Components

For clarity, we have renamed the pre-defined pipelines to reflect what they do rather than which libraries they use as of Rasa NLU 0.15. The tensorflow_embedding pipeline is now called supervised_embeddings, and spacy_sklearn is now known as pretrained_embeddings_spacy. Please update your code if you are using these.

This is a reference of the configuration options for every built-in component in Rasa NLU. If you want to build a custom component, check out Custom NLU Components.

Word Vector Sources

• MitieNLP
• SpacyNLP

Text Featurizers

• MitieFeaturizer
• SpacyFeaturizer
• ConveRTFeaturizer
• RegexFeaturizer
• CountVectorsFeaturizer

Intent Classifiers

• MitieIntentClassifier
• SklearnIntentClassifier
• EmbeddingIntentClassifier
• KeywordIntentClassifier

Selectors

• Response Selector

Tokenizers

• WhitespaceTokenizer
• JiebaTokenizer
• MitieTokenizer
• SpacyTokenizer
• ConveRTTokenizer

Entity Extractors

• MitieEntityExtractor
• SpacyEntityExtractor
• EntitySynonymMapper
• CRFEntityExtractor
• DucklingHTTPExtractor

Example Configuration

MitieNLP

Short: MITIE initializer

Description: Initializes mitie structures. Every mitie component relies on this, hence this should be put at the beginning of every pipeline that uses any mitie components.

Configuration:

pipeline:
- name: "MitieNLP"
  model: "data/total_word_feature_extractor.dat"

SpacyNLP

Short: spacy language initializer

Description: Initializes spacy structures. Every spacy component relies on this, hence this should be put at the beginning of every pipeline that uses any spacy components.

Configuration:

pipeline:
- name: "SpacyNLP"
  model: "en_core_web_md"
  case_sensitive: false

RegexFeaturizer

Short: regex feature creation to support intent and entity classification

Outputs: text_features and tokens.pattern

Configuration:

pipeline:
- name: "RegexFeaturizer"

CountVectorsFeaturizer

Short: Creates bag-of-words representation of user message and label (intent and response) features

Outputs: nothing

Configuration:

pipeline:
- name: "CountVectorsFeaturizer"
  use_shared_vocab: false
  analyzer: 'word'
  min_df: 1
  max_df: 1.0
  min_ngram: 1
  max_ngram: 1
  lowercase: true

Conclusion

These components help create a robust and efficient NLU pipeline within Rasa. For more details, consider exploring the official Rasa documentation.