I want my bot to always say hi when someone writes to it. To achieve this I created a boolean slot called slot_has_greeted and tried to create stories depending on the value of this slot. But it is not working and I don’t know why. I made a small test to see if I was doing some wrong, but the result was the same.
- story: Greeting
steps:
- slot_was_set:
- slot_common_has_greeted: false
- intent: intent_common_greet
- action: utter_teste_true
- story: Greeting
steps:
- slot_was_set:
- slot_common_has_greeted: true
- intent: intent_common_greet
- action: utter_teste_false
- story: Greeting
steps:
- slot_was_set:
- slot_common_has_greeted: null
- intent: intent_common_greet
- action: utter_teste_null
- action: action_common_greet
- slot_was_set:
- slot_common_has_greeted: true
When I write hi, it correctly calls the utter_teste_null and sets the slot to true. But when I write hi again it calls the utter_teste_null again. I expected it to call utter_teste_true. I’m not sure if I am doing something wrong or even if my configs are influencing this behavior. Could someone help me?
My config file (I’m going to tweek it now, starting from the default values): language: pt pipeline: - name: WhitespaceTokenizer - name: RegexFeaturizer - name: LexicalSyntacticFeaturizer - name: CountVectorsFeaturizer - name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 - name: DIETClassifier epochs: 100 constrain_similarities: true model_confidence: linear_norm - name: EntitySynonymMapper - name: ResponseSelector constrain_similarities: true model_confidence: linear_norm epochs: 100 # Fallback when the intent confidence is low. - name: FallbackClassifier threshold: 0.3 ambiguity_threshold: 0.1 policies: # Fallback when the story confidence is low. - name: RulePolicy core_fallback_threshold: 0.3 core_fallback_action_name: “action_listen” enable_fallback_prediction: True - max_history: 6 name: AugmentedMemoizationPolicy - name: TEDPolicy max_history: 10 epochs: 20 constrain_similarities: true model_confidence: linear_norm batch_size: - 32 - 64