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

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"
  # language model to load
  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"
  # language model to load
  model: "en_core_web_md"
  case_sensitive: false

Featurizers

MitieFeaturizer

Short: MITIE intent featurizer

Description: Creates feature for intent classification using the MITIE featurizer.

Configuration:

pipeline:
- name: "MitieFeaturizer"

SpacyFeaturizer

Short: spacy intent featurizer

Description: Creates feature for intent classification using the spacy featurizer.

Configuration:

pipeline:
- name: "SpacyFeaturizer"
  ner_feature_vectors: True

NGramFeaturizer

Short: Appends char-ngram features to feature vector

Configuration:

pipeline:
- name: "NGramFeaturizer"
  max_number_of_ngrams: 10

RegexFeaturizer

Short: regex feature creation to support intent and entity classification

Configuration:

pipeline:
- name: "RegexFeaturizer"

CountVectorsFeaturizer

Short: Creates bag-of-words representation of user message.

Configuration:

pipeline:
- name: "CountVectorsFeaturizer"
  use_shared_vocab: False,
  analyzer: 'word'
  token_pattern: r'(?u)\b\w\w+\b'
  min_df: 1
  max_df: 1.0
  min_ngram: 1
  max_ngram: 1
  lowercase: true
  OOV_token: None

Intent Classifiers

KeywordIntentClassifier

Short: Simple keyword matching intent classifier.

Description: This classifier is mostly used as a placeholder.

MitieIntentClassifier

Short: MITIE intent classifier

Configuration:

pipeline:
- name: "MitieIntentClassifier"

SklearnIntentClassifier

Short: sklearn intent classifier

Configuration:

pipeline:
- name: "SklearnIntentClassifier"
  C: [1, 2, 5, 10, 20, 100]
  kernels: ["linear"]

EmbeddingIntentClassifier

Short: Embedding intent classifier

Configuration:

pipeline:
- name: "EmbeddingIntentClassifier"

Selectors

Response Selector

Short: Response Selector

Description: Response Selector component can be used to build a response retrieval model.

Configuration:

pipeline:
- name: "ResponseSelector"
  retrieval_intent: None

Tokenizers

WhitespaceTokenizer

Short: Tokenizer using whitespaces as a separator

Configuration:

pipeline:
- name: "WhitespaceTokenizer"
  case_sensitive: false

JiebaTokenizer

Short: Tokenizer using Jieba for Chinese language

Configuration:

pipeline:
- name: "JiebaTokenizer"
  dictionary_path: "path/to/custom/dictionary/dir"

MitieTokenizer

Configuration:

pipeline:
- name: "MitieTokenizer"

SpacyTokenizer

Configuration:

pipeline:
- name: "SpacyTokenizer"

Entity Extractors

MitieEntityExtractor

Short: MITIE entity extraction

Configuration:

pipeline:
- name: "MitieEntityExtractor"

SpacyEntityExtractor

Short: spaCy entity extraction

Configuration:

pipeline:
- name: "SpacyEntityExtractor"
  dimensions: ["PERSON", "LOC", "ORG", "PRODUCT"]

EntitySynonymMapper

Short: Maps synonymous entity values to the same value.

CRFEntityExtractor

Short: conditional random field entity extraction

Configuration:

pipeline:
- name: "CRFEntityExtractor"
  features: [["low", "title"], ["bias", "suffix3"]]
  BILOU_flag: true
  max_iterations: 50
  L1_c: 0.1
  L2_c: 0.1

DucklingHTTPExtractor

Short: Duckling entity extraction.

Configuration:

pipeline:
- name: "DucklingHTTPExtractor"
  url: "http://localhost:8000"
  dimensions: ["time", "number", "amount-of-money", "distance"]
  locale: "de_DE"

👋 I can help you get started with Rasa and answer your technical questions.