You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is it possible to have guardrails classification based on categories and Sensitivity.
For Example, if a prompt is getting classified into 5 categories (Harassment, Hate, .. etc) can we have configure sensitivity scoring or classification such as Low, Medium, High. So we can implement a RBAC layer to allow policies to the users.
Is there any inherent solution provided by the Nemo Guardrails?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Is it possible to have guardrails classification based on categories and Sensitivity.
For Example, if a prompt is getting classified into 5 categories (Harassment, Hate, .. etc) can we have configure sensitivity scoring or classification such as Low, Medium, High. So we can implement a RBAC layer to allow policies to the users.
Is there any inherent solution provided by the Nemo Guardrails?
Beta Was this translation helpful? Give feedback.
All reactions