Update app.py

app.py

@@ -1,44 +1,44 @@
-import gradio as gr
-import pandas as pd
-import numpy as np
-import faiss
-from sentence_transformers import SentenceTransformer
-import joblib
-
-# Load all assets
-df = pd.read_csv("clean_feedback.csv")
-embeddings = np.load("embeddings.npy")
-index = faiss.read_index("feedback.index")
-clf = joblib.load("clf.pkl")
-
-model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2")
-
-def classify_feedback(text, top_k=5):
-    # Embed query
-    query_emb = model.encode([text])
-    
-    # Retrieve top-k similar samples
-    distances, indices = index.search(query_emb, top_k)
-    
-    # Gather context
-    retrieved = df.iloc[indices[0]]
-    context = "\n".join(retrieved['Sentence'].tolist())
-    
-    # Predict sentiment
-    sentiment = clf.predict(query_emb)[0]
-    
-    # Prepare explanation
-    examples = "\n".join([f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())])
-    
-    return f"**Predicted Sentiment:** {sentiment}\n\n**Similar Feedbacks:**\n{examples}"
-
-# Gradio UI
-demo = gr.Interface(
-    fn=classify_feedback,
-    inputs=[gr.Textbox(label="Enter Student Feedback")],
-    outputs=[gr.Markdown(label="Prediction & Explanation")],
-    title="🎓 Student Feedback RAG System",
-    description="Classifies Roman Urdu/English student feedback with context and reasoning."
-)
-
-demo.launch()
+import gradio as gr
+import pandas as pd
+import numpy as np
+import faiss
+from sentence_transformers import SentenceTransformer
+import joblib
+
+# 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")
+
+model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2")
+
+def classify_feedback(text, top_k=5):
+    # Embed query
+    query_emb = model.encode([text])
+    
+    # Retrieve top-k similar samples
+    distances, indices = index.search(query_emb, top_k)
+    
+    # Gather context
+    retrieved = df.iloc[indices[0]]
+    context = "\n".join(retrieved['Sentence'].tolist())
+    
+    # Predict sentiment
+    sentiment = clf.predict(query_emb)[0]
+    
+    # Prepare explanation
+    examples = "\n".join([f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())])
+    
+    return f"**Predicted Sentiment:** {sentiment}\n\n**Similar Feedbacks:**\n{examples}"
+
+# Gradio UI
+demo = gr.Interface(
+    fn=classify_feedback,
+    inputs=[gr.Textbox(label="Enter Student Feedback")],
+    outputs=[gr.Markdown(label="Prediction & Explanation")],
+    title="🎓 Student Feedback RAG System",
+    description="Classifies Roman Urdu/English student feedback with context and reasoning."
+)
+
+demo.launch()