Update app.py

app.py

@@ -42,29 +42,37 @@ def classify_feedback(text, top_k=5):
     print(f"\n🧠 New query: {text}")
 
     if not text.strip():
-        return "⚠️ Please enter a feedback text.", pd.read_csv(USER_LOG_FILE)
+        return "⚠️ Please enter a feedback text."
 
-    # Embed query
+    # Embed the input
     query_emb = model.encode([text])
     print("Embedding shape:", query_emb.shape)
 
-    # Search similar samples
+    # Retrieve top similar examples
     distances, indices = index.search(query_emb, top_k)
-    print("Retrieved indices:", indices)
-
     retrieved = df.iloc[indices[0]]
 
-    # Predict sentiment
+    # Predict sentiment and probability
     try:
         sentiment = clf.predict(query_emb)[0]
+        if hasattr(clf, "predict_proba"):
+            confidence = clf.predict_proba(query_emb).max() * 100
+            confidence = round(confidence, 2)
+        else:
+            confidence = "N/A"
     except Exception as e:
-        return f"❌ Model prediction error: {str(e)}", pd.read_csv(USER_LOG_FILE)
+        return f"❌ Model prediction error: {str(e)}"
 
-    examples = "\n".join(
-        [f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())]
-    )
+    examples = "\n".join([f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())])
     print("✅ Prediction done")
 
+    return (
+        f"**Predicted Sentiment:** {sentiment}\n"
+        f"**Confidence:** {confidence}%\n\n"
+        f"**Similar Feedbacks:**\n{examples}"
+    )
+
+
     # ------------------------
     # Save user input to log
     # ------------------------