@Marvin when using .map vs. .submit how do I pass arguments to the task ?

You can use the

.map

and

.submit

methods in Prefect to pass arguments to tasks. Here’s how you can do it: Using `.map`: The

.map

function automatically creates a task run for each element of its inputs. Here are some code examples:

from prefect import flow, task

@task
def print_nums(nums):
    for n in nums:
        print(n)

@task
def square_num(num):
    return num**2

@flow
def map_flow(nums):
    print_nums(nums)
    squared_nums = square_num.map(nums)
    print_nums(squared_nums)

map_flow([1, 2, 3, 5, 8, 13])

You can also pass static values that don't get mapped:

from prefect import flow, task

@task
def add_together(x, y):
    return x + y

@flow
def sum_it(numbers, static_value):
    futures = add_together.map(numbers, static_value)
    return futures

sum_it([1, 2, 3], 5)

Using `.submit`: The

.submit

method is used to run a task asynchronously and doesn't block the flow. Here’s how you can do it:

from prefect import flow, task
import time

@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()

For more details: - Documentation on Map: https://docs.prefect.io/latest/concepts/tasks/ - Additional Examples: https://raw.githubusercontent.com/zzstoatzz/prefect-code-examples/main/examples/tasks/submitting.py https://raw.githubusercontent.com/zzstoatzz/prefect-code-examples/main/examples/tasks/basic.py

@Marvin the task I am calling .map on accepts multiple arguments such as x, y, z. When I call the task how can I pass the arguments x, y, z using .map

When using

.map

to call tasks that accept multiple arguments, you can pass those arguments as lists. You can also use the

unmapped

function to handle static values. Here’s how you can do it: Example with multiple dynamic arguments:

from prefect import flow, task

@task
def process_values(x, y, z):
    return x + y + z

@flow
def main_flow(x_vals, y_vals, z_vals):
    result = process_values.map(x=x_vals, y=y_vals, z=z_vals)
    return result

main_flow([1, 2, 3], [4, 5, 6], [7, 8, 9])

Example with static and dynamic arguments using `unmapped`:

from prefect import flow, task, unmapped

@task
def process_values(x, y, z):
    return x + y + z

@flow
def main_flow(x_vals, y_vals, static_z):
    result = process_values.map(x=x_vals, y=y_vals, z=unmapped(static_z))
    return result

main_flow([1, 2, 3], [4, 5, 6], 10)

In these examples, you can see how to pass both dynamic lists of values and static values by using

unmapped

. For further details, you can check the Prefect documentation on Tasks.