CODEWITHSUNDEEP
machine-learningrasa-nlurasa-core
user1870035
user1870035

Reputation:

Rasa Core - Understanding Stories

I am having a difficult time understanding how rasa core interprets stories. Say I have the following:

Slot:
 name:
  type: text
 animal:
  type: categorical
  values:
  - dog
  - cat

How do I write my stories to handle the sad path for a categorical slot? 

*greet
 - utter_greet
 - utter_please_give_name
*inform{"Name":"Name"}
 - utter_hello
 - utter_ask_animal
*inform{"Animal": "Dog"}
 - utter_hello_fido
 - action_restart

*greet
 - utter_greet
 - utter_please_give_name
*inform{"Name":"Name"}
 - utter_hello
 - utter_ask_animal
*inform{"Animal": "Cat"}
 - utter_hello_kitty
 - action_restart

*greet
 - utter_greet
 - utter_please_give_name
*inform{"Name": null}
  -utter_please_give_name

*greet 
 - utter_greet
 - utter_please_give_name
*inform{"Name": "Name"}
  -utter_ask_animal
*inform{"Animal": **"?????"**}
 - utter_please_tell_animal

Also if I give a partial story in stories.md, like below, how does rasa connect the graph on the back to know what to do next? Does it read each story as an independent flow?

*greet
 - utter_greet
 - utter_please_give_name
*inform{"Name": null}
  -utter_please_give_name

Thank you, any advice is appreciated.

Upvotes: 2

Views: 602

Answers (2)

Noarah
Noarah

Reputation: 29

If you want to handle all animals names so simply you can add more categories or make a custom action to fetch some api to call an animal name or something, Rasa is learning by examples anything not entered in data or domain will act as strange text.

Upvotes: 0

Tobias
Tobias

Reputation: 1910

To handle the sad path simply omit the slot annotation, e.g.:

## sad path
*greet
 - utter_greet
 - utter_please_give_name
*inform
  -utter_please_give_name

Depending whether you use augmentation the single stories are glued together during the training to provide more training data.

Upvotes: 1

Related Questions