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

Support for hosting artifacts as microservices #3

Open
romain-intel opened this issue Dec 2, 2019 · 7 comments
Open

Support for hosting artifacts as microservices #3

romain-intel opened this issue Dec 2, 2019 · 7 comments
Assignees
Labels

Comments

@romain-intel
Copy link
Contributor

@romain-intel romain-intel commented Dec 2, 2019

Once Metaflow has been used to train a model, it produces artifacts that are typically persisted (for example in S3). A natural extension of this is to provide an easy mechanism to deploy web services that would take these artifacts and serve them in some way so that they can be consumed by downstream applications.

@wuqunfei

This comment has been minimized.

Copy link

@wuqunfei wuqunfei commented Dec 4, 2019

`from metaflow import WebServiceSpec
from metaflow import endpoint

class MyWebService(WebServiceSpec):

@ednpoint
def show_data(self, request):
### TODO
return {}`

I did not find these classes in master branch. looking forward to seeing.

@savingoyal

This comment has been minimized.

Copy link
Contributor

@savingoyal savingoyal commented Dec 4, 2019

@wuqunfei Yes, you are correct, we haven’t released WebServiceSpec yet.

@wuqunfei

This comment has been minimized.

Copy link

@wuqunfei wuqunfei commented Dec 4, 2019

thanks, @savingoyal, it is a really good idea to expose endpoint. I am using sagemaker to host endpoint, but it is not so easy as your annotation.

@justinttl

This comment has been minimized.

Copy link

@justinttl justinttl commented Dec 12, 2019

Hi! Saw the talk on this topic yesterday and am really excited for this feature to be released in the future.

Is there a channel where development on this is being discussed? Would love to participate and help out.

@savingoyal

This comment has been minimized.

Copy link
Contributor

@savingoyal savingoyal commented Dec 12, 2019

Yes, @justinttl this issue tracks the development.

@romain-intel

This comment has been minimized.

Copy link
Contributor Author

@romain-intel romain-intel commented Dec 13, 2019

This is a good medium to communicate your ideas, etc. We are currently working on a redesign of the ideas expressed in the talk internally and, given sufficient interest, we will look at releasing this to the community as well. The talk (and associated slides) give a pretty good idea of where we are at right now. Comments/thoughts are more than welcome here!

@retnuh

This comment has been minimized.

Copy link

@retnuh retnuh commented Dec 30, 2019

Kubeflow uses seldon.io for deploying models; it may be worth looking into - or perhaps a pluggable layer with a seldon backend.

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

Successfully merging a pull request may close this issue.

None yet
5 participants
You can’t perform that action at this time.