I have a little bit of code that goes like: import argparse from clearml import Task from DeployKit.argument_parser import get_parser import KitUtils if __na...

is there a way to get a Task's docker container id/name? I'm generally interested in resource profiling of each container, so I noticed I can use docker stat...

is there a way to copy the entire folder an agent in a machine (different from server machine) builds to the server machine?

Is there a way to deploy a ClearML server with a preconfigured user + its credentials?

how can i disable agent pip caching? sometimes the agents load an earlier version of one of my libraries. i'm running them in docker mode

is there a way to tell an experiment not to use caches? from the python API specifically. something like task.use_caches = False ? I don't want it to use any...

Can I change the clearml-serving inference port? 8080 is already used for my self-hosted server.. I guess I can just change it in the docker-compose, but I f...

Quick question, can trains log keras loss values and/or metrics automatically? Or would I have to attach a tensorboard callback?

How do I disable completely any kind of python env caching by the agents? I tried having venvs_cache: { # maximum number of cached venvs max_entries: 10 # mi...

we're getting critical alerts for elasticsearch container around the JDK version. it's apparently end-of-life. can you look into upgrading the image? it look...

if I have 1 machine with a GPU, can I put a worker on it with GPU and two workers with --cpu-only ? i.e. can 2 workers in the same machine be launched in cpu...

does clearml-serving somehow cache the preprocess and postprocess functions? like after I call the endpoint once, it won't "rerun" the instructions in these ...

what is the series parameter of the Logger class functions for?

Is it possible to restrict an agent's cpu usage? like limit the number of cores it can use?

quick question about the cleanup service: one argument is cleanup_period_in_days , another is run_as_service . If the latter is false, it should only run onc...

what could be causing this?

Any idea what could be going on here? [2023-01-09 16:18:15,727][root][INFO][utils_atom_fn.py:85] - Running fn: fn_get_heat_map_nan [2023-01-09 16:18:15,782][...

Has anyone used clearml-serving and successfully sent an inference request via curl? I'm having trouble trying to send an inference request to the keras mnis...

I think there is a little bug with the PipelineDecorator.component : i provide the name of the component but it uses the name of the wrapped function as the ...

is there a way to limit the number of jobs/tasks that can run concurrently on the services queues?

the Dataset method create seems to expect the parameter parent_datasets in the form of a list indicating the parent dataset task IDs, instead of the name. Th...

if I do task.create() how do I pass the output_uri=True thing to it? that task.init generally has?

what is the python version an agent runs a task with? the one the agent was launched with, or the task? i.e. if Iaunch an agent with python 3.8.5, but a task...

clearly the link is 404

are the ClearML server AWS AMIs a paid only feature?

is it possible to add extra arguments to pip install for a docker agent? somewhere in clearml.conf or maybe some docker arguments? I'm trying to add a truste...

Hi, I'm trying to set up my trains-server and I'm getting the following: (base) emilio@unicorn:~$ docker-compose -f /opt/trains/docker-compose.yml up -d ERRO...

Hi there, are there any plans to add better documentation/examples to clearml-serving ? I have my serving working with version 0.9.0, but I can't see any doc...

What does it mean to publish a model or a dataset?

is there any clearml-serving api documentation?