use do_ flag in pipeline_options

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

docling/datamodel/pipeline_options.py

@@ -64,6 +64,8 @@ class PipelineOptions(BaseModel):
         True  # This defautl will be set to False on a future version of docling
     )
 
+    do_dummy_picture_classifer: bool = False
+
 
 class PdfPipelineOptions(PipelineOptions):
     artifacts_path: Optional[Union[Path, str]] = None

docling/models/dummy_picture_enrichment.py

@@ -10,12 +10,19 @@ from docling.models.base_model import BaseEnrichmentModel
 
 
 class DummyPictureClassifierEnrichmentModel(BaseEnrichmentModel):
+
+    def __init__(self, enabled: bool):
+        self.enabled = enabled
+
     def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
-        return isinstance(element, PictureItem)
+        return self.enabled and isinstance(element, PictureItem)
 
     def __call__(
         self, doc: DoclingDocument, element_batch: Iterable[NodeItem]
     ) -> Iterable[Any]:
+        if not self.enabled:
+            return
+
         for element in element_batch:
             assert isinstance(element, PictureItem)
             element.data.classification = PictureClassificationData(

docling/pipeline/standard_pdf_pipeline.py

@@ -84,7 +84,10 @@ class StandardPdfPipeline(PaginatedPipeline):
 
         self.enrichment_pipe = [
             # Other models working on `NodeItem` elements in the DoclingDocument
-            # DummyPictureClassifierEnrichmentModel()
+            # TODO Question: should we use the enabled flag or simply not add the model in the list?
+            DummyPictureClassifierEnrichmentModel(
+                enabled=pipeline_options.do_dummy_picture_classifer
+            )
         ]
 
     @staticmethod

examples/custom_convert.py

@@ -58,6 +58,7 @@ def main():
     pipeline_options.do_ocr = False
     pipeline_options.do_table_structure = True
     pipeline_options.table_structure_options.do_cell_matching = True
+    pipeline_options.do_dummy_picture_classifer = True
 
     doc_converter = DocumentConverter(
         format_options={