Update app.py

app.py

@@ -5,40 +5,63 @@ import faiss
 from sentence_transformers import SentenceTransformer
 import joblib
 
-# Load all assets
+# ===============================
+# 🔹 Load all assets
+# ===============================
 df = pd.read_csv("clean_feedback.csv")
-embeddings = np.load("embeddings.npy")
-index = faiss.read_index("feedback.index")
-clf = joblib.load("feedback_model.pkl")
+embeddings = np.load("embedings.npy")  # ✅ matches your file spelling
+index = faiss.read_index("feedback.index")  # ✅ matches the visible file
+clf = joblib.load("feedback_model.pkl")  # ✅ your classifier model
 
-model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2")
+# ✅ Use CPU to avoid Hugging Face GPU issues
+model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2", device="cpu")
 
+# ===============================
+# 🔹 Define feedback classifier
+# ===============================
 def classify_feedback(text, top_k=5):
-    # Embed query
+    if not text.strip():
+        return "**Please enter some feedback text.**"
+
+    # Create embedding for user input
     query_emb = model.encode([text])
-    
-    # Retrieve top-k similar samples
+
+    # Retrieve top-k similar feedbacks from FAISS index
     distances, indices = index.search(query_emb, top_k)
-    
-    # Gather context
+
+    # Get similar sentences
     retrieved = df.iloc[indices[0]]
-    context = "\n".join(retrieved['Sentence'].tolist())
-    
-    # Predict sentiment
+
+    # Combine context (optional, for RAG explainability)
+    context = "\n".join(retrieved['Sentence'].astype(str).tolist())
+
+    # Predict sentiment from classifier
     sentiment = clf.predict(query_emb)[0]
-    
-    # Prepare explanation
-    examples = "\n".join([f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())])
-    
+
+    # Prepare explanation list
+    examples = "\n".join(
+        [f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].astype(str).tolist())]
+    )
+
     return f"**Predicted Sentiment:** {sentiment}\n\n**Similar Feedbacks:**\n{examples}"
 
-# Gradio UI
+# ===============================
+# 🔹 Gradio UI
+# ===============================
 demo = gr.Interface(
     fn=classify_feedback,
-    inputs=[gr.Textbox(label="Enter Student Feedback")],
+    inputs=[
+        gr.Textbox(
+            label="Enter Student Feedback",
+            placeholder="Type a Roman Urdu or English feedback sentence here..."
+        )
+    ],
     outputs=[gr.Markdown(label="Prediction & Explanation")],
     title="🎓 Student Feedback RAG System",
-    description="Classifies Roman Urdu/English student feedback with context and reasoning."
+    description="Analyzes student feedback (Roman Urdu or English) using Retrieval-Augmented Generation with contextual examples."
 )
 
+# ===============================
+# 🔹 Launch app
+# ===============================
 demo.launch()