RASA CALM -Slots value are not reflected in actions methods though seen in rasa server logs

Rasa Pro CALM
1

I am experiencing the below issue where, in Rasa server logs I can see slot values assigned properly but when I try to get slot values with tracker.getslot in action methhos I get the value as None. I have given enough of nlu examples and trained model. Please see logs below. Any suggestions how to solve this issue? 024-09-25 19:41:43 [INFO ] [info ] llm_command_generator.predict_commands.finished commands=[StartFlowCommand(flow=‘search_note_flow_with_content’), SetSlotCommand(name=‘note_query’, value=‘dance’)] inaction method,t wont be available in slot or entity but is there in text 2024-09-25 19:41:43,579 - root - INFO - note text is Give me notes on dance 2024-09-25 19:41:43,579 - root - INFO - No note query found in entity and Note query in Slot is , None

2

This is my config.yml. recipe: default.v1

language: en pipeline:

  • name: SpacyNLP model: “en_core_web_md”
  • name: SpacyTokenizer
  • name: RegexFeaturizer case_sensitive: False regex_features:
    • name: reminder_type pattern: “(doctor('s|s)? appointment|appointment with (the |a )?doctor|checkup|medical visit|appointment|medication|task|meeting|call|birthday|anniversary| work|gym|dentist|market|school|bills|rents)”
    • name: date pattern: “\d{4}-\d{2}-\d{2}”
    • name: time pattern: “\d{1,2}:\d{2} (AM|PM)|july 10th”
    • name:duration
    • pattern: “(today|tomorrow|this week|next week|this month |next month|next year|this year)”
    • name: month_name
    • pattern: “(january|february|march|april|may|june|july|august|september|october|november|december)” use_lookup_tables: True # Add this line
  • name: SpacyFeaturizer
  • name: LexicalSyntacticFeaturizer
  • name: CountVectorsFeaturizer
  • name: DIETClassifier constrain_similarities: true epochs: 100
  • name: EntitySynonymMapper
  • name: DucklingEntityExtractor url: http://localhost:8000 dimensions:
    • “time”
    • “dates”
    • “duration” timezone: “Asia/Kolkata” # Set according to your location locale: “en_IN”
  • name: LLMCommandGenerator llm: model_name: gpt-4o request_timeout: 7 max_tokens: 256 prompt: prompts/command-generator.jinja2

policies:

  • name: FlowPolicy confidence_threshold: 0.6