cleaning messages

app.py

@@ -36,22 +36,22 @@ def compute_embeddings(problems):
     return model.encode(problems, normalize_embeddings=True)
 
 
+
 def find_similar_problems(df, similarity_threshold=0.9):
-    """Find similar problems using cosine similarity"""
+    """Find similar problems using cosine similarity, optimized for speed with clean UI updates."""
     
-    st.status("🔄 Computing problem embeddings...")
+    status_box = st.empty() 
+    status_box.info("🔄 Computing problem embeddings...")
     start_time = time.time()
     embeddings = compute_embeddings(df['problem'].tolist())
-    st.success("✅ Embeddings computed!", icon="✅")
     
-    st.status("🔄 Computing cosine similarity matrix...")
+    status_box.info("🔄 Computing cosine similarity matrix...")
     similarity_matrix = util.cos_sim(embeddings, embeddings).numpy()
-    st.success("✅ Similarity matrix computed!", icon="✅")
 
+    status_box.info("🔄 Filtering similar problems...")
     num_problems = len(df)
     upper_triangle_indices = np.triu_indices(num_problems, k=1)
     
-    st.status("🔄 Filtering similar problems...")
     i_indices, j_indices = upper_triangle_indices
     similarity_scores = similarity_matrix[i_indices, j_indices]
 
@@ -66,7 +66,8 @@ def find_similar_problems(df, similarity_threshold=0.9):
     ]
     
     sorted_pairs = sorted(pairs, key=lambda x: x[2], reverse=True)
-    
+
+    status_box.empty()
     st.success(f"✅ Analysis complete! Found {len(sorted_pairs)} similar problems in {time.time() - start_time:.2f}s", icon="🎉")
 
     return sorted_pairs