fix: Restore embedding-mode parameter to all examples

- All examples now have --embedding-mode parameter (unified interface benefit)
- Default is 'sentence-transformers' (consistent with original behavior)
- Users can now use OpenAI or MLX embeddings with any data source
- Maintains functional equivalence with original scripts

examples/browser_rag.py

@@ -21,7 +21,7 @@ class BrowserRAG(BaseRAGExample):
         super().__init__(
             name="Browser History",
             description="Process and query Chrome browser history with LEANN",
-            default_index_name="google_history_index",  # Match original: "./google_history_index",
+            default_index_name="google_history_index",
         )
 
     def _add_specific_arguments(self, parser):