-
Notifications
You must be signed in to change notification settings - Fork 180
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Feature/support existing environments #1891
Feature/support existing environments #1891
Conversation
7e1aa73
to
8471a49
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Many thanks @idlefella for your contribution. This makes sense.
The logic seems ok, left some minor comments.
This change lacks though test coverage, could you please add relevant test cases for the new code?
@@ -277,6 +278,21 @@ Note that, in the folder layout above, we are assuming that: | |||
} | |||
``` | |||
|
|||
If you want to use an already exisiting python environment, you can use the parameter `environment_path` of your `model-settings.json`: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
maybe add in the docs that we can have envs etc. in the enviornment_path
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could you explain that further? I'm not quite sure what I'm supposed to do.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@ramonpzg minor changes to the docs FYI
Hi @sakoush |
Hi @sakoush, I've added unittests for the code. Let me know if there's anything else to do |
@idlefella I have triggered CI and it looks like there are some linting issue. Could you take a look? you can also run lint locally using |
Hi @sakoush |
Using Pre-existing Python Environments
Description
The current implementation of mlserver only supports specifying a Python environment through a tarball, which is then unpacked before the workers are activated. Our configuration, however, already includes pre-defined environments we aim to utilize. The current pull request offers an option to select a path to an already set up Python environment.
Changes Made
environment_path
model parameter to specify the path to the existing environment.PoolRegistry
toEnvironment
– the component where it’s unpackeddelete_env
attribute within Environment, determining whether the environment should be deleted from the disk upon the application's termination.Related Issues
Screenshots (if applicable)
Checklist
Additional Notes