renaming

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

docling/datamodel/base_models.py

@@ -4,10 +4,10 @@ from typing import TYPE_CHECKING, Dict, List, Optional, Union
 from docling_core.types.doc import (
     BoundingBox,
     DocItemLabel,
+    NodeItem,
     PictureDataType,
     Size,
     TableCell,
-    TextItem,
 )
 from docling_core.types.io import (  # DO ΝΟΤ REMOVE; explicitly exposed from this location
     DocumentStream,
@@ -202,12 +202,12 @@ class AssembledUnit(BaseModel):
     headers: List[PageElement] = []
 
 
-class TextImageEnrichmentElement(BaseModel):
+class ItemAndImageEnrichmentElement(BaseModel):
-    element: TextItem
-    image: Image
-
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
+    item: NodeItem
+    image: Image
+
 
 class Page(BaseModel):
     model_config = ConfigDict(arbitrary_types_allowed=True)

docling/models/base_model.py

@@ -4,7 +4,7 @@ from typing import Any, Generic, Iterable, Optional
 from docling_core.types.doc import DoclingDocument, NodeItem, TextItem
 from typing_extensions import TypeVar
 
-from docling.datamodel.base_models import Page, TextImageEnrichmentElement
+from docling.datamodel.base_models import ItemAndImageEnrichmentElement, Page
 from docling.datamodel.document import ConversionResult
 
 
@@ -48,13 +48,15 @@ class BaseEnrichmentModel(GenericEnrichmentModel[NodeItem]):
         return None
 
 
-class BaseTextImageEnrichmentModel(GenericEnrichmentModel[TextImageEnrichmentElement]):
+class BaseItemAndImageEnrichmentModel(
+    GenericEnrichmentModel[ItemAndImageEnrichmentElement]
+):
 
     images_scale: float
 
     def prepare_element(
         self, conv_res: ConversionResult, element: NodeItem
-    ) -> Optional[TextImageEnrichmentElement]:
+    ) -> Optional[ItemAndImageEnrichmentElement]:
         if not self.is_processable(doc=conv_res.document, element=element):
             return None
 
@@ -64,4 +66,4 @@ class BaseTextImageEnrichmentModel(GenericEnrichmentModel[TextImageEnrichmentEle
         cropped_image = conv_res.pages[page_ix].get_image(
             scale=self.images_scale, cropbox=element_prov.bbox
         )
-        return TextImageEnrichmentElement(element=element, image=cropped_image)
+        return ItemAndImageEnrichmentElement(item=element, image=cropped_image)

docling/models/page_assemble_model.py

@@ -21,8 +21,8 @@ from docling.utils.profiling import TimeRecorder
 _log = logging.getLogger(__name__)
 
 
-class PageAssembleOptions(BaseModel):  # could be removed entirely or just make empty
+class PageAssembleOptions(BaseModel):
-    keep_images: bool = False
+    pass
 
 
 class PageAssembleModel(BasePageModel):

docling/pipeline/base_pipeline.py

@@ -198,12 +198,13 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
         return conv_res
 
     def _unload(self, conv_res: ConversionResult) -> ConversionResult:
-        if conv_res.input._backend:
-            conv_res.input._backend.unload()
-
         for page in conv_res.pages:
             if page._backend is not None:
                 page._backend.unload()
+
+        if conv_res.input._backend:
+            conv_res.input._backend.unload()
+
         return conv_res
 
     def _determine_status(self, conv_res: ConversionResult) -> ConversionStatus:

docs/examples/develop_formula_understanding.py

@@ -4,19 +4,19 @@ from typing import Iterable
 
 from docling_core.types.doc import DocItemLabel, DoclingDocument, NodeItem, TextItem
 
-from docling.datamodel.base_models import InputFormat, TextImageEnrichmentElement
+from docling.datamodel.base_models import InputFormat, ItemAndImageEnrichmentElement
 from docling.datamodel.pipeline_options import PdfPipelineOptions
 from docling.document_converter import DocumentConverter, PdfFormatOption
-from docling.models.base_model import BaseTextImageEnrichmentModel
+from docling.models.base_model import BaseItemAndImageEnrichmentModel
 from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
 
 
-class ExampleFormulaUPipelineOptions(PdfPipelineOptions):
+class ExampleFormulaUnderstandingPipelineOptions(PdfPipelineOptions):
     do_formula_understanding: bool = True
 
 
 # A new enrichment model using both the document element and its image as input
-class ExampleFormulaUEnrichmentModel(BaseTextImageEnrichmentModel):
+class ExampleFormulaUnderstandingEnrichmentModel(BaseItemAndImageEnrichmentModel):
     images_scale = 2.6
 
     def __init__(self, enabled: bool):
@@ -30,7 +30,9 @@ class ExampleFormulaUEnrichmentModel(BaseTextImageEnrichmentModel):
         )
 
     def __call__(
-        self, doc: DoclingDocument, element_batch: Iterable[TextImageEnrichmentElement]
+        self,
+        doc: DoclingDocument,
+        element_batch: Iterable[ItemAndImageEnrichmentElement],
     ) -> Iterable[NodeItem]:
         if not self.enabled:
             return
@@ -38,18 +40,18 @@ class ExampleFormulaUEnrichmentModel(BaseTextImageEnrichmentModel):
         for enrich_element in element_batch:
             enrich_element.image.show()
 
-            yield enrich_element.element
+            yield enrich_element.item
 
 
 # How the pipeline can be extended.
-class ExampleFormulaUPipeline(StandardPdfPipeline):
+class ExampleFormulaUnderstandingPipeline(StandardPdfPipeline):
 
-    def __init__(self, pipeline_options: ExampleFormulaUPipelineOptions):
+    def __init__(self, pipeline_options: ExampleFormulaUnderstandingPipelineOptions):
         super().__init__(pipeline_options)
-        self.pipeline_options: ExampleFormulaUPipelineOptions
+        self.pipeline_options: ExampleFormulaUnderstandingPipelineOptions
 
         self.enrichment_pipe = [
-            ExampleFormulaUEnrichmentModel(
+            ExampleFormulaUnderstandingEnrichmentModel(
                 enabled=self.pipeline_options.do_formula_understanding
             )
         ]
@@ -58,8 +60,8 @@ class ExampleFormulaUPipeline(StandardPdfPipeline):
             self.keep_backend = True
 
     @classmethod
-    def get_default_options(cls) -> ExampleFormulaUPipelineOptions:
+    def get_default_options(cls) -> ExampleFormulaUnderstandingPipelineOptions:
-        return ExampleFormulaUPipelineOptions()
+        return ExampleFormulaUnderstandingPipelineOptions()
 
 
 # Example main. In the final version, we simply have to set do_formula_understanding to true.
@@ -68,13 +70,13 @@ def main():
 
     input_doc_path = Path("./tests/data/2203.01017v2.pdf")
 
-    pipeline_options = ExampleFormulaUPipelineOptions()
+    pipeline_options = ExampleFormulaUnderstandingPipelineOptions()
     pipeline_options.do_formula_understanding = True
 
     doc_converter = DocumentConverter(
         format_options={
             InputFormat.PDF: PdfFormatOption(
-                pipeline_cls=ExampleFormulaUPipeline,
+                pipeline_cls=ExampleFormulaUnderstandingPipeline,
                 pipeline_options=pipeline_options,
             )
         }