@Marvin what are best practices, if any, for using run_deployment to kick off subflows from within a flow

Here are some best practices for using

run_deployment

to kick off subflows from within a flow: 1.

run_deployment

is used to run a pre-existing deployment as a subflow of the calling flow. This is effectively the same as calling the flow object itself in a parent flow with something like

asyncio.gather

. The big difference is that when you use

run_deployment

, the subflows will run according to the infrastructure associated with that deployment, whereas when you call the

subflow()

object itself, it will necessarily run on the calling (parent) flow’s infrastructure as a process. [^1^] 2. You can run multiple flows from deployments concurrently with no issues. Here's an example code snippet:

python
from prefect.deployments import run_deployment

for _ in range(1, 100):
    run_deployment(name="flow/deployment", timeout=0)

This is a workaround, and it's recommended to try this for now. [^2^] Please note that these are excerpts from discussions and may not represent the official documentation. Always refer to the official Prefect documentation for the most accurate and up-to-date information. [^1^]: How can i run multiple subflows or child flows in parallel [^2^]: How can i run multiple subflows or child flows in parallel