Forms
One of the most common conversation patterns is to collect a few pieces of information from a user in order to do something (book a restaurant, call an API, search a database, etc.). This is also called **slot filling**.
Usage
To use forms with Rasa you need to make sure that the Rule Policy is added to your policy configuration. For example:
Defining a Form
Define a form by adding it to the forms
section in your domain.
The name of the form is also the name of the action which you can use in
stories or rules to handle form executions.
You will need to specify a list of slot names to the mandatory required_slots
key.
The following example form restaurant_form
will fill the slot
cuisine
and slot num_people
.
You can define a list of intents to ignore for the whole form under the
ignored_intents
key. Intents listed under ignored_intents
will be added to the
not_intent
key of each slot mapping.
For example, if you do not want any of the required slots of a form to be filled when
the intent is chitchat
, then you would need to define the following (after the form
name and under the ignored_intents
keyword):
Once the form action gets called for the first time, the form gets activated and will
prompt the user for the next required slot value. It does this by
looking for a response called
utter_ask_<form_name>_<slot_name>
or utter_ask_<slot_name>
if the former isn't
found. Make sure to define these responses in your domain file for
each required slot.
Activating a Form
To activate a form you need to add a story or rule, which describes when the assistant should run the form. In the case a specific intent triggering a form, you can for example use the following rule:
note
The active_loop: restaurant_form
step indicates that the form should be activated after
restaurant_form
was run.
Deactivating a Form
A form will automatically deactivate itself once all required slots are filled.
You can describe your assistant's behavior for the end of a form with a rule or a story.
If you don't add an applicable story or rule, the assistant will automatically listen
for the next user message after the form is finished.
The following example runs the utterances utter_submit
and utter_slots_values
as soon as the form
your_form
filled all required slots.
Users might want to break out of a form early. Please see Writing Stories / Rules for Unhappy Form Paths on how to write stories or rules for this case.
Slot Mappings
Changed in 3.0
As of 3.0, slot mappings are defined in the slots
section of the domain.
This change allows the same slot mapping to be reused across multiple forms, removing any unnecessary duplication.
Please follow the migration guide to update your assistant.
Note specifically the role of Mapping Conditions and the unique entity mapping constraint.
Writing Stories / Rules for Unhappy Form Paths
Your users will not always respond with the information you ask of them. Typically, users will ask questions, make chitchat, change their mind, or otherwise stray from the happy path.
While a form is active, if a user's input does not fill the requested slot, the execution of
the form action will be rejected i.e. the form will automatically raise an ActionExecutionRejection
.
These are the specific scenarios in which a form will raise an ActionExecutionRejection
:
- a slot was requested, but the user didn't fill the slot with their last message and you didn't define a custom action for validating slots or extracting slots.
- a slot was requested, but your custom action for
validating slots or
extracting slots didn't return any
SlotSet
events.
To intentionally reject the form execution, you can also return an ActionExecutionRejected
event as part of your
custom validations or slot mappings.
To handle situations that might cause a form's execution to be rejected, you can write rules or stories that include the expected interruptions. For example, if you expect your users to chitchat with your bot, you could add a rule to handle this:
In some situations, users may change their mind in the middle of the form action and decide not to go forward with their initial request. In cases like this, the assistant should stop asking for the requested slots.
You can handle such situations
gracefully using a default action action_deactivate_loop
which will deactivate
the form and reset the requested slot. An example story of such conversation could
look as follows:
It is strongly recommended that you build these rules or stories using interactive learning. If you write these rules / stories by hand you will likely miss important things.
Advanced Usage
Forms are fully customizable using Custom Actions.
Validating Form Input
After extracting a slot value from user input, you can validate the extracted slots. By default Rasa only validates if any slot was filled after requesting a slot.
You can implement a Custom Action validate_<form_name>
to validate any extracted slots. Make sure to add this action to the actions
section of your domain:
When the form is executed it will run your custom action after every user turn to validate the latest filled slots.
This custom action can extend FormValidationAction
class to simplify
the process of validating extracted slots. In this case, you need to write functions
named validate_<slot_name>
for every extracted slot.
The following example shows the implementation of a custom action
which validates that the slot named cuisine
is valid.
You can also extend the Action
class and retrieve extracted slots with tracker.slots_to_validate
to fully customize the validation process.
Custom Slot Mappings
Changed in 3.0
The slots_mapped_in_domain
argument provided to the required_slots
method of FormValidationAction
has been replaced by the domain_slots
argument, please update your custom actions to the new argument name.
If none of the predefined Slot Mappings fit your use
case, you can use the
Custom Action validate_<form_name>
to write your own
extraction code. Rasa will trigger this action when the form is run.
If you're using the Rasa SDK we recommend you to extend the provided
FormValidationAction
. When using the FormValidationAction
, three steps are required
to extract customs slots:
- Define a method
extract_<slot_name>
for every slot that should be mapped in a custom way. Each slot which has been defined in thedomain.yml
file with a custom mapping must have its own independent implementation of anextract_<slot_name>
method. - In your domain file, for your form's
required_slots
, list all required slots, with both predefined and custom mappings.
In addition, you can override the required_slots
method to add dynamically requested slots: you can read more in the
Dynamic Form Behavior section.
note
If you have added a slot with a custom mapping in the slots
section of the domain file which you only
want to be validated within the context of a form by a custom action extending FormValidationAction
,
please make sure that this slot has a mapping of type custom
and that the slot name is included in the
form's required_slots
.
The following example shows the implementation of a form which extracts a slot
outdoor_seating
in a custom way, in addition to the slots which use predefined mappings.
The method extract_outdoor_seating
sets the slot outdoor_seating
based on whether
the keyword outdoor
was present in the last user message.
By default the FormValidationAction
will automatically set the requested_slot
to the
first slot specified in required_slots
which is not filled.
Dynamic Form Behavior
By default, Rasa will ask for the next empty slot from the slots
listed for your form in the domain file. If you use
custom slot mappings and the FormValidationAction
,
it will ask for the first empty slot returned by the required_slots
method. If all
slots in required_slots
are filled the form will be deactivated.
You can update the required slots of your form dynamically. This is, for example, useful when you need to fill additional slots based on how a previous slot was filled or when you want to change the order in which slots are requested.
If you are using the Rasa SDK, we strongly recommend that you use the FormValidationAction
and
override required_slots
to fit your dynamic behavior. You must implement
a method extract_<slot name>
for every slot which doesn't use a predefined mapping,
as described in Custom Slot Mappings.
The example below will ask the user if they want to sit in
the shade or in the sun in case they said they want to sit outside.
If conversely, you want to remove a slot from the form's required_slots
defined in the domain file under certain conditions,
you should copy the domain_slots
over to a new variable and apply changes to that new variable instead of directly modifying
domain_slots
. Directly modifying domain_slots
can cause unexpected behaviour. For example:
The requested_slot slot
The slot requested_slot
is automatically added to the domain as a
slot of type text
. The value of the requested_slot
will be
ignored during conversations. If you want to change this behavior, you need to add
the requested_slot
to your domain file as a categorical slot with
influence_conversation
set to true
.
You might want to do this if you
want to handle your unhappy paths differently, depending on what slot is
currently being asked from the user. For example, if your users respond
to one of the bot's questions with another question, like why do you need to know that?
The response to this explain
intent depends on where we are in the story.
In the restaurant case, your stories would look something like this:
Again, it is strongly recommended that you use interactive learning to build these stories.
Using a Custom Action to Ask For the Next Slot
As soon as the form determines which slot has to be filled next by the user, it will
execute the action utter_ask_<form_name>_<slot_name>
or utter_ask_<slot_name>
to ask the user to provide the necessary information. If a regular utterance is not
enough, you can also use a custom action action_ask_<form_name>_<slot_name>
or
action_ask_<slot_name>
to ask for the next slot.
If there is more than one asking option for the slot, Rasa prioritizes in the following order:
action_ask_<form_name>_<slot_name>
utter_ask_<form_name>_<slot_name>
action_ask_<slot_name>
utter_ask_<slot_name>