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

Ensure all model servers have pinned requirements and the full requirements.txt is included in the docs #2065

Closed
axsaucedo opened this issue Jul 2, 2020 · 1 comment · Fixed by #2398 or #2399

Comments

@axsaucedo
Copy link
Contributor

axsaucedo commented Jul 2, 2020

Currently the requirements on the sklearn model server are not pinned down, resulting in un-predictable "latest" versions for the dependencies available. We'll need to pin down these versions and ensure that all the dependencies are explicitly provided in the documentation. It may be worth adding a mention in the prepackaged server pages linking to the custom server doc page to specify that the image can be overriden with custom images with specific dependencies as required. Relevant to #2012.

@axsaucedo axsaucedo added bug triage Needs to be triaged and prioritised accordingly labels Jul 2, 2020
@axsaucedo axsaucedo added this to the 1.2 milestone Jul 2, 2020
@axsaucedo
Copy link
Contributor Author

There is currently also not explicit description that joblib instead of sklearn.extensions.joblib should be used. We shoudl specify and provide an example of how the model server expects the models to be exported.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment