fix: properly load models at boot (#244)

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docling_serve/settings.py

@@ -41,6 +41,7 @@ class DoclingServeSettings(BaseSettings):
     scratch_path: Optional[Path] = None
     single_use_results: bool = True
     result_removal_delay: float = 300  # 5 minutes
+    load_models_at_boot: bool = True
     options_cache_size: int = 2
     enable_remote_services: bool = False
     allow_external_plugins: bool = False