Custom rasa component returning string to the next component

Rasa Open Source
1

I am trying to create a rasa chatbot where I want to add a custom component for spell checking. In this component, I will receive the message text, then do spelling correction and then return the corrected string for tokenization. What should I write in provides = [] to return a text to the next component?

2

Hi @tonysinghmss. Do you want to correct the entire input message before it’s tokenised? In that case the custom component implementation would be a bit simpler. I quickly put together an example with autocorrect:

from rasa.nlu.components import Component
import typing
from typing import Any, Optional, Text, Dict

if typing.TYPE_CHECKING:
    from rasa.nlu.model import Metadata


class SpellChecker(Component):
    """A new component"""

    # Defines what attributes the pipeline component will
    # provide when called. The listed attributes
    # should be set by the component on the message object
    # during test and train, e.g.
    # ```message.set("entities", [...])```
    provides = ['text'] #set as text but shouldn't really have much influence on the component

    # Which attributes on a message are required by this
    # component. e.g. if requires contains "tokens", than a
    # previous component in the pipeline needs to have "tokens"
    # within the above described `provides` property.
    requires = []

    # Defines the default configuration parameters of a component
    # these values can be overwritten in the pipeline configuration
    # of the model. The component should choose sensible defaults
    # and should be able to create reasonable results with the defaults.
    defaults = {}

    # Defines what language(s) this component can handle.
    # This attribute is designed for instance method: `can_handle_language`.
    # Default value is None which means it can handle all languages.
    # This is an important feature for backwards compatibility of components.
    language_list = None

    def __init__(self, component_config=None):
        super(SpellChecker, self).__init__(component_config)

    def train(self, training_data, cfg, **kwargs):
        """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:`components.Component.pipeline_init`
        of ANY component and
        on any context attributes created by a call to
        :meth:`components.Component.train`
        of components previous to this one."""
        pass

    def process(self, message, **kwargs):
        """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:`components.Component.pipeline_init`
        of ANY component and
        on any context attributes created by a call to
        :meth:`components.Component.process`
        of components previous to this one."""
        from autocorrect import spell

        mesg = message.text #get original message
        text = spell(mesg) #correct the message with autocorrect
        message.text = text #set the corrected message as the message for the next components to process


    def persist(self, file_name: Text, model_dir: Text) -> Optional[Dict[Text, Any]]:
        """Persist this component to disk for future loading."""

        pass

    @classmethod
    def 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."""

        if cached_component:
            return cached_component
        else:
            return cls(meta)

In my pipeline configuration this component then comes first. For example:

language: en
pipeline:
- name: spellcheck.SpellChecker
- name: "WhitespaceTokenizer"
- name: "RegexFeaturizer"
- name: "CRFEntityExtractor"
- name: "EntitySynonymMapper"
- name: "CountVectorsFeaturizer"
- name: "EmbeddingIntentClassifier"
  intent_tokenization_flag: true
  intent_split_symbol: "+"

I hope it helps. Let me know if you have any issues with the implementation

1 Like
3

Thanks @Juste Can I get the list of all possible values that can be used in provides list and required list. It will give me and others clarity on what to use and when to use. You might update this in your documentation as well.

4

Hi Juste, could you tell me how to load the Python module autocorrect when use Docker?