Update app.py

app.py

@@ -59,7 +59,7 @@ def main():
     # Highest sentiment
     max_label, max_score = max(sentiment_results.items(), key=lambda x: x[1])
     st.subheader("Highest Sentiment")
-    st.write(f"**{max_label}** ({max_score:.4f})")
+    st.markdown(f"**Highest Sentiment:** **{max_label}** ({max_score:.4f})")
 
     # Top 3 keywords
     keywords = kw_model.extract_keywords(
@@ -72,16 +72,16 @@ def main():
     for kw, score in keywords:
         st.write(f"• {kw} ({score:.4f})")
 
-    # GPT-Driven Analysis & Suggestions (concise)
+    # GPT-Driven Analysis & Suggestions (detailed)
     st.subheader("GPT Analysis & Seller Suggestions")
     prompt = f"""
-You are a concise e-commerce feedback analyst.
+You are an analytical e-commerce feedback expert.
 Review: "{review}"
-Scores: {sentiment_results}
-Keywords: {[kw for kw, _ in keywords]}
-Provide:
-1. One-sentence summary of customer sentiment.
-2. Three bullet-point suggestions, each no more than 8 words.
+Sentiment Scores: {sentiment_results}
+Top Keywords: {[kw for kw, _ in keywords]}
+Tasks:
+1. Write a concise paragraph (2 sentences) interpreting customer sentiment by combining the scores and keywords.
+2. Provide 3 actionable suggestions with brief explanations (up to 5 sentences each).
 """
 
     response = openai_client.chat.completions.create(
@@ -90,11 +90,11 @@ Provide:
             {"role": "system", "content": "You are a product-feedback analyst."},
             {"role": "user", "content": prompt}
         ],
-        temperature=0.5,
-        max_tokens=120
+        temperature=0.7,
+        max_tokens=200
     )
     gpt_reply = response.choices[0].message.content.strip()
     st.markdown(gpt_reply)
 
 if __name__ == "__main__":
-    main()
+    main()