Update app.py

app.py

@@ -214,7 +214,6 @@ def process_and_summarize(df, top_n=50, topic_strategy="Auto", n_topics=None, mi
         "n_gram_range": (1, 3),
         "top_n_words": 15,
         "verbose": True,
-        "diversity": 0.5,
         "stop_words": ARABIC_STOP_WORDS
     }
     
@@ -318,8 +317,12 @@ def main():
                 )
                 
                 if topic_strategy == "Manual":
+                    # Calculate reasonable max topics based on dataset size
                     n_documents = len(df)
-                    max_topics = min(500, int(np.log10(n_documents) * 100))
+                    if n_documents < 1000:
+                        max_topics = min(50, n_documents // 20)
+                    else:
+                        max_topics = min(500, int(np.log10(n_documents) * 100))
                     
                     n_topics = st.slider(
                         "Number of Topics",
@@ -328,6 +331,13 @@ def main():
                         value=min(20, max_topics),
                         help=f"Select the desired number of topics (max {max_topics} based on dataset size)"
                     )
+                    
+                    st.info(f"""
+                        💡 For your dataset of {n_documents:,} documents:
+                        - Minimum topics: 2
+                        - Maximum topics: {max_topics}
+                        - Recommended range: {max(2, max_topics//5)}-{max_topics//2}
+                        """)
             
             with col2:
                 top_n = st.number_input(