Update app.py

app.py

@@ -4,10 +4,8 @@ import gradio as gr
 from transformers import pipeline
 from collections import Counter
 
-# Load NER pipeline
+# Load pipelines
 ner_pipeline = pipeline("ner", model="dslim/bert-base-NER", tokenizer="dslim/bert-base-NER", aggregation_strategy="simple")
-
-# Load NEW job classifier with human-readable labels
 text_classifier = pipeline("text-classification", model="tkuye/job-description-classifier")
 
 def clean_resume_text(text):
@@ -60,15 +58,14 @@ def process_resumes(files):
         entities = ner_pipeline(cleaned_text)
         classification = classify_resume_ner(entities)
 
-            all_results[file_name] = {
-                "Persons": list({e["word"] for e in entities if e["entity_group"] == "PER"}),
-                "Organizations": list({e["word"] for e in entities if e["entity_group"] == "ORG"}),
-                "Locations": list({e["word"] for e in entities if e["entity_group"] == "LOC"}),
-                "Other Entities": list({e["word"] for e in entities if e["entity_group"] not in ["PER", "ORG", "LOC"]}),
-                "Cleaned_Text": cleaned_text,
-                "Classification (NER)": classification
-            }
-
+        all_results[file_name] = {
+            "Persons": list({e["word"] for e in entities if e["entity_group"] == "PER"}),
+            "Organizations": list({e["word"] for e in entities if e["entity_group"] == "ORG"}),
+            "Locations": list({e["word"] for e in entities if e["entity_group"] == "LOC"}),
+            "Other Entities": list({e["word"] for e in entities if e["entity_group"] not in ["PER", "ORG", "LOC"]}),
+            "Cleaned_Text": cleaned_text,
+            "Classification (NER)": classification
+        }
     return all_results
 
 def classify_resumes_with_model(files):
@@ -80,7 +77,7 @@ def classify_resumes_with_model(files):
             predictions[file_name] = {"error": error}
             continue
         cleaned_text = clean_resume_text(resume_text)
-        result = text_classifier(cleaned_text[:512])
+        result = text_classifier(cleaned_text[:512])  # Truncate long resumes
         predictions[file_name] = {
             "Predicted Job Category": result[0]['label'],
             "Confidence Score": round(result[0]['score'], 4)