diff --git a/clearml_serving/preprocess/preprocess_template.py b/clearml_serving/preprocess/preprocess_template.py
index 274a8c3..7fda339 100644
--- a/clearml_serving/preprocess/preprocess_template.py
+++ b/clearml_serving/preprocess/preprocess_template.py
@@ -12,7 +12,8 @@ class Preprocess(object):
 
     def __init__(self):
         # set internal state, this will be called only once. (i.e. not per request)
-        pass
+        # it will also set the internal model_endpoint to reference the specific model endpoint object being served
+        self.model_endpoint = None  # type: clearml_serving.serving.endpoints.ModelEndpoint
 
     def load(self, local_file_name: str) -> Optional[Any]:  # noqa
         """
diff --git a/clearml_serving/serving/model_request_processor.py b/clearml_serving/serving/model_request_processor.py
index 5d7d271..8380cdc 100644
--- a/clearml_serving/serving/model_request_processor.py
+++ b/clearml_serving/serving/model_request_processor.py
@@ -228,7 +228,8 @@ class ModelRequestProcessor(object):
             if len(models) > 1:
                 print("Warning: Found multiple Models for \'{}\', selecting id={}".format(model_query, models[0].id))
             endpoint.model_id = models[0].id
-        elif not endpoint.model_id:
+        elif not endpoint.model_id and endpoint.engine_type != "custom":
+            # if the "engine_type" is "custom" it might be there is no model_id attached
             print("Warning: No Model provided for \'{}\'".format(url))
 
         # upload as new artifact
diff --git a/clearml_serving/serving/preprocess_service.py b/clearml_serving/serving/preprocess_service.py
index 0f1195c..5c08054 100644
--- a/clearml_serving/serving/preprocess_service.py
+++ b/clearml_serving/serving/preprocess_service.py
@@ -71,6 +71,8 @@ class BasePreprocessRequest(object):
         Preprocess.send_request = BasePreprocessRequest._preprocess_send_request
         # create preprocess class
         self._preprocess = Preprocess()
+        # update the model endpoint on the instance we created
+        self._preprocess.model_endpoint = self.model_endpoint
         # custom model load callback function
         if callable(getattr(self._preprocess, 'load', None)):
             self._model = self._preprocess.load(self._get_local_model_file())
@@ -129,6 +131,8 @@ class BasePreprocessRequest(object):
         pass
 
     def _get_local_model_file(self):
+        if not self.model_endpoint.model_id:
+            return None
         model_repo_object = Model(model_id=self.model_endpoint.model_id)
         return model_repo_object.get_local_copy()