Create app.py

app.py

@@ -0,0 +1,98 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+import faiss
+import os
+from sentence_transformers import SentenceTransformer
+import joblib
+
+# ------------------------
+# Load assets
+# ------------------------
+print("🔄 Loading data and models...")
+df = pd.read_csv("clean_feedback.csv")
+print("✅ CSV loaded with columns:", df.columns.tolist())
+
+embeddings = np.load("embeddings.npy")
+print("✅ Embeddings loaded with shape:", embeddings.shape)
+
+index = faiss.read_index("feedback.index")
+print("✅ FAISS index loaded")
+
+clf = joblib.load("feedback_model.pkl")
+print("✅ Sentiment model loaded")
+
+model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2", device="cpu")
+print("✅ SentenceTransformer ready")
+
+# ------------------------
+# Setup shared CSV for user submissions
+# ------------------------
+USER_LOG_FILE = "user_feedback.csv"
+
+# Create file if missing
+if not os.path.exists(USER_LOG_FILE):
+    pd.DataFrame(columns=["Sentence", "Predicted_Sentiment"]).to_csv(USER_LOG_FILE, index=False)
+    print("✅ Created user_feedback.csv")
+
+# ------------------------
+# Define classification + logging function
+# ------------------------
+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)
+
+    # Embed query
+    query_emb = model.encode([text])
+    print("Embedding shape:", query_emb.shape)
+
+    # Search similar samples
+    distances, indices = index.search(query_emb, top_k)
+    print("Retrieved indices:", indices)
+
+    retrieved = df.iloc[indices[0]]
+
+    # Predict sentiment
+    try:
+        sentiment = clf.predict(query_emb)[0]
+    except Exception as e:
+        return f"❌ Model prediction error: {str(e)}", pd.read_csv(USER_LOG_FILE)
+
+    examples = "\n".join(
+        [f"{i+1}. {s}" for i, s in enumerate(retrieved['Sentence'].tolist())]
+    )
+    print("✅ Prediction done")
+
+    # ------------------------
+    # Save user input to log
+    # ------------------------
+    log_entry = pd.DataFrame([[text, sentiment]], columns=["Sentence", "Predicted_Sentiment"])
+    log_entry.to_csv(USER_LOG_FILE, mode="a", header=False, index=False)
+    print("📝 Saved to user_feedback.csv")
+
+    # Read updated log to show
+    user_log = pd.read_csv(USER_LOG_FILE)
+
+    output_text = f"**Predicted Sentiment:** {sentiment}\n\n**Similar Feedbacks:**\n{examples}"
+    return output_text, user_log
+
+# ------------------------
+# Gradio UI
+# ------------------------
+demo = gr.Interface(
+    fn=classify_feedback,
+    inputs=[gr.Textbox(label="Enter Student Feedback")],
+    outputs=[
+        gr.Markdown(label="Prediction & Explanation"),
+        gr.Dataframe(label="🧾 All User Feedback", headers=["Sentence", "Predicted_Sentiment"])
+    ],
+    title="🎓 Student Feedback RAG System",
+    description=(
+        "Classifies Roman Urdu/English student feedback with context and reasoning.\n\n"
+        "All submissions are saved and visible to everyone below 👇"
+    ),
+)
+
+demo.launch()