This is documentation for Rasa & Rasa Pro Documentation v2.x, which is no longer actively maintained.
For up-to-date documentation, see the latest version (3.x).
Policy which predicts fallback actions.
A fallback can be triggered by a low confidence score on a NLU prediction or by a low confidence score on an action prediction.
Create a new Fallback policy.
priority- Fallback policy priority.
core_threshold- if NLU confidence threshold is met, predict fallback action with confidence
core_threshold. If this is the highest confidence in the ensemble, the fallback action will be executed.
nlu_threshold- minimum threshold for NLU confidence. If intent prediction confidence is lower than this, predict fallback action with confidence 1.0.
ambiguity_threshold- threshold for minimum difference between confidences of the top two predictions
fallback_action_name- name of the action to execute as a fallback
Does nothing. This policy is deterministic.
Check if the highest confidence is lower than
Check if top 2 confidences are closer than
Check if fallback action should be predicted.
- predicted NLU confidence is lower than
- difference in top 2 NLU confidences lower than
- last action is action listen
Prediction scores used if a fallback is necessary.
Predicts a fallback action.
The fallback action is predicted if the NLU confidence is low or no other policy has a high-confidence prediction.