Update src/streamlit_app.py

src/streamlit_app.py

@@ -18,14 +18,14 @@ def load_models():
         ner_pipe = pipeline(
             "token-classification", 
             model="jjzha/jobbert-base-cased-v2", 
-            aggregation_strategy="simple" # Merges sub-word tokens
+            aggregation_strategy="simple"
         )
         
         # 2. Zero-Shot Classification Model (Categorizes the terms)
         st.info("Loading Zero-Shot Classification Model...")
         classifier_pipe = pipeline(
             "zero-shot-classification", 
-            model="valhalla/distilbart-mnli-12-1" # Smaller, faster classification model
+            model="valhalla/distilbart-mnli-12-1" 
         )
         return ner_pipe, classifier_pipe
     except Exception as e:
@@ -42,11 +42,10 @@ def process_text(text, ner_pipe, classifier_pipe):
     # Step 1: Extract Entities (Candidates)
     ner_results = ner_pipe(text)
     
-    # Filter and clean extracted words, removing very short, possibly meaningless terms
     candidates = set()
     for entity in ner_results:
         word = entity['word'].strip()
-        if len(word.split()) > 1 or len(word) > 2: # Keep multi-word phrases or single words longer than 2 chars
+        if len(word.split()) > 1 or len(word) > 2:
             candidates.add(word)
     
     candidates = list(candidates)
@@ -57,21 +56,18 @@ def process_text(text, ner_pipe, classifier_pipe):
     skills = []
     knowledge = []
     
-    # These are the labels the Zero-Shot model will use for classification
     classification_labels = ["software tool or technology", "concept or knowledge"]
     
     for candidate in candidates:
         try:
-            # Classify the term
             result = classifier_pipe(candidate, candidate_labels=classification_labels)
             top_label = result['labels'][0]
             
-            # Append to the correct list
             if top_label == "software tool or technology":
                 skills.append(candidate)
             else:
                 knowledge.append(candidate)
-        except Exception as e:
+        except Exception:
             # Fallback for classification errors
             knowledge.append(candidate)