Update utils/vulnerability_classifier.py

utils/vulnerability_classifier.py

@@ -75,6 +75,9 @@ def load_vulnerabilityClassifier(config_file:str = None, classifier_name:str = N
     found then will look for configfile, else raise error.
     Return: document classifier model
     """
+
+    # If no classifier given
+    
     if not classifier_name:
         if not config_file:
             logging.warning("Pass either model name or config file")
@@ -84,6 +87,7 @@ def load_vulnerabilityClassifier(config_file:str = None, classifier_name:str = N
             classifier_name = config.get('vulnerability','MODEL')
     
     logging.info("Loading vulnerability classifier")
+    
     # we are using the pipeline as the model is multilabel and DocumentClassifier 
     # from Haystack doesnt support multilabel
     # in pipeline we use 'sigmoid' to explicitly tell pipeline to make it multilabel
@@ -93,7 +97,7 @@ def load_vulnerabilityClassifier(config_file:str = None, classifier_name:str = N
     #                     task="text-classification",
     #                     top_k = None)
 
-    # # Download model from HF Hub
+    # Download model from HF Hub
     doc_classifier = SetFitModel.from_pretrained("leavoigt/vulnerability_multilabel")
     
     # doc_classifier = pipeline("text-classification", 
@@ -112,8 +116,7 @@ def vulnerability_classification(haystack_doc:pd.DataFrame,
     """
     Text-Classification on the list of texts provided. Classifier provides the 
     most appropriate label for each text. these labels are in terms of if text 
-    belongs to which particular Sustainable Devleopment Goal (SDG).
-    Params
+    reference a group in a vulnerable situation.
     ---------
     haystack_doc: List of haystack Documents. The output of Preprocessing Pipeline 
     contains the list of paragraphs in different format,here the list of