Forms

Forms

Note
There is an in-depth tutorial here about how to use Rasa Forms for slot filling.

Configuration File

To use forms, you also need to include the FormPolicy in your policy configuration file. For example:

policies:
  - name: "FormPolicy"

Form Basics

Using a FormAction, you can describe all of the happy paths with a single story. By “happy path”, we mean that whenever you ask a user for some information, they respond with the information you asked for.

## happy path
* request_restaurant
    - restaurant_form
    - form{"name": "restaurant_form"}
    - form{"name": null}

In this story the user intent is request_restaurant, which is followed by the form action restaurant_form. With form{"name": "restaurant_form"} the form is activated and with form{"name": null} the form is deactivated again. As shown in the section Handling unhappy paths the bot can execute any kind of actions outside the form while the form is still active. On the “happy path”, where the user is cooperating well and the system understands the user input correctly, the form is filling all requested slots without interruption.

The FormAction will only request slots which haven’t already been set. If a user starts the conversation with I’d like a vegetarian Chinese restaurant for 8 people, then they won’t be asked about the cuisine and num_people slots.

Slot Usage

Note that for this story to work, your slots should be unfeaturized. If any of these slots are featurized, your story needs to include slot{} events to show these slots being set. In that case, the easiest way to create valid stories is to use Interactive Learning.

Required Methods

You need to define three methods:

def name(self) -> Text:
    return "restaurant_form"
@staticmethod
def required_slots(tracker: Tracker) -> List[Text]:
    return ["cuisine", "num_people", "outdoor_seating", "preferences", "feedback"]
def submit(
    self,
    dispatcher: CollectingDispatcher,
    tracker: Tracker,
    domain: Dict[Text, Any],
) -> List[Dict]:
    dispatcher.utter_message(template="utter_submit")
    return []

Custom slot mappings

If you do not define slot mappings, slots will be only filled by entities with the same name as the slot that are picked up from the user input.

Here’s an example for the restaurant bot:

def slot_mappings(self) -> Dict[Text, Union[Dict, List[Dict]]]:
    return {
        "cuisine": self.from_entity(entity="cuisine", not_intent="chitchat"),
        "num_people": [
            self.from_entity(
                entity="number", intent=["inform", "request_restaurant"]
            )
        ],
        "outdoor_seating": [
            self.from_entity(entity="seating"),
            self.from_intent(intent="affirm", value=True),
            self.from_intent(intent="deny", value=False)
        ],
        "preferences": [
            self.from_intent(intent="deny", value="no additional preferences"),
            self.from_text(not_intent="affirm")
        ],
        "feedback": [self.from_entity(entity="feedback"), self.from_text()]
    }

Validating user input

After extracting a slot value from user input, the form will try to validate the value of the slot. By default, validation only checks if the requested slot was successfully extracted from the slot mappings.

Here is an example validation function:

def validate_cuisine(self, value: Text, dispatcher: CollectingDispatcher, tracker: Tracker, domain: Dict[Text, Any]) -> Dict[Text, Any]:
    if value.lower() in self.cuisine_db():
        return {"cuisine": value}
    else:
        dispatcher.utter_message(template="utter_wrong_cuisine")
        return {"cuisine": None}

Handling unhappy paths

Of course your users will not always respond with the information you ask of them. Typically, to handle these situations, use the action_deactivate_form which will deactivate the form and reset the requested slot.

## chitchat
* request_restaurant
    - restaurant_form
    - form{"name": "restaurant_form"}
* stop
    - utter_ask_continue
* deny
    - action_deactivate_form
    - form{"name": null}

Debugging

The first thing to try is to run your bot with the --debug flag.