Rasa Pro coexistence issue

I had a codebase which was nlu based built using rasa community version. Now I have a developer license and I am migrating my code to llm based. My pipeline in config.yml looks like this

   - name: WhitespaceTokenizer
   - name: RegexFeaturizer
   - name: LexicalSyntacticFeaturizer
   - name: CountVectorsFeaturizer
   - name: CountVectorsFeaturizer
     analyzer: char_wb
     min_ngram: 1
     max_ngram: 4
   - name: CRFEntityExtractor
   - name: DIETClassifier
     epochs: 100
     constrain_similarities: true
   - name: EntitySynonymMapper
   - name: ResponseSelector
     epochs: 100
     constrain_similarities: true
   - name: FallbackClassifier
     threshold: 0.5
     ambiguity_threshold: 0.1
   - name: LogisticRegressionClassifier
   - name: NLUCommandAdapter
   - name: IntentBasedRouter
     nlu_entry:
       sticky:
         // some sticky intents
       non_sticky:
         - affirm
         - deny
         - goodbye
       calm_entry:
         sticky:
           - greet
           - mood_great
           - mood_unhappy
           - bot_challenge
       fallback_intent: nlu_fallback

   - name: SingleStepLLMCommandGenerator
     llm:
       model_group: rasa_command_generation_model
     flow_retrieval:
       active: false

Still while doing rasa train getting below error

2025-05-06 17:11:24 ERROR rasa.engine.validation - [error ] (β€˜The configuration of the IntentBasedRouter is invalid. Please check the documentation.’,) event_key=validation.coexistance.invalid_configuration

Unable to fix the issue. Requesting some understanding on this.

Hi, @Jyoti_Prakash_Behera thank you for your message. Could you please check that nlu_entry and calm_entry are on the same level, as mentioned in this document: Coexistence Routers | Rasa Documentation

nlu_entry:
...
calm_entry:

Let me know if this helped fix the error.

This was the exact issue. Thank you so much for the response. :slight_smile:

1 Like