Version: 2.0.x



find_unavailable_packages(package_names: List[Text]) -> Set[Text]

Tries to import all package names and returns the packages where it failed.


  • package_names - The package names to import.


Package names that could not be imported.


validate_requirements(component_names: List[Optional[Text]]) -> None

Validates that all required importable python packages are installed.


  • InvalidConfigError - If one of the component names is None, likely indicates that a custom implementation is missing this property or that there is an invalid configuration file that we did not catch earlier.


  • component_names - The list of component names.


validate_empty_pipeline(pipeline: List["Component"]) -> None

Ensures the pipeline is not empty.


  • pipeline - the list of the :class:rasa.nlu.components.Component.


validate_only_one_tokenizer_is_used(pipeline: List["Component"]) -> None

Validates that only one tokenizer is present in the pipeline.


  • pipeline - the list of the :class:rasa.nlu.components.Component.


validate_required_components(pipeline: List["Component"]) -> None

Validates that all required components are present in the pipeline.


  • pipeline - The list of the :class:rasa.nlu.components.Component.


validate_pipeline(pipeline: List["Component"]) -> None

Validates the pipeline.


  • pipeline - The list of the :class:rasa.nlu.components.Component.


any_components_in_pipeline(components: Iterable[Text], pipeline: List["Component"])

Check if any of the provided components are listed in the pipeline.


  • components - A list of :class:rasa.nlu.components.Components to check.
  • pipeline - A list of :class:rasa.nlu.components.Components.


True if any of the components are in the pipeline, else False.


validate_required_components_from_data(pipeline: List["Component"], data: TrainingData) -> None

Validates that all components are present in the pipeline based on data.


  • pipeline - The list of the :class:rasa.nlu.components.Components.
  • data - The :class:rasa.shared.nlu.training_data.training_data.TrainingData.

MissingArgumentError Objects

class MissingArgumentError(ValueError)

Raised when not all parameters can be filled from the context / config.


  • message - explanation of which parameter is missing

UnsupportedLanguageError Objects

class UnsupportedLanguageError(RasaException)

Raised when a component is created but the language is not supported.


  • component - component name
  • language - language that component doesn't support

ComponentMetaclass Objects

class ComponentMetaclass(type)

Metaclass with name class property.


| @property
| name(cls)

The name property is a function of the class - its name.

Component Objects

class Component(, metaclass=ComponentMetaclass)

A component is a message processing unit in a pipeline.

Components are collected sequentially in a pipeline. Each component is called one after another. This holds for initialization, training, persisting and loading the components. If a component comes first in a pipeline, its methods will be called first.

E.g. to process an incoming message, the process method of each component will be called. During the processing (as well as the training, persisting and initialization) components can pass information to other components. The information is passed to other components by providing attributes to the so called pipeline context. The pipeline context contains all the information of the previous components a component can use to do its own processing. For example, a featurizer component can provide features that are used by another component down the pipeline to do intent classification.


| @property
| name() -> Text

Access the class's property name from an instance.


| @classmethod
| required_components(cls) -> List[Type["Component"]]

Specify which components need to be present in the pipeline.


The list of class names of required components.


| @classmethod
| required_packages(cls) -> List[Text]

Specify which python packages need to be installed.

E.g. ["spacy"]. More specifically, these should be importable python package names e.g. sklearn and not package names in the dependencies sense e.g. scikit-learn

This list of requirements allows us to fail early during training if a required package is not installed.


The list of required package names.


| @classmethod
| load(cls, meta: Dict[Text, Any], model_dir: Optional[Text] = None, model_metadata: Optional["Metadata"] = None, cached_component: Optional["Component"] = None, **kwargs: Any, ,) -> "Component"

Load this component from file.

After a component has been trained, it will be persisted by calling persist. When the pipeline gets loaded again, this component needs to be able to restore itself. Components can rely on any context attributes that are created by :meth:components.Component.create calls to components previous to this one.


  • meta - Any configuration parameter related to the model.
  • model_dir - The directory to load the component from.
  • model_metadata - The model's :class:rasa.nlu.model.Metadata.
  • cached_component - The cached component.


the loaded component


| @classmethod
| create(cls, component_config: Dict[Text, Any], config: RasaNLUModelConfig) -> "Component"

Creates this component (e.g. before a training is started).

Method can access all configuration parameters.


  • component_config - The components configuration parameters.
  • config - The model configuration parameters.


The created component.


| provide_context() -> Optional[Dict[Text, Any]]

Initialize this component for a new pipeline.

This function will be called before the training is started and before the first message is processed using the interpreter. The component gets the opportunity to add information to the context that is passed through the pipeline during training and message parsing. Most components do not need to implement this method. It's mostly used to initialize framework environments like MITIE and spacy (e.g. loading word vectors for the pipeline).


The updated component configuration.


| train(training_data: TrainingData, config: Optional[RasaNLUModelConfig] = None, **kwargs: Any, ,) -> None

Train this component.

This is the components chance to train itself provided with the training data. The component can rely on any context attribute to be present, that gets created by a call to :meth:rasa.nlu.components.Component.create of ANY component and on any context attributes created by a call to :meth:rasa.nlu.components.Component.train of components previous to this one.


training_data: The :class:rasa.shared.nlu.training_data.training_data.TrainingData.

  • config - The model configuration parameters.


| process(message: Message, **kwargs: Any) -> None

Process an incoming message.

This is the components chance to process an incoming message. The component can rely on any context attribute to be present, that gets created by a call to :meth:rasa.nlu.components.Component.create of ANY component and on any context attributes created by a call to :meth:rasa.nlu.components.Component.process of components previous to this one.


  • message - The :class:rasa.shared.nlu.training_data.message.Message to process.


| persist(file_name: Text, model_dir: Text) -> Optional[Dict[Text, Any]]

Persist this component to disk for future loading.


  • file_name - The file name of the model.
  • model_dir - The directory to store the model to.


An optional dictionary with any information about the stored model.


| @classmethod
| cache_key(cls, component_meta: Dict[Text, Any], model_metadata: "Metadata") -> Optional[Text]

This key is used to cache components.

If a component is unique to a model it should return None. Otherwise, an instantiation of the component will be reused for all models where the metadata creates the same key.


  • component_meta - The component configuration.
  • model_metadata - The component's :class:rasa.nlu.model.Metadata.


A unique caching key.


| prepare_partial_processing(pipeline: List["Component"], context: Dict[Text, Any]) -> None

Sets the pipeline and context used for partial processing.

The pipeline should be a list of components that are previous to this one in the pipeline and have already finished their training (and can therefore be safely used to process messages).


  • pipeline - The list of components.
  • context - The context of processing.


| partially_process(message: Message) -> Message

Allows the component to process messages during training (e.g. external training data).

The passed message will be processed by all components previous to this one in the pipeline.


  • message - The :class:rasa.shared.nlu.training_data.message.Message to process.


The processed :class:rasa.shared.nlu.training_data.message.Message.


| @classmethod
| can_handle_language(cls, language: Hashable) -> bool

Check if component supports a specific language.

This method can be overwritten when needed. (e.g. dynamically determine which language is supported.)


  • language - The language to check.


True if component can handle specific language, False otherwise.

ComponentBuilder Objects

class ComponentBuilder()

Creates trainers and interpreters based on configurations.

Caches components for reuse.


| load_component(component_meta: Dict[Text, Any], model_dir: Text, model_metadata: "Metadata", **context: Any, ,) -> Component

Loads a component.

Tries to retrieve a component from the cache, else calls load to create a new component.


component_meta: The metadata of the component to load in the pipeline. model_dir: The directory to read the model from. model_metadata (Metadata): The model's :class:rasa.nlu.model.Metadata.


The loaded component.


| create_component(component_config: Dict[Text, Any], cfg: RasaNLUModelConfig) -> Component

Creates a component.

Tries to retrieve a component from the cache, calls create to create a new component.


  • component_config - The component configuration.
  • cfg - The model configuration.


The created component.


| create_component_from_class(component_class: Type[C], **cfg: Any) -> C

Create a component based on a class and a configuration.

Mainly used to make use of caching when instantiating component classes.