notice

This is unreleased documentation for Rasa Documentation Main/Unreleased version.
For the latest released documentation, see the latest version (3.x).

Version: Main/Unreleased

rasa.nlu.utils.mitie_utils

MitieModel Objects

class MitieModel()

Wraps MitieNLP output to make it fingerprintable.

__init__

def __init__(
model_path: Path,
word_feature_extractor: Optional[
"mitie.total_word_feature_extractor"] = None
) -> None

Initializing MitieModel.

fingerprint

def fingerprint() -> Text

Fingerprints the model path.

Use a static fingerprint as we assume this only changes if the file path changes and want to avoid investigating the model in greater detail for now.

Returns:

Fingerprint for model.

MitieNLP Objects

@DefaultV1Recipe.register(
DefaultV1Recipe.ComponentType.MODEL_LOADER, is_trainable=False
)
class MitieNLP(GraphComponent)

Component which provides the common configuration and loaded model to others.

This is used to avoid loading the Mitie model multiple times. Instead the Mitie model is only loaded once and then shared by depending components.

get_default_config

@staticmethod
def get_default_config() -> Dict[Text, Any]

Returns default config (see parent class for full docstring).

__init__

def __init__(
path_to_model_file: Path,
extractor: Optional["mitie.total_word_feature_extractor"] = None
) -> None

Constructs a new language model from the MITIE framework.

required_packages

@staticmethod
def required_packages() -> List[Text]

Lists required dependencies (see parent class for full docstring).

create

@classmethod
def create(cls, config: Dict[Text, Any], model_storage: ModelStorage,
resource: Resource,
execution_context: ExecutionContext) -> MitieNLP

Creates component (see parent class for full docstring).

provide

def provide() -> MitieModel

Provides loaded MitieModel and path during training and inference.