Feature/support existing environments#1891
Conversation
|
|
sakoush
left a comment
sakoush
left a comment
There was a problem hiding this comment.
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?
| } | ||
| ``` | ||
|
|
||
| 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.
maybe add in the docs that we can have envs etc. in the enviornment_path?
There was a problem hiding this comment.
Could you explain that further? I'm not quite sure what I'm supposed to do.
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 |
3 participants
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_pathmodel parameter to specify the path to the existing environment.PoolRegistrytoEnvironment– the component where it’s unpackeddelete_envattribute 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