Update app.py

app.py

@@ -38,20 +38,26 @@ def compute_embeddings(problems):
 def find_similar_problems(df, similarity_threshold=0.9):
     """Find similar problems using cosine similarity, optimized for speed."""
     
-    st.status("🔄 Computing problem embeddings...")
+    status_msgs = []  # Store status messages to clear later
+
+    # Step 1: Compute embeddings
+    msg = st.status("🔄 Computing problem embeddings...")
+    status_msgs.append(msg)
     start_time = time.time()
     embeddings = compute_embeddings(df['problem'].tolist())
-    st.success("✅ Embeddings computed!", icon="✅")
-    
-    st.status("🔄 Computing cosine similarity matrix...")
+
+    # Step 2: Compute similarity matrix
+    msg = st.status("🔄 Computing cosine similarity matrix...")
+    status_msgs.append(msg)
     similarity_matrix = util.cos_sim(embeddings, embeddings).numpy()
-    st.success("✅ Similarity matrix computed!", icon="✅")
 
-    # Use numpy.triu_indices to efficiently get upper-triangle indices (excluding diagonal)
+    # Step 3: Filter top similarities
+    msg = st.status("🔄 Filtering similar problems...")
+    status_msgs.append(msg)
+    
     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]
 
@@ -61,14 +67,18 @@ def find_similar_problems(df, similarity_threshold=0.9):
     filtered_j = j_indices[mask]
     filtered_scores = similarity_scores[mask]
 
-    # Convert results into a sorted list of tuples
     pairs = [
         (df.iloc[i]["uuid"], df.iloc[j]["uuid"], float(score))
         for i, j, score in zip(filtered_i, filtered_j, filtered_scores)
     ]
     
     sorted_pairs = sorted(pairs, key=lambda x: x[2], reverse=True)
-    
+
+    # Step 4: Remove intermediate messages
+    for msg in status_msgs:
+        msg.empty()  # Clear only the intermediate messages
+
+    # Step 5: Display final success message
     st.success(f"✅ Analysis complete! Found {len(sorted_pairs)} similar problems in {time.time() - start_time:.2f}s", icon="🎉")
 
     return sorted_pairs