Tracker
These docs are for version 1.x of Rasa Open Source.
User Guide
- Installation
- Tutorial: Rasa Basics
- Tutorial: Building Assistants
- Command Line Interface
- Architecture
- Messaging and Voice Channels
- Testing Your Assistant
- Setting up CI/CD
- Validate Data
- Configuring the HTTP API
- Deploying Your Rasa Assistant
- Cloud Storage
NLU
- About
- Using NLU Only
- Training Data Format
- Language Support
- Choosing a Pipeline
- Components
- Entity Extraction
Core
- About
- Stories
- Domains
- Responses
- Actions
- Reminders and External Events
- Policies
- Slots
- Forms
- Retrieval Actions
- Interactive Learning
- Fallback Actions
- Knowledge Base Actions
Conversation Design
API Reference
- Action Server
- HTTP API
- Jupyter Notebooks
- Agent
- Custom NLU Components
- Rasa SDK
- Events
- Tracker
- Tracker Stores
- Event Brokers
- Lock Stores
- Training Data Importers
- Featurization of Conversations
- TensorFlow Configuration
- Migration Guide
- Rasa Open Source Change Log
Migrate from (beta)
Reference
Versions
viewing: 1.10.21
Warning: This document is for an old version of Rasa. The latest version is 1.10.26.
Tracker
Trackers maintain the state of a dialogue between the assistant and the user in the form of conversation sessions. To learn more about how to configure the session behavior, check out the docs on Session configuration.
class rasa.core.trackers.DialogueStateTracker(sender_id, slots, max_event_history=None, sender_source=None)
Maintains the state of a conversation.
applied_events()
Returns all actions that should be applied - w/o reverted events.
Return type: List[Event]
as_dialogue()
Return a Dialogue object containing all of the turns.
This can be serialized and later used to recover the state of this tracker exactly.
Return type: Dialogue
change_form_to(form_name)
Activate or deactivate a form.
Return type: None
clear_followup_action()
Clears follow-up action when it was executed.
Return type: None
copy()
Creates a duplicate of this tracker.
Return type: DialogueStateTracker
current_slot_values()
Return the currently set values of the slots.
Return type: Dict[str, Any]
current_state(event_verbosity=<EventVerbosity.NONE: 1>)
Return the current tracker state as an object.
Return type: Dict[str, Any]
events_after_latest_restart()
Return a list of events after the most recent restart.
Return type: List[Event]
export_stories(e2e=False, include_source=False)
Dump the tracker as a story in the Rasa Core story format. Returns the dumped tracker as a string.
Return type: str
export_stories_to_file(export_path='debug.md')
Dump the tracker as a story to a file.
Return type: None
classmethod from_dict(sender_id, events_as_dict, slots=None, max_event_history=None)
Create a tracker from dump. The dump should be an array of dumped events. When restoring the tracker, these events will be replayed to recreate the state.
Return type: DialogueStateTracker
generate_all_prior_trackers()
Returns a generator of the previous trackers of this tracker.
Return type: Generator[DialogueStateTracker, None, None]
get_last_event_for(event_type, action_names_to_exclude=None, skip=0)
Gets the last event of a given type which was actually applied.
Return type: Optional[Event]
get_latest_entity_values(entity_type, entity_role=None, entity_group=None)
Get entity values found for the passed entity type and optional role and group in the latest message.
Return type: Iterator[str]
get_latest_input_channel()
Get the name of the input_channel of the latest UserUttered event.
Return type: Optional[str]
get_slot(key)
Retrieves the value of a slot.
Return type: Optional[Any]
idx_after_latest_restart()
Return the idx of the most recent restart in the list of events.
Return type: int
init_copy()
Creates a new state tracker with the same initial values.
Return type: DialogueStateTracker
is_paused()
State whether the tracker is currently paused.
Return type: bool
last_executed_action_has(name, skip=0)
Returns whether last ActionExecuted event had a specific name.
Return type: bool
past_states(domain)
Generate the past states of this tracker based on the history.
Return type: deque
recreate_from_dialogue(dialogue)
Use a serialized Dialogue to update the tracker's state.
Return type: None
reject_action(action_name)
Notify active form that it was rejected.
Return type: None
replay_events()
Update the tracker based on a list of events.
Return type: None
set_form_validation(validate)
Toggle form validation.
Return type: None
set_latest_action_name(action_name)
Set latest action name and reset form validation and rejection parameters.
Return type: None
travel_back_in_time(target_time)
Creates a new tracker with a state at a specific timestamp.
Return type: DialogueStateTracker
trigger_followup_action(action)
Triggers another action following the execution of the current.
Return type: None
update(event, domain=None)
Modify the state of the tracker according to an Event.
Return type: None
👋 I can help you get started with Rasa and answer your technical questions.