Rasa 3.10.0 provider for local llm is giving error

My config file-

recipe: default.v1
language: en
pipeline:
- name: SingleStepLLMCommandGenerator
  llm:
    model: gemma     
    base_url: http://localhost:11434/v1 
    # api_type: ollama
  
  flow_retrieval:
    embeddings:
      provider: "huggingface_local"
      model: "BAAI/bge-small-en-v1.5"
      api_base: "http://localhost:11434/"
      model_kwargs: # used during instantiation
        device: "cpu"
      encode_kwargs: # used during inference
        normalize_embeddings: true
    # active: false



policies:
- name: FlowPolicy
- name: IntentlessPolicy
  llm:
    model: gemma     
    base_url: http://localhost:11434/v1 
  embeddings:
    provider: "huggingface_local"
    model: "BAAI/bge-small-en-v1.5"
    api_base: "http://localhost:11434/"
    model_kwargs: # used during instantiation
      device: "cpu"
    encode_kwargs: # used during inference
      normalize_embeddings: true
      # api_type: ollama
assistant_id: 20240916-212334-mean-developer

My error looks like this-

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.

2024-09-17 01:04:50 ERROR    rasa.utils.log_utils  - [error    ] nlg.llm.error                  error=Prov
  1. List item