This documentation was last modified: Friday, April 5th, 2019 at 9:49 pm
A Fallback Skill is a Skill that will be called if no Intent is matched to the Utterance. Previously, Wolfram Alpha was the only Fallback Skill, finding answers for general queries. Recently a system for multiple Fallback Skills was added.
The Fallback Skills all have a priority and will be checked in order from low priority value to high priority value. If a Fallback Skill can handle the Utterance it will create a response and return
True. After this no other Fallback Skills are tried. This means the priority for Fallbacks that can handle a broad range of queries should be high (80-100) and Fallbacks that only responds to a very specific range of queries should be higher (20-80). The more specific, the lower the priority value.
FallbackSkill base class:
from mycroft.skills.core import FallbackSkill
Create a derived class:
class MeaningFallback(FallbackSkill): """ A Fallback skill to answer the question about the meaning of life, the universe and everything. """ def __init__(self): super(MeaningFallback, self).__init__(name='My Fallback Skill) # Add your own initialization code here
Register the handler with the fallback system
FallbackSkill can register any number of fallback handlers
def initialize(self): """ Registers the fallback handler """ self.register_fallback(self.handle_fallback, 10) # Any other initialize code you like can be placed here
Implement the fallback handler (the method that will be called to potentially handle the Utterance). The method implements logic to determine if the Utterance can be handled and shall output speech if itcan handle the query. It shall return Boolean
True if the Utterance was handled and Boolean
False if not.
def handle_fallback(self, message): """ Answers question about the meaning of life, the universe and everything. """ utterance = message.data.get("utterance") if 'what' in utterance and 'meaning' in utterance and ('life' in utterance or 'universe' in utterance or 'everything' in utterance): self.speak('42') return True else: return False
Finally, the Skill creator must make sure the skill handler is removed when the Skill is shutdown by the system.
def shutdown(self): """ Remove this skill from list of fallback skills. """ self.remove_fallback(self.handle_fallback) super(MeaningFallback, self).shutdown()
And as with a normal Skill the function
create_skill() needs to be in the file to instantiate the skill.
def create_skill(): return MeaningFallback()
The above example can be found here.