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.

Sign up for GitHub

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

Jump to bottom

Raise "conflicting rules/stories" error message before training the TEDPolicy model #7691

Closed
1 task
humcasma opened this issue Jan 7, 2021 · 3 comments · Fixed by #8716
Closed
1 task

Raise "conflicting rules/stories" error message before training the TEDPolicy model #7691

humcasma opened this issue Jan 7, 2021 · 3 comments · Fixed by #8716
Assignees
@joejuzl
Labels
area:rasa-oss 🎡 Anything related to the open source Rasa framework area:rasa-oss/training-data Issues focused around Rasa training data (stories, NLU, domain, etc.) effort:atom-squad/1 Label which is used by the Rasa Atom squad to do internal estimation of task sizes. type:enhancement ✨ Additions of new features or changes to existing ones, should be doable in a single PR

Comments

@humcasma
Copy link

humcasma commented Jan 7, 2021 •
edited by TyDunn
Loading

Description of Problem:
If there are conflicting rules and/or stories, an error message "InvalidRule: Contradicting rules or stories found" is raised. But this only happens after the core models, including the TEDPolicy model, are trained, which can take long.
I would suggest moving the check for invalid rules/stories before the TEDPolicy model is trained.

Definition of done:

  • Change the default config to put the rule policy first
@humcasma humcasma added area:rasa-oss 🎡 Anything related to the open source Rasa framework type:enhancement ✨ Additions of new features or changes to existing ones, should be doable in a single PR labels Jan 7, 2021
@sara-tagger
Copy link
Collaborator

Thanks for submitting this feature request 🚀 @amn41 will get back to you about it soon! ✨

@joejuzl joejuzl added area:rasa-oss/ml 👁 All issues related to machine learning type:discussion 👨‍👧‍👦 Early stage of an idea or validation of thoughts. Should NOT be closed by PR. labels Jan 27, 2021
@joejuzl
Copy link
Contributor

joejuzl commented Jan 27, 2021

@JEM-Mosig any idea whether this is possible? Or is it required to have a trained policy before checking for conflicts with rules?

@TyDunn
Copy link
Contributor

TyDunn commented Apr 20, 2021

@JEM-Mosig Following up about this. Is this possible?

@TyDunn TyDunn added area:rasa-oss/training-data Issues focused around Rasa training data (stories, NLU, domain, etc.) and removed area:rasa-oss/ml 👁 All issues related to machine learning labels Apr 30, 2021
@TyDunn TyDunn mentioned this issue Apr 30, 2021
Closed
@TyDunn TyDunn removed the type:discussion 👨‍👧‍👦 Early stage of an idea or validation of thoughts. Should NOT be closed by PR. label May 7, 2021
@wochinge wochinge added the effort:atom-squad/1 Label which is used by the Rasa Atom squad to do internal estimation of task sizes. label May 7, 2021
@joejuzl joejuzl mentioned this issue May 18, 2021
Merged
1 task
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@joejuzl joejuzl

Labels
area:rasa-oss 🎡 Anything related to the open source Rasa framework area:rasa-oss/training-data Issues focused around Rasa training data (stories, NLU, domain, etc.) effort:atom-squad/1 Label which is used by the Rasa Atom squad to do internal estimation of task sizes. type:enhancement ✨ Additions of new features or changes to existing ones, should be doable in a single PR
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Changed the default config to train the RulePolicy before the TEDPolicy. RasaHQ/rasa
5 participants
@joejuzl @humcasma @wochinge @TyDunn @sara-tagger