Version: 3.x


EventTypeError Objects

class EventTypeError(RasaCoreException, ValueError)

Represents an error caused by a Rasa Core event not being of the expected type.

Checkpoint Objects

class Checkpoint()

Represents places where trackers split.

This currently happens if

  • users place manual checkpoints in their stories
  • have or statements for intents in their stories.


def __init__(name: Text, conditions: Optional[Dict[Text, Any]] = None) -> None

Creates Checkpoint.


  • name - Name of the checkpoint.
  • conditions - Slot conditions for this checkpoint.


def filter_trackers(
trackers: List[DialogueStateTracker]) -> List[DialogueStateTracker]

Filters out all trackers that do not satisfy the conditions.

StoryStep Objects

class StoryStep()

A StoryStep is a section of a story block between two checkpoints.

NOTE: Checkpoints are not only limited to those manually written in the story file, but are also implicitly created at points where multiple intents are separated in one line by chaining them with "OR"s.


def __init__(block_name: Text,
start_checkpoints: Optional[List[Checkpoint]] = None,
end_checkpoints: Optional[List[Checkpoint]] = None,
events: Optional[List[Union[Event, List[Event]]]] = None,
source_name: Optional[Text] = None) -> None

Initialise StoryStep default attributes.


def as_story_string(flat: bool = False, e2e: bool = False) -> Text

Returns a story as a string.


def is_action_unlikely_intent(event: Event) -> bool

Checks if the executed action is a action_unlikely_intent.


def is_action_session_start(event: Event) -> bool

Checks if the executed action is a action_session_start.


def explicit_events(domain: Domain,
should_append_final_listen: bool = True) -> List[Event]

Returns events contained in the story step including implicit events.

Not all events are always listed in the story dsl. This includes listen actions as well as implicitly set slots. This functions makes these events explicit and returns them with the rest of the steps events.

RuleStep Objects

class RuleStep(StoryStep)

A Special type of StoryStep representing a Rule.


def get_rules_condition() -> List[Union[Event, List[Event]]]

Returns a list of events forming a condition of the Rule.


def get_rules_events() -> List[Union[Event, List[Event]]]

Returns a list of events forming the Rule, that are not conditions.


def add_event_as_condition(event: Event) -> None

Adds event to the Rule as part of its condition.


  • event - The event to be added.

Story Objects

class Story()


def from_events(events: List[Event],
story_name: Optional[Text] = None) -> "Story"

Create a story from a list of events.

StoryGraph Objects

class StoryGraph()

Graph of the story-steps pooled from all stories in the training data.


def __hash__() -> int

Return hash for the story step.


Hash of the story step.


def fingerprint() -> Text

Returns a unique hash for the stories which is stable across python runs.


fingerprint of the stories


def ordered_steps() -> List[StoryStep]

Returns the story steps ordered by topological order of the DAG.


def cyclic_edges() -> List[Tuple[Optional[StoryStep], Optional[StoryStep]]]

Returns the story steps ordered by topological order of the DAG.


def merge(other: Optional["StoryGraph"]) -> "StoryGraph"

Merge two StoryGraph together.


def overlapping_checkpoint_names(cps: List[Checkpoint],
other_cps: List[Checkpoint]) -> Set[Text]

Find overlapping checkpoints names.


def with_cycles_removed() -> "StoryGraph"

Create a graph with the cyclic edges removed from this graph.


def order_steps(
story_steps: List[StoryStep]) -> Tuple[deque, List[Tuple[Text, Text]]]

Topological sort of the steps returning the ids of the steps.


def topological_sort(
graph: Dict[Text, Set[Text]]) -> Tuple[deque, List[Tuple[Text, Text]]]

Creates a top sort of a directed graph. This is an unstable sorting!

The function returns the sorted nodes as well as the edges that need to be removed from the graph to make it acyclic (and hence, sortable).

The graph should be represented as a dictionary, e.g.:

>>> example_graph = { ... "a": set("b", "c", "d"), ... "b": set(), ... "c": set("d"), ... "d": set(), ... "e": set("f"), ... "f": set()} >>> StoryGraph.topological_sort(example_graph) (deque([u'e', u'f', u'a', u'c', u'd', u'b']), [])


def is_empty() -> bool

Checks if StoryGraph is empty.


def __repr__() -> Text

Returns text representation of object.


def generate_id(prefix: Text = "", max_chars: Optional[int] = None) -> Text

Generate a random UUID.


  • prefix - String to prefix the ID with.
  • max_chars - Maximum number of characters.


Generated random UUID.