fix

modular_graph_and_candidates.py

@@ -156,11 +156,14 @@ def embedding_similarity_clusters(models_root: Path, missing: List[str], thr: fl
     sims_mat = embeddings @ embeddings.T
 
     out = {}
-    for i in range(len(names)):
-        for j in range(i + 1, len(names)):
+    matrix_size = embeddings.shape[0]  # Actual number of embeddings we have
+    processed_names = names[:matrix_size]  # Only use names that have embeddings
+    
+    for i in range(matrix_size):
+        for j in range(i + 1, matrix_size):
             s = float(sims_mat[i, j])
             if s >= thr:
-                out[(names[i], names[j])] = s
+                out[(processed_names[i], processed_names[j])] = s
     return out