Skip to content
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

Dockerize the entier wrapping process of building sklearn_iris example #51

Merged
merged 1 commit into from
Jan 19, 2018

Conversation

errordeveloper
Copy link
Contributor

No description provided.

@errordeveloper
Copy link
Contributor Author

There are probably more docs changes that would be needed, but I'm just trying to demonstrate how simple this becomes.

- use multi-stage build and Alpine as a base
- use stripped-down model image
- provide Makefile for running docker build command
- declare all Python dependencies in one requirements.txt file
- copy sklearn_iris_deployment.json
@ahousley
Copy link
Member

Thanks @errordeveloper! @gsunner is reviewing.

@ahousley ahousley requested a review from gsunner January 19, 2018 09:50
@gsunner gsunner merged commit 4a5f002 into SeldonIO:master Jan 19, 2018
@gsunner
Copy link
Contributor

gsunner commented Jan 19, 2018

This is useful, thanks

@errordeveloper
Copy link
Contributor Author

errordeveloper commented Jan 19, 2018

As @gsunner asked on Slack, I've updated this to create another directory instead modifying the existing one. I've not touched the docs, as I am not sure how you'd like to go about it, but all there is to do now is:

  1. install Heml chart
  2. cd examples/models/sklearn_iris_docker
  3. make
  4. kubectl apply -f sklearn_iris_deployment.json

I've tested it on Docker for Mac (latest versions that included Kubernetes), and it works. For other cases with a remote cluster, one would probably need to push the image, maybe adding make push_container_image is a thing to add...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants