Update app.py

app.py

@@ -8,20 +8,23 @@ detector = pipeline(
     "text-classification",
     model="songhieng/roberta-phishing-content-detector-1.0",
     device=device,
-    top_k=1,                   # replaces deprecated return_all_scores=False
+    top_k=1,
 )
 
 # 2. Wrap prediction in a function for Gradio
 def classify_text(text: str):
     """
     Returns (label, score) for the given text.
+    Handles both flat and nested list outputs from the pipeline.
     """
     if not text or not text.strip():
         return "⚠️ Please enter some text", 0.0
-    
-    result = detector(text)[0]
-    label = result["label"]
-    score = float(result["score"])
+
+    preds = detector(text)
+    # If preds is [[{...}]], unwrap one level
+    first = preds[0][0] if isinstance(preds[0], list) else preds[0]
+    label = first["label"]
+    score = float(first["score"])
     return label, round(score, 4)
 
 # 3. Realistic example test cases
@@ -33,7 +36,7 @@ examples = [
     ["Invoice overdue—pay now to avoid suspension: http://billing.example.com/pay"],
     ["Security Notice: Confirm your bank details here: https://bank-secure-update.com"],
 
-    # Legit
+    # Legitimate
     ["Your Amazon order has shipped! Track here: https://amazon.com/track"],
     ["Reminder: Zoom meeting with Marketing tomorrow at 3:00 PM."],
     ["Hey Jane, lunch at the café this Friday? 😊"],
@@ -73,10 +76,9 @@ with gr.Blocks(theme="default") as demo:
 
     gr.Markdown(
         """
-        **Model:** Version 1.0
+        **Model:** Version 1. 
         """
     )
 
 if __name__ == "__main__":
-    # set share=True if you want a public link
     demo.launch()