@Marvin with tags pattern

Here's an example of using tags in a Prefect flow with Python:

python
import time
from prefect import flow, task
from pydantic import BaseModel, Field

class Data(BaseModel):
    key: str
    value: dict = Field(default_factory=dict)

@task
def fetch_data_for_key(key: str) -> Data:
    """A task that simulates fetching data from some source"""
    return Data(key=key, value={"data": "some data"})

@task
def process_data(data: Data) -> Data:
    """A task that simulates processing data"""
    print(f"Processing {data!r} (I swear)")
    time.sleep(3)
    return data

@flow
def work_i_need_to_do_sometimes(keys: list[str]):
    """Work you might need to do ever so often"""
    
    raw_data_futures = fetch_data_for_key.map(keys)

    process_data.map(raw_data_futures)

if __name__ == "__main__":
    work_i_need_to_do_sometimes.serve(
        name="sporradic-deployment",
        parameters={"keys": ["foo", "bar", "baz"]},
    )

In this code example, tasks are set up to fetch and process data, and then those tasks are used inside a flow that serves as a sporadic deployment. This code does not explicitly show the use of tags, but if you were to incorporate tags, they might be used to categorize or organize tasks and flows, e.g., by adding a

tags

argument to your task or flow definitions. You can find the raw code example here: GitHub Gist - serve.py