These docs are for version 1.x of Rasa Open Source. ## User Guide - [Installation](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/installation/) - [Tutorial: Rasa Basics](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/rasa-tutorial/) - [Tutorial: Building Assistants](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/building-assistants/) - [Command Line Interface](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/command-line-interface/) - [Architecture](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/architecture/) - [Messaging and Voice Channels](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/messaging-and-voice-channels/) - [Testing Your Assistant](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/testing-your-assistant/) - [Setting up CI/CD](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/setting-up-ci-cd/) - [Validate Data](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/validate-files/) - [Configuring the HTTP API](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/configuring-http-api/) - [Deploying Your Rasa Assistant](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/how-to-deploy/) - [Cloud Storage](https://legacy-docs-v1.rasa.com/1.10.15/user-guide/cloud-storage/) ## NLU - [About](https://legacy-docs-v1.rasa.com/1.10.15/nlu/about/) - [Using NLU Only](https://legacy-docs-v1.rasa.com/1.10.15/nlu/using-nlu-only/) - [Training Data Format](https://legacy-docs-v1.rasa.com/1.10.15/nlu/training-data-format/) - [Language Support](https://legacy-docs-v1.rasa.com/1.10.15/nlu/language-support/) - [Choosing a Pipeline](https://legacy-docs-v1.rasa.com/1.10.15/nlu/choosing-a-pipeline/) - [Components](https://legacy-docs-v1.rasa.com/1.10.15/nlu/components/) - [Entity Extraction](https://legacy-docs-v1.rasa.com/1.10.15/nlu/entity-extraction/) ## Core - [About](https://legacy-docs-v1.rasa.com/1.10.15/core/about/) - [Stories](https://legacy-docs-v1.rasa.com/1.10.15/core/stories/) - [Domains](https://legacy-docs-v1.rasa.com/1.10.15/core/domains/) - [Responses](https://legacy-docs-v1.rasa.com/1.10.15/core/responses/) - [Actions](https://legacy-docs-v1.rasa.com/1.10.15/core/actions/) - [Reminders and External Events](https://legacy-docs-v1.rasa.com/1.10.15/core/reminders-and-external-events/) - [Policies](https://legacy-docs-v1.rasa.com/1.10.15/core/policies/) - [Slots](https://legacy-docs-v1.rasa.com/1.10.15/core/slots/) - [Forms](https://legacy-docs-v1.rasa.com/1.10.15/core/forms/) - [Retrieval Actions](https://legacy-docs-v1.rasa.com/1.10.15/core/retrieval-actions/) - [Interactive Learning](https://legacy-docs-v1.rasa.com/1.10.15/core/interactive-learning/) - [Fallback Actions](https://legacy-docs-v1.rasa.com/1.10.15/core/fallback-actions/) - [Knowledge Base Actions](https://legacy-docs-v1.rasa.com/1.10.15/core/knowledge-bases/) ## Conversation Design - [Dialogue Elements](https://legacy-docs-v1.rasa.com/1.10.15/dialogue-elements/dialogue-elements/) - [Small Talk](https://legacy-docs-v1.rasa.com/1.10.15/dialogue-elements/small-talk/) - [Completing Tasks](https://legacy-docs-v1.rasa.com/1.10.15/dialogue-elements/completing-tasks/) - [Guiding Users](https://legacy-docs-v1.rasa.com/1.10.15/dialogue-elements/guiding-users/) ## API Reference - [Action Server](https://legacy-docs-v1.rasa.com/1.10.15/api/action-server/) - [HTTP API](https://legacy-docs-v1.rasa.com/1.10.15/api/http-api/) - [Jupyter Notebooks](https://legacy-docs-v1.rasa.com/1.10.15/api/jupyter-notebooks/) - [Agent](https://legacy-docs-v1.rasa.com/1.10.15/api/agent/) - [Custom NLU Components](https://legacy-docs-v1.rasa.com/1.10.15/api/custom-nlu-components/#) - [Rasa SDK](https://legacy-docs-v1.rasa.com/1.10.15/api/rasa-sdk/) - [Events](https://legacy-docs-v1.rasa.com/1.10.15/api/events/) - [Tracker](https://legacy-docs-v1.rasa.com/1.10.15/api/tracker/) - [Tracker Stores](https://legacy-docs-v1.rasa.com/1.10.15/api/tracker-stores/) - [Event Brokers](https://legacy-docs-v1.rasa.com/1.10.15/api/event-brokers/) - [Lock Stores](https://legacy-docs-v1.rasa.com/1.10.15/api/lock-stores/) - [Training Data Importers](https://legacy-docs-v1.rasa.com/1.10.15/api/training-data-importers/) - [Featurization of Conversations](https://legacy-docs-v1.rasa.com/1.10.15/api/core-featurization/) - [TensorFlow Configuration](https://legacy-docs-v1.rasa.com/1.10.15/api/tensorflow_usage/) - [Migration Guide](https://legacy-docs-v1.rasa.com/1.10.15/migration-guide/) - [Rasa Open Source Change Log](https://legacy-docs-v1.rasa.com/1.10.15/changelog/) ## Migrate from (beta) - [Dialogflow](https://legacy-docs-v1.rasa.com/1.10.15/migrate-from/google-dialogflow-to-rasa/) - [Wit.ai](https://legacy-docs-v1.rasa.com/1.10.15/migrate-from/facebook-wit-ai-to-rasa/) - [LUIS](https://legacy-docs-v1.rasa.com/1.10.15/migrate-from/microsoft-luis-to-rasa/) - [IBM Watson](https://legacy-docs-v1.rasa.com/1.10.15/migrate-from/ibm-watson-to-rasa/) ## Reference - [Glossary](https://legacy-docs-v1.rasa.com/1.10.15/glossary/) # Custom NLU Components You can create a custom component to perform a specific task which NLU doesn’t currently offer (for example, sentiment analysis). Below is the specification of the [`rasa.nlu.components.Component`](https://legacy-docs-v1.rasa.com/1.10.15/api/custom-nlu-components/#rasa.nlu.components.Component "rasa.nlu.components.Component") class with the methods you’ll need to implement. Note: There is a detailed tutorial on building custom components [here](https://blog.rasa.com/enhancing-rasa-nlu-with-custom-components/). You can add a custom component to your pipeline by adding the module path. So if you have a module called `sentiment` containing a `SentimentAnalyzer` class: ``` pipeline: - name: "sentiment.SentimentAnalyzer" ``` Also be sure to read the section on the [Component Lifecycle](https://legacy-docs-v1.rasa.com/1.10.15/nlu/choosing-a-pipeline/#component-lifecycle). To get started, you can use this skeleton that contains the most important methods that you should implement: | | | | --- | --- | | ```
import typing
from typing import Any, Optional, Text, Dict, List, Type
from rasa.nlu.components import Component
from rasa.nlu.config import RasaNLUModelConfig
from rasa.nlu.training_data import Message, TrainingData
if typing.TYPE_CHECKING:
from rasa.nlu.model import Metadata
class MyComponent(Component):
"""A new component"""
@classmethod
def required_components(cls) -> List[Type[Component]]:
return []
defaults = {}
supported_language_list = None
not_supported_language_list = None
def __init__(self, component_config: Optional[Dict[Text, Any]] = None) -> None:
super().__init__(component_config)
def train(
self,
training_data: TrainingData,
config: Optional[RasaNLUModelConfig] = None,
**kwargs: Any,
) -> None:
pass
def process(self, message: Message, **kwargs: Any) -> None:
pass
def persist(self, file_name: Text, model_dir: Text) -> Optional[Dict[Text, Any]]:
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":
if cached_component:
return cached_component
else:
return cls(meta)
``` | Note: If you create a custom tokenizer you should implement the methods of `rasa.nlu.tokenizers.tokenizer.Tokenizer`. The `train` and `process` methods are already implemented and you simply need to overwrite the `tokenize` method. `train` and `process` will automatically add a special token `__CLS__` to the end of list of tokens, which is needed further down the pipeline. Note: If you create a custom featurizer you should return a sequence of features. E.g. your featurizer should return a matrix of size (number-of-tokens x feature-dimension). The feature vector of the `__CLS__` token should contain features for the complete message.