fix: enrichment models batch size and expose picture classifier (#878)

* expose picture classifier in CLI

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

* use different batch size in each model

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

* remove batch size from CLI

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

* cleanup imports

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

---------

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

docling/models/base_model.py

@@ -6,6 +6,7 @@ from typing_extensions import TypeVar
 
 from docling.datamodel.base_models import ItemAndImageEnrichmentElement, Page
 from docling.datamodel.document import ConversionResult
+from docling.datamodel.settings import settings
 
 
 class BasePageModel(ABC):
@@ -21,6 +22,8 @@ EnrichElementT = TypeVar("EnrichElementT", default=NodeItem)
 
 class GenericEnrichmentModel(ABC, Generic[EnrichElementT]):
 
+    elements_batch_size: int = settings.perf.elements_batch_size
+
     @abstractmethod
     def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
         pass

docling/models/code_formula_model.py

@@ -61,6 +61,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
         Processes the given batch of elements and enriches them with predictions.
     """
 
+    elements_batch_size = 5
     images_scale = 1.66  # = 120 dpi, aligned with training data resolution
     expansion_factor = 0.03