Not necessarily on the same branch, no

I don't think there's a PR issue for that yet, at least I haven't created one.

I could have a look at this and maybe make a PR.
Not sure what would the recommended flow be like though 🤔

Or if it wasn't clear, that chunk of code is from clearml's dataset.py

Holy crap this was a light-bulb moment, is this listed somewhere in the docs?
It solves so much of my issues xD

More experiments @<1537605940121964544:profile|EnthusiasticShrimp49> - the core issue with the create_function_step seems to be that the chosen executable will be e.g. IPython or some notebook, and not e.g. python3.10 , so it fails running it as a task… 🤔

~ is a bit weird since it's not part of the package (might as well let the user go through clearml-init ), but using ${PWD} works! 👍 👍

(Though I still had to add the CLEARML_API_HOST and CLEARML_WEB_HOST ofc, or define them in the clearml.conf)

I can indeed.

I mean, if I search for "model", will it automatically search for tasks containing "model" in their name?

Setting the endpoint will not be the only thing missing though, so unfortunately that's insufficient 😞

Bump?

I know the ClearML enterprise offers a vault.
If these are static-ish, you can set them directly in the agent's config file.
If not, what we did was that before executing remotely, we uploaded environment variables of interest as parameters, and then loaded them in the remote task.
These can then be overwritten with *** after loading them.

For the former (static-ish environment variables), just add:

environment {
  VAR1: value1
  VAR2: value2
}

to the agent’s clearml.conf

Yes. Though again, just highlighting the naming of foo-mod is arbitrary. The actual module simply has a folder structured with an implicit namespace:

foo/
  mod/
    __init__.py
    # stuff

FWIW, for the time being I’m just setting the packages to all the packages the pipeline tasks sees with:

    packages = get_installed_pkgs_detail()
    packages = [f"{name}=={version}" if version else name for name, version in packages.values()]
    packages = task.data.script.require...

I think this is about maybe the credential.helper used

I mean, it makes sense to have it in a time-series plot when one is logging iterations and such. But that's not always the case... Anyway I opened an issue about that too! 🙂

Not sure if ClearML has any built in support, but we used the above for a similar issue but with Prefect2 :)

some absolute path, i.e. /data/clearml

And last but not least, for dictionary for example, it would be really cool if one could do:
my_config = task.connect_configuration(my_config, name=name) my_other_config = task.connect_configuration(my_other_config, name=other_name) my_other_config['bar'] = my_config # Creates the link automatically between the dictionaries

Thanks David! I appreciate that, it would be very nice to have a consistent pattern in this!

Yes

I just used this to create the dual_gpu queue:
clearml-agent daemon --queue dual_gpu --create-queue --gpus 0,1 --detached

Last but not least - can I cancel the offline zip creation if I'm not interested in it 🤔
EDIT: I see not, guess one has to patch ZipFile ...

Yup, latest version of ClearML SDK, and we're deployed on AWS using K8s helm

Hah. Now it worked.

No it doesn't, the agent has its own clearml.conf file.

I'm not too familiar with clearml on docker, but I do remember there are config options to pass some environment variables to docker.
You can then set your environment variables in any way you'd like before the container starts

Aw you deleted your response fast CostlyOstrich36 xD

Indeed it does not appear in ps aux so I cannot simply kill it (or at least, find it).
I was wondering if it's maybe just a zombie in the server API or similar

Then I wonder:

• How to achieve this? The pipeline controller seems to only work with functions, not classes, so running smaller steps remotely seems more difficult then I imagined. I was already prepared to upload artifacts myself etc, but now I’m not sure?
• Do I really need to recreate the pipeline everytime from scratch? Or can I remove/edit steps? It’s mostly used as a… controller for notebook-based executions and experimentations, before the actual pipeline is known. That is, it will ...

It does, but I don't want to guess the json structure (what if ClearML changes it or the folder structure it uses for offline execution?). If I do this, I'm planning a test that's reliant on ClearML implementation of offline mode, which is tangent to the unit test

I guess following the example https://github.com/allegroai/clearml/blob/master/examples/advanced/execute_remotely_example.py , it's not clear to me how the server has access to the data loaders location when it hits execute_remotely

Sure, for example when reporting HTML files: