Oh, can you please do the same with developer tools when user tries to accept?

By default the agent will try to install packages according to what was logged in the 'installed packages' section of the task in 'execution' tab

I see, so if you have 60 in queue and you select 30 you'd like to move them up the queue but so out of the selected 30 they would still keep their relative order, correct?

What is your use case though? I think the point of local/remote is that you can debug in local

Ok, have you tried it?

The controller simply runs the logic of the pipeline and requires minimal resources. All the heavy computation happens on the nodes/machines running the steps

Hi @<1714451225295982592:profile|FreshWoodpecker88> , is it possible that you didn't get permissions to the relevant directories to act as the actual storage for mongodb?

Hi @<1652120623545061376:profile|FrightenedSealion82> , do you see any errors in the apiserver or the webserver containers?

From the looks of this example this should be connected automatically actually
https://github.com/allegroai/clearml/blob/master/examples/frameworks/hydra/hydra_example.py

Hey GrievingTurkey78 ,

Please take a look here : https://clear.ml/docs/latest/docs/references/sdk/task#taskinit

I think what you're looking for is this:
Task.init(.., continue_last_task=True )

Just search for this parameter for more more info 🙂

Are you using the PRO or a self hosted server?

Hi FierceHamster54 , you have docker_args in https://clear.ml/docs/latest/docs/references/sdk/automation_controller_pipelinecontroller#pipelinedecoratorcomponent

Hmmm, but what should be the default task state? What is the use case by the way?

Hi @<1523704461418041344:profile|EnormousCormorant39> , is there any chance this could be indeed network related if it does manage to work sometimes?

Can you add a larger portion of the log with errors?

Also what type of machines are these? Linux to linux?

Multiple instances of the autoscaler maybe?

Hi @<1658643479691005952:profile|TroubledLobster8> , about the agents in the web UI, they usually clear out in 10-15 minutes from there

Hi @<1577468626967990272:profile|PerplexedDolphin99> , I think you will get the submodules, you just need to make sure to set up the agent with git_ask_pass to true

Hi @<1523702459048923136:profile|SmugSnake6> , what framework are you using? Do you have a stand alone snippet that reproduces this?

@<1736556867255013376:profile|ImpressionableElk3> , What issues are you having exactly? Can you attach logs?

Is it possible the machines are running out of memory? Do you get this error on the pipeline controller itself? Does this constantly reproduce?

SubstantialMonkey63 , Hi! What exactly are you looking for ? I think you might find some relevant things here https://github.com/allegroai/clearml/tree/master/examples

Hi @<1578555761724755968:profile|GrievingKoala83> , what happens if you rerun this via the webUI ?

Can you provide a self contained contained snippet that reproduces this behavior?

Also in applications I see an option for subnet ID & security group

Thanks FiercePenguin76
We will update the roadmap and go into details on the next community Talk (in a week from now, I think)
Regrading clearml-serving, Yes! we are actively working on it internally, but we would love to get some feedback, I think  AnxiousSeal95  would appreciate it  😉

Hi @<1736919317200506880:profile|NastyStarfish19> , the services queue is for running the pipeline controller itself. I guess you are self hosting the OS?

@<1582179652133195776:profile|LudicrousPanda17> , I think you misunderstood me. This is entirely possible through the API. I suggest you do this via UI with dev tools open (F12) to see what the UI is sending since the UI is using the same API. Then you can replicate this behavior via code. Understood?

Hi UpsetTurkey67 ,

Is this what you're looking for?
https://clear.ml/docs/latest/docs/references/sdk/trigger#add_model_trigger

Hi @<1523701235335565312:profile|HugeArcticwolf77> , user roles & permissions are only available in the Scale & Enterprise versions

Hi @<1523701295830011904:profile|CluelessFlamingo93> , I think you need this module as a part of repository, otherwise, how will the pipeline know what code to use?