feat: Updated Layout processing with forms and key-value areas

docling/datamodel/base_models.py

@@ -129,6 +129,7 @@ class Cluster(BaseModel):
     bbox: BoundingBox
     confidence: float = 1.0
     cells: List[Cell] = []
+    children: List["Cluster"] = []  # Add child cluster support
 
 
 class BasePageElement(BaseModel):
@@ -143,6 +144,12 @@ class LayoutPrediction(BaseModel):
     clusters: List[Cluster] = []
 
 
+class ContainerElement(
+    BasePageElement
+):  # Used for Form and Key-Value-Regions, only for typing.
+    pass
+
+
 class Table(BasePageElement):
     otsl_seq: List[str]
     num_rows: int = 0
@@ -182,7 +189,7 @@ class PagePredictions(BaseModel):
     equations_prediction: Optional[EquationPrediction] = None
 
 
-PageElement = Union[TextElement, Table, FigureElement]
+PageElement = Union[TextElement, Table, FigureElement, ContainerElement]
 
 
 class AssembledUnit(BaseModel):

docling/datamodel/document.py

@@ -73,7 +73,7 @@
 
 layout_label_to_ds_type = {
     DocItemLabel.TITLE: "title",
-    DocItemLabel.DOCUMENT_INDEX: "table-of-contents",
+    DocItemLabel.DOCUMENT_INDEX: "table",
     DocItemLabel.SECTION_HEADER: "subtitle-level-1",
     DocItemLabel.CHECKBOX_SELECTED: "checkbox-selected",
     DocItemLabel.CHECKBOX_UNSELECTED: "checkbox-unselected",
@@ -88,6 +88,8 @@
     DocItemLabel.PICTURE: "figure",
     DocItemLabel.TEXT: "paragraph",
     DocItemLabel.PARAGRAPH: "paragraph",
+    DocItemLabel.FORM: DocItemLabel.FORM.value,
+    DocItemLabel.KEY_VALUE_REGION: DocItemLabel.KEY_VALUE_REGION.value,
 }
 
 _EMPTY_DOCLING_DOC = DoclingDocument(name="dummy")

docling/datamodel/pipeline_options.py

@@ -139,6 +139,8 @@ class EasyOcrOptions(OcrOptions):
 
     use_gpu: Optional[bool] = None
 
+    confidence_threshold: float = 0.65
+
     model_storage_directory: Optional[str] = None
     recog_network: Optional[str] = "standard"
     download_enabled: bool = True

docling/datamodel/settings.py

@@ -31,6 +31,7 @@ class DebugSettings(BaseModel):
     visualize_cells: bool = False
     visualize_ocr: bool = False
     visualize_layout: bool = False
+    visualize_raw_layout: bool = False
     visualize_tables: bool = False
 
     profile_pipeline_timings: bool = False

docling/models/ds_glm_model.py

@@ -22,9 +22,15 @@
 from docling_core.types.legacy_doc.document import CCSFileInfoObject as DsFileInfoObject
 from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
 from PIL import ImageDraw
-from pydantic import BaseModel, ConfigDict
-
-from docling.datamodel.base_models import Cluster, FigureElement, Table, TextElement
+from pydantic import BaseModel, ConfigDict, TypeAdapter
+
+from docling.datamodel.base_models import (
+    Cluster,
+    ContainerElement,
+    FigureElement,
+    Table,
+    TextElement,
+)
 from docling.datamodel.document import ConversionResult, layout_label_to_ds_type
 from docling.datamodel.settings import settings
 from docling.utils.glm_utils import to_docling_document
@@ -204,7 +210,31 @@ def make_spans(cell):
                             )
                         ],
                         obj_type=layout_label_to_ds_type.get(element.label),
-                        # data=[[]],
+                        payload={
+                            "children": TypeAdapter(List[Cluster]).dump_python(
+                                element.cluster.children
+                            )
+                        },  # hack to channel child clusters through GLM
+                    )
+                )
+            elif isinstance(element, ContainerElement):
+                main_text.append(
+                    BaseText(
+                        text="",
+                        payload={
+                            "children": TypeAdapter(List[Cluster]).dump_python(
+                                element.cluster.children
+                            )
+                        },  # hack to channel child clusters through GLM
+                        obj_type=layout_label_to_ds_type.get(element.label),
+                        name=element.label,
+                        prov=[
+                            Prov(
+                                bbox=target_bbox,
+                                page=element.page_no + 1,
+                                span=[0, 0],
+                            )
+                        ],
                     )
                 )
 

docling/models/easyocr_model.py

@@ -118,6 +118,7 @@ def __call__(
                                 ),
                             )
                             for ix, line in enumerate(result)
+                            if line[2] >= self.options.confidence_threshold
                         ]
                         all_ocr_cells.extend(cells)