rasa.core.training.interactive
You are viewing documentation for our open source project which is maintained by the community. If you want to get started building assistants with Rasa please check out our latest documentation here.
RestartConversation Objects
class RestartConversation(Exception)
Exception used to break out the flow and restart the conversation.
ForkTracker Objects
class ForkTracker(Exception)
Exception used to break out the flow and fork at a previous step.
The tracker will be reset to the selected point in the past and the conversation will continue from there.
UndoLastStep Objects
class UndoLastStep(Exception)
Exception used to break out the flow and undo the last step.
The last step is either the most recent user message or the most recent action run by the bot.
Abort Objects
class Abort(Exception)
Exception used to abort the interactive learning and exit.
send_message
async send_message(endpoint: EndpointConfig, conversation_id: Text, message: Text, parse_data: Optional[Dict[Text, Any]]=None)-> Dict[Text, Any]
Send a user message to a conversation.
request_prediction
async request_prediction(endpoint: EndpointConfig, conversation_id: Text)-> Dict[Text, Any]
Request the next action prediction from core.
retrieve_domain
async retrieve_domain(endpoint: EndpointConfig)-> Dict[Text, Any]
Retrieve the domain from core.
retrieve_status
async retrieve_status(endpoint: EndpointConfig)-> Dict[Text, Any]
Retrieve the status from core.
retrieve_tracker
async retrieve_tracker(endpoint: EndpointConfig, conversation_id: Text, verbosity: EventVerbosity = EventVerbosity.ALL)-> Dict[Text, Any]
Retrieve a tracker from core.
send_action
async send_action(endpoint: EndpointConfig, conversation_id: Text, action_name: Text, policy: Optional[Text]=None, confidence: Optional[float]=None, is_new_action:bool=False)-> Dict[Text, Any]
Log an action to a conversation.
send_event
async send_event(endpoint: EndpointConfig, conversation_id: Text, evt: Union[List[Dict[Text, Any]], Dict[Text, Any]])-> Dict[Text, Any]
Log an event to a conversation.
format_bot_output
format_bot_output(message: BotUttered)-> Text
Format a bot response to be displayed in the history table.
latest_user_message
latest_user_message(events: List[Dict[Text, Any])]-> Optional[Dict[Text, Any]]
Return most recent user message.
is_listening_for_message
async is_listening_for_message(conversation_id: Text, endpoint: EndpointConfig)->bool
Check if the conversation is in need of a user message.
record_messages
async record_messages(endpoint: EndpointConfig, file_importer: TrainingDataImporter, conversation_id: Text = DEFAULT_SENDER_ID, max_message_limit: Optional[int]=None, skip_visualization:bool=False)->None
Read messages from the command line and print bot responses.
start_visualization
start_visualization(image_path: Text, port:int)->None
Add routes to serve the conversation visualization files.
run_interactive_learning
run_interactive_learning(file_importer: TrainingDataImporter, skip_visualization:bool=False, conversation_id: Text = uuid.uuid4().hex, server_args: Dict[Text, Any]=None)->None
Start the interactive learning with the model of the agent.
calc_true_wrapping_width
calc_true_wrapping_width(text: Text, monospace_wrapping_width:int)->int
Calculates a wrapping width that also works for CJK characters.
Chinese, Japanese and Korean characters are often broader than ascii characters. We need to account for that otherwise the wrapping doesn't work appropriately for long strings and the table overflows and creates errors.