@Marvin I've checked

create_flow_run_from_deployment

function. I would like to schedule deployment with custom parameter. I know, from UI, I can do this with

Custom run

, but I couldn't understand how to achieve client function. https://github.com/PrefectHQ/prefect/blob/cb84f4af54be700d3ba433b90cb36c6da3d36290/src/prefect/client/orchestration.py#L559-L627

To schedule a deployment with custom parameters using the Prefect client function, you can provide the necessary parameters at the time of creation in the

parameters

argument of the

create_flow_run_from_deployment

function. Here's a link to the documentation that discusses setting parameters in deployments, which could be relevant for your client call as well: Default parameters and overriding parameters. For example, to set custom parameters from the

create_flow_run_from_deployment

, you can include them in the function call. Unfortunately, since Prefect 2.x is new, and I have no experience with it, I can't provide an updated code example directly related to

create_flow_run_from_deployment

. However, I do have a general code example that demonstrates task submission, but it doesn't directly answer your question:

python
import time
from prefect import flow, task

@task
def sleep(t: int):
    print(f"Going to sleep for {t} seconds...")
    time.sleep(t)
    print("...and I'm awake!")

@flow(log_prints=True)
def my_flow():
    sleep(3)  # block the flow for 3 seconds (not concurrently)

    future = sleep.submit(2)  # submit a task run to the task runner, doesn't block flow

    future.wait()  # block the flow until the submitted task run is complete

    sleep.map([5] * 10)  # submit 10 at once, each sleeps for 5 seconds, don't block

if __name__ == "__main__":
    my_flow()

Prefect submitting tasks example The actual function you would use to schedule a deployment with custom parameters likely looks something like this:

python
from prefect import create_flow_run_from_deployment

# Set your deployment ID and custom parameters
deployment_id = "your-deployment-id"
custom_parameters = {"param1": "value1", "param2": "value2"}

# Schedule the deployment with custom parameters
create_flow_run_from_deployment(
    deployment_id=deployment_id,
    parameters=custom_parameters
)

You will need to replace

"your-deployment-id"

with the actual ID of your deployment and define your custom parameters in the

custom_parameters

dictionary. Please note that you should adjust the function to match the exact syntax and parameters of Prefect 2.x, as I am extrapolating from my existing knowledge which is not up-to-date on the latest Prefect version. I recommend checking the latest Prefect 2.x documentation for detailed and accurate examples or use cases related to deployments in Prefect 2.x.

Thanks solved with this thread https://prefect-community.slack.com/archives/CL09KU1K7/p1715222337388529