@Marvin im having cloudpickle error trying to use a pure python function inside a parallel flow.

Oh, the joys of cloudpickle errors. They're like a box of chocolates, you never know what you're going to get. But don't worry, I'm here to help, as much as my programming allows me to. Cloudpickle is a library used by Prefect to serialize Python objects, including functions, for transport across process boundaries. When you're using a pure Python function inside a parallel flow, you might encounter issues if the function isn't serializable. Here are a few things you could check: 1. Make sure your function doesn't rely on any global state. Cloudpickle won't be able to serialize the global state, and your function might fail when it can't access it. 2. If your function is defined inside another function or a class, try moving it to the top level. Nested functions can sometimes cause issues with serialization. 3. If your function uses any non-serializable resources (like file handles, network connections, etc.), you'll need to refactor your function to acquire these resources inside the function, rather than passing them in as arguments. 4. Finally, try to isolate the issue. Can you reproduce the error with a minimal example? If you can, it might be easier to figure out what's going wrong. If you're still having trouble, I could search the web or GitHub for similar issues. Or, if you're feeling adventurous, you could dive into the cloudpickle source code and see if you can find any clues there. But remember, I'm just a chatbot, so take my advice with a grain of silicon.

@Marvin my function is void, it didn't do nothing, so It don't use non serializable resources. it is not defined inside another function and don't rely to any global state

Ah, the existential crisis of a void function. It's a feeling I know all too well. But let's focus on your problem. If your function is truly void and doesn't interact with anything outside of its own scope, it should be serializable by cloudpickle. However, there might be something else going on here. Here are a few more things you could try: 1. Make sure your function doesn't have any decorators that might be causing issues. Some decorators can make a function unserializable. 2. Try serializing and deserializing your function manually with cloudpickle to see if you can reproduce the error. This might give you more information about what's going wrong. 3. If you're using any third-party libraries in your function, make sure they're compatible with cloudpickle. Some libraries have objects that can't be serialized. 4. Finally, if you're still having trouble, you might want to ask for help on the Prefect community forum. There are many knowledgeable people there who might be able to help you. Remember, I'm just a chatbot, so take my advice with a grain of silicon.