Update retailgpt_evaluator/app.py

retailgpt_evaluator/app.py

@@ -1,7 +1,6 @@
 import streamlit as st
 from shared.hf_helpers import build_pipeline
 from retailgpt_evaluator.leaderboard import build_leaderboard
-from retailgpt_evaluator.evaluate import evaluate_all  # ✅ NEW import
 import yaml, pandas as pd, os
 from pathlib import Path
 
@@ -19,21 +18,7 @@ def main():
     with open(config_path) as f:
         cfg = yaml.safe_load(f)
 
-    # -------------------------------
-    # Evaluation Trigger Button
-    # -------------------------------
-    st.markdown("### 🛠️ Run Evaluation")
-    if st.button("⚙️ Run evaluate.py now"):
-        with st.spinner("Running model evaluations..."):
-            try:
-                evaluate_all()
-                st.success("✅ Evaluation complete! Leaderboard updated.")
-            except Exception as e:
-                st.error(f"❌ Evaluation failed: {e}")
-
-    # -------------------------------
     # Show leaderboard if exists
-    # -------------------------------
     if os.path.exists("models/retail_eval_results.json"):
         df = build_leaderboard()
         st.subheader("📊 Model Leaderboard")
@@ -41,14 +26,12 @@ def main():
     else:
         st.warning("Run `evaluate.py` first to generate metrics.")
 
-    # -------------------------------
     # Model chat interface
-    # -------------------------------
     st.markdown("---")
     model_name = st.selectbox("Choose a model to chat with:", cfg["models"])
     pipe = build_pipeline(model_name)
 
-    query = st.text_area("Customer query:", "I want to return a damaged product.")
+    query = st.text_area("Customer query:", "Which is the best country for retail?.")
     if st.button("Ask Model"):
         result = pipe(query, max_new_tokens=cfg["demo"]["max_new_tokens"])
         st.markdown("### 🧠 Model Response")