SIENTIAPDE-1174

SIENTIAPDE-1174 Update replica count and enhance logging in MLFlow

- Changed replicaCount in values.yaml from 3 to 1 for reduced resource usage.
- Added debug logging for prediction response data in MLFlow to improve traceability.

laborious/utils/repository/model_repository.py

@@ -68,7 +68,7 @@ class MLFlowRepository():
         try:
             start_time = datetime.now()
             data = self.model_serving.get_cached_predict(
-                model_name, data, model_retention)[0:1]
+                model_name, data, model_retention)
 
             end_time = datetime.now()
             data = pd.DataFrame(data, columns=['prediction'])