Default Actions
Default actions are actions that are built into the dialogue manager by default. Most of these are automatically predicted based on certain conversation situations. You may want to customize these to personalize your assistant.
Each of these actions have a default behavior, described in the sections below.
In order to overwrite this default behavior, write a custom action
whose name()
method returns the same name as the default action:
Add this action to the actions section of your domain file so your assistant knows to use the custom definition instead of the default one:
caution
After adding this action to your domain file, re-train your model with
rasa train --force
. Otherwise Rasa won't know you've changed anything
and may skip re-training your dialogue model.
action_listen
This action is predicted to signal that the assistant should do nothing and wait for the next user input.
action_restart
This action resets the whole conversation history, including any slots that were set during it.
It can be triggered by the user in a conversation by sending a
"/restart" message, if the RulePolicy is included in the model configuration.
If you define an utter_restart
response in your domain, this will be sent to the user as well.
action_session_start
This action starts a new conversation session, and is executed in the following situations:
- at the beginning of each new conversation
- after a user was inactive for a period defined by the
session_expiration_time
parameter in the domain's session configuration - when a user sends a "/session_start" message during a conversation
The action will reset the conversation tracker, but by default will not clear any slots that were set.
Customization
The default behavior of the session start action is to take all existing slots and to
carry them over into the next session. Let's say you do not want to carry over all
slots, but only a user's name and their phone number. To do that, you'd override the
action_session_start
with a custom action that might look like this:
If you want to access the metadata which was sent with the user message which triggered
the session start, you can access the special slot session_started_metadata
:
action_default_fallback
This action undoes the last user-bot interaction and sends the utter_default
response if it is defined.
It is triggered by low action prediction confidence, if you have this fallback mechanism enabled.
action_deactivate_loop
This action deactivates the active loop and resets the requested slot. This is used when handling unhappy paths in forms.
note
If you wish to reset all slots, we recommend using a custom action
that returns the AllSlotsReset
event after form deactivation.
action_two_stage_fallback
This is a fallback loop that can be used to handle low NLU confidence. Read more about handling low NLU confidence.
action_default_ask_affirmation
This action is used by the action_two_stage_fallback
loop. It asks the user to confirm
the intent of their message. This action can be customized to be more personalized
to your specific use case.
action_default_ask_rephrase
This action is used by the action_two_stage_fallback
loop if the user denies the
intent action_default_ask_affirmation
displays. It asks the user to rephrase
their message.
action_back
This action undoes the last user-bot interaction. It can be triggered by the user by sending a "/back" message to the assistant if the RulePolicy is configured. |
Form Action
By default Rasa uses FormAction
for processing any
form logic. You can override this default action with a custom action by
adding a custom action with the form's name to the domain.
Overriding the default action for forms should only be used during the process of
migrating from Rasa 1.0 to 2.0.
action_unlikely_intent
Rasa triggers action_unlikely_intent
via UnexpecTEDIntentPolicy
.
You can control how often this action is predicted by tuning the tolerance
parameter of UnexpecTEDIntentPolicy
.
Customization
You can customize your assistant's behaviour to configure what should happen once action_unlikely_intent
is triggered. For example, as a follow up you can trigger a hand-off to a human agent with a rule:
Alternatively, you can also override it's behaviour as a custom action
by
adding action_unlikely_intent
to the list of actions in the domain and implementing the custom behaviour:
note
Since action_unlikely_intent
can be triggered at any conversation step during inference,
all policies which are trained on only story data, for example - TEDPolicy
, UnexpecTEDIntentPolicy
,
MemoizationPolicy
ignore its presence in the tracker when making a prediction. However, RulePolicy
takes its presence into account so that conversation behaviour is customizable.
note
action_unlikely_intent
cannot be included in the training stories. It can only be added to rules.
action_extract_slots
This action runs after each user turn, before the next assistant action prediction and execution.
action_extract_slots
loops through the slot mappings of each domain slot in order to set or update
slots throughout the conversation with information extracted from the latest user message.
If action_extract_slots
finds a custom slot mapping, it will check first if a custom action was defined in the
mapping via the action
key and then run it.
After applying all the slot mappings, action_extract_slots
will run the custom validation action
action_validate_slot_mappings
if it is present in the domain actions. Otherwise it will immediately return the already
extracted slots.
Note that custom actions used by slot mappings or slot mapping validation should only return events of type SlotSet
or
BotUttered
. Events of any other type are not permitted and will be ignored when updating the tracker.
The default action action_extract_slots
replaces the slot extraction previously executed by FormAction
.
If you wish to set a slot based on information extracted from intents that trigger forms, you must explicitly specify a
mapping that does not contain the conditions
key. A slot mapping with conditions
applies only once the specified form is active.
action_extract_slots
runs directly after each user message, and thus before the activation of the form.
Therefore a mapping that should apply to user messages that trigger a form must not specify conditions
, or the form
will re-ask for the slot once it is activated.
note
If action_default_fallback
is the next action predicted and executed by the assistant, this will result in a
UserUtteranceReverted
event which will unset the slots previously filled in the last user turn.