notice
This is documentation for Rasa Open Source Documentation v2.1.x, which is no longer actively maintained.
For up-to-date documentation, see the latest version (2.2.x).
rasa.core.actions.action
default_actions
List default actions.
action_for_index
Get an action based on its index in the list of available actions.
Arguments:
index
- The index of the action. This is usually used byPolicy
s as they predict the action index instead of the name.domain
- TheDomain
of the current model. The domain contains the actions provided by the user + the default actions.action_endpoint
- Can be used to runcustom_actions
(e.g. using therasa-sdk
).
Returns:
The instantiated Action
or None
if no Action
was found for the given
index.
action_for_name
Create an Action
object based on the name of the Action
.
Arguments:
action_name
- The name of theAction
.domain
- TheDomain
of the current model. The domain contains the actions provided by the user + the default actions.action_endpoint
- Can be used to runcustom_actions
(e.g. using therasa-sdk
).
Returns:
The instantiated Action
or None
if no Action
was found for the given
index.
is_retrieval_action
Check if an action name is a retrieval action.
The name for a retrieval action has an extra utter_
prefix added to
the corresponding retrieval intent name.
Arguments:
action_name
- Name of the action.retrieval_intents
- List of retrieval intents defined in the NLU training data.
Returns:
True
if the resolved intent name is present in the list of retrieval
intents, False
otherwise.
action_from_name
Retrieves an action by its name.
Arguments:
name
- The name of the action.domain
- The current model domain.action_endpoint
- The endpoint to execute custom actions.
Returns:
The instantiated action.
create_bot_utterance
Create BotUttered event from message.
Action Objects
Next action to be taken in response to a dialogue state.
name
Unique identifier of this simple action.
run
Execute the side effects of this action.
Arguments:
nlg
- whichnlg
to use for response generationoutput_channel
-output_channel
to which to send the resulting message.tracker
DialogueStateTracker - the state tracker for the current user. You can access slot values usingtracker.get_slot(slot_name)
and the most recent user message istracker.latest_message.text
.domain
Domain - the bot's domainmetadata
- dictionary that can be sent to action server with custom data.
Returns:
List[Event]
- A list of :class:rasa.core.events.Event
instances
ActionUtterTemplate Objects
An action which only effect is to utter a template when it is run.
Both, name and utter template, need to be specified using
the name
method.
run
Simple run implementation uttering a (hopefully defined) template.
ActionRetrieveResponse Objects
An action which queries the Response Selector for the appropriate response.
intent_name_from_action
Resolve the name of the intent from the action name.
action_name_from_intent
Resolve the action name from the name of the intent.
run
Query the appropriate response and create a bot utterance with that.
ActionBack Objects
Revert the tracker state by two user utterances.
ActionListen Objects
The first action in any turn - bot waits for a user message.
The bot should stop taking further actions and wait for the user to say something.
ActionRestart Objects
Resets the tracker to its initial state.
Utters the restart response if available.
ActionSessionStart Objects
Applies a conversation session start.
Takes all SlotSet
events from the previous session and applies them to the new
session.
ActionDefaultFallback Objects
Executes the fallback action and goes back to the previous state of the dialogue
ActionDeactivateLoop Objects
Deactivates an active loop.
RemoteAction Objects
action_response_format_spec
Expected response schema for an Action endpoint.
Used for validation of the response returned from the Action endpoint.
ActionExecutionRejection Objects
Raising this exception will allow other policies to predict a different action
ActionRevertFallbackEvents Objects
Reverts events which were done during the TwoStageFallbackPolicy
.
This reverts user messages and bot utterances done during a fallback
of the TwoStageFallbackPolicy
. By doing so it is not necessary to
write custom stories for the different paths, but only of the happy
path. This is deprecated and can be removed once the
TwoStageFallbackPolicy
is removed.
ActionDefaultAskAffirmation Objects
Default implementation which asks the user to affirm his intent.
It is suggested to overwrite this default action with a custom action to have more meaningful prompts for the affirmations. E.g. have a description of the intent instead of its identifier name.
ActionDefaultAskRephrase Objects
Default implementation which asks the user to rephrase his intent.