I am trying to deploy a model to a Managed Online Endpoint using:

blue_deployment = ManagedOnlineDeployment(name='blue',
                                        endpoint_name='diabetes-online-endpoint',
                                        model=loaded_model,
                                        )

ml_client.online_deployments.begin_create_or_update(blue_deployment, local=True)    

To which I am getting below error:

MlException: ['Non-string passed to RegistryStr for model', 'Non-string passed to ArmStr for model', "'XGBClassifier' object has no attribute '_intellectual_property'"]  

I've loaded an already registered model in the workspace using:

loaded_model = mlflow.xgboost.load_model('models:/diabetes-prediction/1')

The reason I've loaded using xgboost flavour is because it's an XGBoost classifier model and the MLmodel too says so:

artifact_path: model
flavors:
  python_function:
    data: model.xgb
    env:
      conda: conda.yaml
      virtualenv: python_env.yaml
    loader_module: mlflow.xgboost
    python_version: 3.8.20
  xgboost:
    code: null
    data: model.xgb
    model_class: xgboost.sklearn.XGBClassifier
    model_format: xgb
    xgb_version: 2.1.4
mlflow_version: 2.17.2
model_size_bytes: 425440
model_uuid: 0863a662a4c9434093c017bc86325
run_id: tough_floor_l2290mxbms_1
signature:
  inputs: '[{"type": "tensor", "tensor-spec": {"dtype": "float64", "shape": [-1, 8]}}]'
  outputs: '[{"type": "tensor", "tensor-spec": {"dtype": "int64", "shape": [-1]}}]'
  params: null
utc_time_created: '2025-03-13 04:38:29.342371'


                                  

Can someone please let me know where I am going wrong.