@Marvin, Does prefect 3 still support

run_deployment

? How to import it?

In Prefect 3.x, the functionality provided by

run_deployment

does exist, allowing you to run deployments, but there are some compatibility issues and considerations. Here's what I found: 1. Documentation Insights: There isn't explicit documentation from the Prefect 3.x documents directly mentioning

run_deployment

, but related functionality seems to be supported in Prefect through other methods, such as using

serve()

for serving flows and converting flows to deployment objects using

to_deployment

. These methods support similar operations related to deployments. Documentation Link. 2. GitHub Issues: There are known issues related to using

run_deployment

across different versions of Prefect. A common problem is trying to use Prefect 3.x to run a deployment created with Prefect 2.x, which can lead to errors (e.g.,

TypeError: No constructor defined

). It's important to ensure that the deployment environment and client version are compatible. GitHub Issues. To use a similar functionality to trigger deployments in Prefect 3.x, you can look into using the

serve

and the flow conversion methods like

to_deployment

. This showcases how Prefect 3.x allows for serving and managing flows, potentially replacing direct calls to

run_deployment

. If you encounter compatibility issues, you may need to manage version consistency between your client and deployment server or explore alternative methods of triggering flows. Keep an eye on Prefect's updates for any changes in these functionalities.

That doesn't seem correct

run deployment is in the same spot

Thanks for the quick answer! I got an import error for the following:

from prefect.deployments.deployments import run_deployment

Switched to the following and it works 🙂

from prefect.deployments import run_deployment