docling 1.15.0__py3-none-any.whl → 1.16.0__py3-none-any.whl

docling/cli/main.py

@@ -12,8 +12,9 @@ from docling_core.utils.file import resolve_file_source
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
-from docling.datamodel.base_models import ConversionStatus, PipelineOptions
+from docling.datamodel.base_models import ConversionStatus
 from docling.datamodel.document import ConversionResult, DocumentConversionInput
+from docling.datamodel.pipeline_options import PipelineOptions
 from docling.document_converter import DocumentConverter
 
 warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch")

docling/datamodel/base_models.py

@@ -9,6 +9,10 @@ from pydantic import BaseModel, ConfigDict, Field, model_validator
 from typing_extensions import Self
 
 from docling.backend.abstract_backend import PdfPageBackend
+from docling.datamodel.pipeline_options import (  # Must be imported here for backward compatibility.
+    PipelineOptions,
+    TableStructureOptions,
+)
 
 
 class ConversionStatus(str, Enum):
@@ -298,22 +302,6 @@ class DocumentStream(BaseModel):
     stream: BytesIO
 
 
-class TableStructureOptions(BaseModel):
-    do_cell_matching: bool = (
-        True
-        # True:  Matches predictions back to PDF cells. Can break table output if PDF cells
-        #        are merged across table columns.
-        # False: Let table structure model define the text cells, ignore PDF cells.
-    )
-
-
-class PipelineOptions(BaseModel):
-    do_table_structure: bool = True  # True: perform table structure extraction
-    do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text
-
-    table_structure_options: TableStructureOptions = TableStructureOptions()
-
-
 class AssembleOptions(BaseModel):
     keep_page_images: Annotated[
         bool,

docling/datamodel/document.py

@@ -4,13 +4,13 @@ from pathlib import Path, PurePath
 from typing import ClassVar, Dict, Iterable, List, Optional, Tuple, Type, Union
 
 from docling_core.types import BaseCell, BaseText
-from docling_core.types import BoundingBox as DsBoundingBox
 from docling_core.types import Document as DsDocument
 from docling_core.types import DocumentDescription as DsDocumentDescription
 from docling_core.types import FileInfoObject as DsFileInfoObject
 from docling_core.types import PageDimensions, PageReference, Prov, Ref
 from docling_core.types import Table as DsSchemaTable
 from docling_core.types import TableCell
+from docling_core.types.doc.base import BoundingBox as DsBoundingBox
 from docling_core.types.doc.base import Figure
 from pydantic import BaseModel
 from typing_extensions import deprecated

docling/datamodel/pipeline_options.py

@@ -0,0 +1,25 @@
+from enum import Enum, auto
+
+from pydantic import BaseModel
+
+
+class TableFormerMode(str, Enum):
+    FAST = auto()
+    ACCURATE = auto()
+
+
+class TableStructureOptions(BaseModel):
+    do_cell_matching: bool = (
+        True
+        # True:  Matches predictions back to PDF cells. Can break table output if PDF cells
+        #        are merged across table columns.
+        # False: Let table structure model define the text cells, ignore PDF cells.
+    )
+    mode: TableFormerMode = TableFormerMode.FAST
+
+
+class PipelineOptions(BaseModel):
+    do_table_structure: bool = True  # True: perform table structure extraction
+    do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text
+
+    table_structure_options: TableStructureOptions = TableStructureOptions()

docling/document_converter.py

@@ -18,13 +18,13 @@ from docling.datamodel.base_models import (
     DoclingComponentType,
     ErrorItem,
     Page,
-    PipelineOptions,
 )
 from docling.datamodel.document import (
     ConversionResult,
     DocumentConversionInput,
     InputDocument,
 )
+from docling.datamodel.pipeline_options import PipelineOptions
 from docling.datamodel.settings import settings
 from docling.models.ds_glm_model import GlmModel
 from docling.models.page_assemble_model import PageAssembleModel

docling/models/table_structure_model.py

@@ -1,4 +1,5 @@
 import copy
+from pathlib import Path
 from typing import Iterable, List
 
 import numpy
@@ -12,16 +13,22 @@ from docling.datamodel.base_models import (
     TableElement,
     TableStructurePrediction,
 )
+from docling.datamodel.pipeline_options import TableFormerMode
 
 
 class TableStructureModel:
     def __init__(self, config):
         self.config = config
         self.do_cell_matching = config["do_cell_matching"]
+        self.mode = config["mode"]
 
         self.enabled = config["enabled"]
         if self.enabled:
-            artifacts_path = config["artifacts_path"]
+            artifacts_path: Path = config["artifacts_path"]
+
+            if self.mode == TableFormerMode.ACCURATE:
+                artifacts_path = artifacts_path / "fat"
+
             # Third Party
             import docling_ibm_models.tableformer.common as c
 

docling/pipeline/base_model_pipeline.py

@@ -1,7 +1,8 @@
 from pathlib import Path
 from typing import Callable, Iterable, List
 
-from docling.datamodel.base_models import Page, PipelineOptions
+from docling.datamodel.base_models import Page
+from docling.datamodel.pipeline_options import PipelineOptions
 
 
 class BaseModelPipeline:

docling/pipeline/standard_model_pipeline.py

@@ -1,6 +1,6 @@
 from pathlib import Path
 
-from docling.datamodel.base_models import PipelineOptions
+from docling.datamodel.pipeline_options import PipelineOptions
 from docling.models.easyocr_model import EasyOcrModel
 from docling.models.layout_model import LayoutModel
 from docling.models.table_structure_model import TableStructureModel
@@ -32,6 +32,7 @@ class StandardModelPipeline(BaseModelPipeline):
                     "artifacts_path": artifacts_path
                     / StandardModelPipeline._table_model_path,
                     "enabled": pipeline_options.do_table_structure,
+                    "mode": pipeline_options.table_structure_options.mode,
                     "do_cell_matching": pipeline_options.table_structure_options.do_cell_matching,
                 }
             ),

{docling-1.15.0.dist-info → docling-1.16.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.15.0
+Version: 1.16.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -19,7 +19,6 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Provides-Extra: examples
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.21.1,<0.22.0)
 Requires-Dist: docling-core (>=1.6.2,<2.0.0)
@@ -28,17 +27,10 @@ Requires-Dist: docling-parse (>=1.2.0,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
-Requires-Dist: langchain-huggingface (>=0.0.3,<0.0.4) ; extra == "examples"
-Requires-Dist: langchain-milvus (>=0.1.4,<0.2.0) ; extra == "examples"
-Requires-Dist: langchain-text-splitters (>=0.2.4,<0.3.0) ; extra == "examples"
-Requires-Dist: llama-index-embeddings-huggingface (>=0.3.1,<0.4.0) ; extra == "examples"
-Requires-Dist: llama-index-llms-huggingface-api (>=0.2.0,<0.3.0) ; extra == "examples"
-Requires-Dist: llama-index-vector-stores-milvus (>=0.2.1,<0.3.0) ; extra == "examples"
 Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
 Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)
-Requires-Dist: python-dotenv (>=1.0.1,<2.0.0) ; extra == "examples"
 Requires-Dist: requests (>=2.32.3,<3.0.0)
 Requires-Dist: rtree (>=1.3.0,<2.0.0)
 Requires-Dist: scipy (>=1.14.1,<2.0.0)
@@ -211,6 +203,8 @@ This can improve output quality if you find that multiple columns in extracted t
 
 
 ```python
+from docling.datamodel.pipeline_options import PipelineOptions
+
 pipeline_options = PipelineOptions(do_table_structure=True)
 pipeline_options.table_structure_options.do_cell_matching = False  # uses text cells predicted from table structure model
 
@@ -220,6 +214,20 @@ doc_converter = DocumentConverter(
 )
 ```
 
+Since docling 1.16.0: You can control which TableFormer mode you want to use. Choose between `TableFormerMode.FAST` (default) and `TableFormerMode.ACCURATE` (better, but slower) to receive better quality with difficult table structures.
+
+```python
+from docling.datamodel.pipeline_options import PipelineOptions, TableFormerMode
+
+pipeline_options = PipelineOptions(do_table_structure=True)
+pipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE  # use more accurate TableFormer model
+
+doc_converter = DocumentConverter(
+    artifacts_path=artifacts_path,
+    pipeline_options=pipeline_options,
+)
+```
+
 ### Impose limits on the document size
 
 You can limit the file size and number of pages which should be allowed to process per document:

{docling-1.15.0.dist-info → docling-1.16.0.dist-info}/RECORD

@@ -4,28 +4,29 @@ docling/backend/abstract_backend.py,sha256=clJtGxLedpLriEhpx7oyxjmlwMLPorkv-1tdf
 docling/backend/docling_parse_backend.py,sha256=RUWWZbx2cUotZeeTkc-Lbg2k8MVFXFxaDjM4sPfaFZE,7475
 docling/backend/pypdfium2_backend.py,sha256=bIIImVM73wmcVcKMqjl4JF8CD-Qj2W5rZbI4G7clU4s,8877
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=gJBxgZIGza0UBUAPP8pVFp_Ma3rzB9CCw-w3Bs5wieE,7121
+docling/cli/main.py,sha256=dgzaRJib5jlDbV1JfIRRYRSCT-ZiJkRwsx7KjlSVbUU,7167
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=tE2Sxoe3e_fBZjq3GDo2NCughDMU5xDeAfkQgT72TRI,9168
-docling/datamodel/document.py,sha256=hzWObTCtPPU7tvMr5FRKAT-7JGK4lGoOJuAHyULYuxc,16186
+docling/datamodel/base_models.py,sha256=b2FXRhfHrJiBGr5OdlSJ1ssUzvU2rVjelfY5_0YoK8w,8732
+docling/datamodel/document.py,sha256=8iHylLaty-ZVYGzYmP61dZPtduzEyiRM79Tx3gS9UEU,16195
+docling/datamodel/pipeline_options.py,sha256=SuJzaLHTR_-ZZz8KB0wwYRxULTcnfQESiilOGCY0fpc,773
 docling/datamodel/settings.py,sha256=t5g6wrEJnPa9gBzMMl8ppgBRUYz-8xgopEtfMS0ZH28,733
-docling/document_converter.py,sha256=5OiNafoaVcQhZ8ATF69xRp2KyFyKeSMhmwEFUoCzP-k,10980
+docling/document_converter.py,sha256=bk345OKkHbBngc3QS6BevT8068yEt1cS-PtAH3k_tCo,11022
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_ocr_model.py,sha256=Ipl82a3AV2OsgMQSMEMpnWJ6MXcmyIQzmp52PmTaB0g,4465
 docling/models/ds_glm_model.py,sha256=VXGmj8cW0WKMz1He4tp1lZhXHkS8Z39U1G-ujkc7deU,3368
 docling/models/easyocr_model.py,sha256=ABIqALvtNNrDQ47fXaZ0lDFhOwKsYGUUlAPnIsFZgZA,2232
 docling/models/layout_model.py,sha256=ZFmaLXlRWUfsT1pJCiYVxhQFrBBsiz6Aw0m9GM3UvVM,11249
 docling/models/page_assemble_model.py,sha256=8eoG2WiFxPxq9TPvM-wkngb2gkr0tdtCRVXg1JcTETo,5550
-docling/models/table_structure_model.py,sha256=0wOeiRoma6et7FtoJZw2SA3wBd9-R9ivp5uvXBQqeM4,5768
+docling/models/table_structure_model.py,sha256=iHJjWdKCpTcH3l_ElMWnC5pt6tkUpIuByed304Fdq9w,6009
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_model_pipeline.py,sha256=H5XoADpsJEZls8BI3FnppR2ubltkQwf_er4Qr74rdQ8,561
-docling/pipeline/standard_model_pipeline.py,sha256=UTjyaEXvz9htYZz-IMTkn11cZwNjgvo_Fl2dfBVnRQs,1442
+docling/pipeline/base_model_pipeline.py,sha256=rrMog3EuiR5Gx9OWtfMj24rQvHCrWkxZ3g9OIr7LPSQ,607
+docling/pipeline/standard_model_pipeline.py,sha256=9HdUq9TjNOsE9ixA_MpWNmyQUaTg7SS-aVE0zP7Ujys,1522
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/export.py,sha256=bKLdbeUcR-rQsGPV1IqJkCHKMCv7X2QOHyxmjNuH3HE,4655
 docling/utils/layout_utils.py,sha256=FOFbL0hKzUoWXdZaeUvEtFqKv0IkPifIr4sdGW4suKs,31804
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-1.15.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-1.15.0.dist-info/METADATA,sha256=rPvnvD2kQvVibj_Iwf3U6LGjxDaX1Bm8p9dXBuNWPcY,13208
-docling-1.15.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-1.15.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-1.15.0.dist-info/RECORD,,
+docling-1.16.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-1.16.0.dist-info/METADATA,sha256=AESUBe1Ea2pC0vJvvNwLW7l_z26k3iriJiicLFU3U7E,13308
+docling-1.16.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-1.16.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-1.16.0.dist-info/RECORD,,