search

machine-learning-exchange / mlx

Machine Learning eXchange (MLX). Data and AI Assets Catalog and Execution Engine
https://ml-exchange.org/
Apache License 2.0
205 stars 54 forks source link

Model deployment code template cannot change namespace #123

Open Tomcli opened 3 years ago

Tomcli commented 3 years ago

Describe the bug Right now the model deployment code template is hard coded to the anonymous namespace, we need to make it configurable in order to work in the multi-user environment.

To Reproduce

Steps to reproduce the behavior:

  1. Go to '...'
  2. Click on '....'
  3. Scroll down to '....'
  4. See error

Expected behavior

A clear and concise description of what you expected to happen.

Screenshots

If applicable, add screenshots to help explain your problem.

Environment

Additional context

Add any other context about the problem here.

ckadner commented 3 years ago

I will hard-code a quick fix (1c451fa) to use namespace "mlx" until I get a chance to add a new variable to the API

ckadner commented 3 years ago

@Tomcli -- QQ do we still need to use your custom kfserving component.yaml here?

https://github.com/machine-learning-exchange/mlx/blob/ef06fa28ffba1cdf22d6dfa4f81fb426f2fc7f0c/api/server/swagger_server/code_templates/serve_kfserving.TEMPLATE.py#L39

It differs only slightly from this one: https://raw.githubusercontent.com/kubeflow/pipelines/master/components/kubeflow/kfserving/component.yaml

Tomcli commented 3 years ago

@ckadner you can use the official one at https://raw.githubusercontent.com/kubeflow/pipelines/master/components/kubeflow/kfserving/component.yaml

just that some parameter mapping needs to be changed.