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

Delete and unload model from server through API #438

Closed
bigman73 opened this issue Jun 19, 2017 · 1 comment
Closed

Delete and unload model from server through API #438

bigman73 opened this issue Jun 19, 2017 · 1 comment
Labels
help wanted type:enhancement ✨ Additions of new features or changes to existing ones, should be doable in a single PR

Comments

@bigman73
Copy link
Contributor

bigman73 commented Jun 19, 2017

Feature request

rasa NLU version (e.g. 0.7.3):
0.8.10

Used backend / pipeline (mitie, spacy_sklearn, ...):
spacy_sklearn

Operating system (windows, osx, ...):
Docker/Linux

Issue:
Add an REST DELETE API for deleting an available model. As of 0.8.10 the workaround is to delete the trained model folder from the parent /models folder.
The Delete API should not just delete the folder but clean up any internal data structures holding the model trained data - basically untrain the model.

Content of configuration file (if used & relevant):

@tmbo tmbo added the type:enhancement ✨ Additions of new features or changes to existing ones, should be doable in a single PR label Jun 21, 2017
@tmbo tmbo changed the title Feature - Delete model API Delete and unload model from server through API Jun 21, 2017
@tmbo
Copy link
Member

tmbo commented Jun 26, 2017

That sounds like a good addition 👍

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
help wanted type:enhancement ✨ Additions of new features or changes to existing ones, should be doable in a single PR
Projects
None yet
Development

No branches or pull requests

2 participants