config.yml

# The config recipe.
# https://rasa.com/docs/rasa/model-configuration/
recipe: default.v1

# Configuration for Rasa NLU.
# https://rasa.com/docs/rasa/nlu/components/
language: zh

pipeline:
- name: "SpacyNLP"
  model: "zh_core_web_sm"
- name: "JiebaTokenizer"
  dictionary_path: "./jieba_userdict"
  # Flag to check whether to split intents
  "intent_tokenization_flag": False
  # Symbol on which intent should be split
  "intent_split_symbol": "_"
  # Regular expression to detect tokens
  "token_pattern": None
#- name: "CountVectorsFeaturizer"
#  # Analyzer to use, either 'word', 'char', or 'char_wb'
#  "analyzer": "word"
#  # Set the lower and upper boundaries for the n-grams
#  "min_ngram": 1
#  "max_ngram": 8
#  # Set the out-of-vocabulary token
#  "OOV_token": "_oov_"
#  # Whether to use a shared vocab
#  "use_shared_vocab": true
- name: LanguageModelFeaturizer
    # Name of the language model to use
  model_name: "bert"
    # Pre-Trained weights to be loaded
  model_weights: bert-base-chinese

    # An optional path to a directory from which
    # to load pre-trained model weights.
    # If the requested model is not found in the
    # directory, it will be downloaded and
    # cached in this directory for future use.
    # The default value of `cache_dir` can be
    # set using the environment variable
    # `TRANSFORMERS_CACHE`, as per the
    # Transformers library.
  cache_dir: "D:/pycharm project/pretrain_model/bert-base-chinese/"
- name: "DIETClassifier"
  epochs: 50

# Configuration for Rasa Core.
# https://rasa.com/docs/rasa/core/policies/
policies:
- name: MappingPolicy
- name: TEDPolicy
  epochs: 100
  max_history: 5
  constrain_similarities: True