update

modular_graph_and_candidates.py

@@ -123,15 +123,21 @@ def embedding_similarity_clusters(models_root: Path, missing: List[str], thr: fl
     names = list(texts)
     all_embeddings = []
 
-    print("Encoding embeddings...")
+    print(f"Encoding embeddings for {len(names)} models...")
     batch_size = 1
+    
     for i in tqdm(range(0, len(names), batch_size), desc="Models", leave=False):
+        model_name = names[i]
+        text_len = len(texts[model_name])
+        
         try:
-            batch = [texts[names[i]]]
+            print(f"Processing {model_name} (text length: {text_len})")
+            batch = [texts[model_name]]
             emb = model.encode(batch, convert_to_numpy=True, show_progress_bar=False)
             all_embeddings.append(emb)
+            print(f"✓ Completed {model_name}")
         except Exception as e:
-            print(f"⚠️  GPU worker error for {names[i]}: {e}")
+            print(f"⚠️  GPU worker error for {model_name}: {type(e).__name__}: {e}")
             # Create zero embedding as placeholder to maintain consistency
             zero_emb = np.zeros((1, model.get_sentence_embedding_dimension()), dtype=np.float32)
             all_embeddings.append(zero_emb)