Can't train the model as story gets long

Rasa Open Source
1

Hi there! So, I need to make a questionnaire which includes about 40 questions, but I cannot train a model after I add more than 7 actions into story. When I have just 8 actions, the training starts, but gets stuck when 95 % of story blocks are processed. Please advice me, what can I do to make a large questionnaire?

This is my config:

language: en
pipeline:
- name: WhitespaceTokenizer
  intent_tokenization_flag: True
  intent_split_symbol: "+"
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer
  analyzer: char_wb
  min_ngram: 1
  max_ngram: 4
- name: DIETClassifier
  epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector
  epochs: 100
- name: FallbackClassifier
  threshold: 0.7
- name: components.nltk_sentiment.SentimentAnalyzer
#- name: components.HFSentiment.HuggingFaceSentiment
policies:
- name: MemoizationPolicy
- name: TEDPolicy
  max_history: 5
  epochs: 100
- name: RulePolicy
  core_fallback_threshold: 0.4
2

You should use forms for this.

3

I appreciate the information and advice you have shared. I will try to figure it out for more.