fix: make all entity_values unique by appending row index to support bulk_create with ignore_conflicts

2026-07-22 23:17:09 +08:00
parent 0d92a5a170
commit 035d22b234
1 changed files with 2 additions and 4 deletions
@@ -986,10 +986,8 @@ def _run_clustering_pipeline(run, store, entity_ds_id, feature_columns, algorith
                        profiles = []
                        cr_cache = {}
                        for i, row in enumerate(df_umap.iter_rows(named=True)):
-                            ev = str(row.get(ent_col, '')) or f'entity_{i}'
-                            # Ensure uniqueness by appending row index when using fallback
-                            if not row.get(ent_col, ''):
-                                ev = f'{ev}_{i}'
+                            ev = str(row.get(ent_col, '')) or 'entity'
+                            ev = f'{ev}_{i}'
                            lbl = labels_list[i] if i < len(labels_list) else -1
                            cache_key = f'{run.id}_{lbl}'
                            if cache_key not in cr_cache: