removed too much, adapt

app.py

@@ -35,20 +35,23 @@ def compute_embeddings(problems):
     """Compute sentence embeddings."""
     return model.encode(problems, normalize_embeddings=True)
 
-
-
 def find_similar_problems(df, similarity_threshold=0.9):
-    """Find similar problems using cosine similarity, optimized for speed with clean UI updates."""
+    """Find similar problems using cosine similarity, optimized with clear UI updates."""
     
-    status_box = st.empty() 
-    status_box.info("🔄 Computing problem embeddings...")
+    status_msgs = []
+
+    msg = st.status("🔄 Computing problem embeddings...")
+    status_msgs.append(msg)
     start_time = time.time()
     embeddings = compute_embeddings(df['problem'].tolist())
-    
-    status_box.info("🔄 Computing cosine similarity matrix...")
+
+    msg = st.status("🔄 Computing cosine similarity matrix...")
+    status_msgs.append(msg)
     similarity_matrix = util.cos_sim(embeddings, embeddings).numpy()
 
-    status_box.info("🔄 Filtering similar problems...")
+    msg = st.status("🔄 Filtering similar problems...")
+    status_msgs.append(msg)
+    
     num_problems = len(df)
     upper_triangle_indices = np.triu_indices(num_problems, k=1)
     
@@ -67,7 +70,9 @@ def find_similar_problems(df, similarity_threshold=0.9):
     
     sorted_pairs = sorted(pairs, key=lambda x: x[2], reverse=True)
 
-    status_box.empty()
+    for msg in status_msgs:
+        msg.empty()
+        
     st.success(f"✅ Analysis complete! Found {len(sorted_pairs)} similar problems in {time.time() - start_time:.2f}s", icon="🎉")
 
     return sorted_pairs