constrained to a specific directory structure. You can find more about this in the Prefect documentation.