Can we use rasa command generation model and other model at the same time?

[reyna789 (reyna kearns)]

@botNotResponding

Hello guys I am new to rasa. I have a query can anyone please share if you know Can I use the rasa command generation model along with the existing model (groq) which I am using. I want to use it because here rephrasing utterances is not happening utter_greet_user: - text: “Hi, how can I assist you?” metadata: rephrase: True rephrase_prompt: | The following is a conversation with an AI assistant built with Rasa. The assistant is cheerful and ready to help, making the user feel welcome. The user is starting the conversation, and the assistant should greet them warmly. Context / previous conversation with the user: {{history}} {{current_input}} Suggested AI Response

config file recipe: default.v1 language: en pipeline:

• name: NLUCommandAdapter
• name: MultiStepLLMCommandGenerator llm: provider: groq model: llama-3.3-70b-specdec

api_base: ‘http://localhost:11434’

flow_retrieval: embeddings: type: “huggingface” model_name: “sentence-transformers/all-mpnet-base-v2” model_kwargs: device: “cpu” encode_kwargs: normalize_embeddings: True

policies: Arizona dmv

• name: FlowPolicy
• name: EnterpriseSearchPolicy vector_store: type: “faiss” source: “xxxxxxxxxxxxxxxxxxxxxxxx\docs” embeddings: type: “huggingface” model_name: “sentence-transformers/all-mpnet-base-v2” llm: provider: groq model: llama-3.3-70b-specdec prompt: “xxxxxxxxxxxxxxxxxxxxxxxx\custom_prompt.txt” max_history: 2 max_messages_in_query: 3

Combine Rasa’s command generation with your Groq LLM by placing the NLUCommandAdapter after your NLU pipeline but before the MultiStepLLMCommandGenerator. Ensure consistent LLM configurations for both, use a custom prompt, and configure flow_retrieval for context. Include relevant policies and use rasa shell --debug for troubleshooting.