Import statement updates from docling-core

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

docling/backend/abstract_backend.py

@@ -3,7 +3,7 @@ from io import BytesIO
 from pathlib import Path
 from typing import TYPE_CHECKING, Set, Union
 
-from docling_core.types.experimental import DoclingDocument
+from docling_core.types.doc import DoclingDocument
 
 if TYPE_CHECKING:
     from docling.datamodel.base_models import InputFormat

docling/backend/docling_parse_backend.py

@@ -5,7 +5,7 @@ from pathlib import Path
 from typing import Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
-from docling_core.types.experimental import BoundingBox, CoordOrigin, Size
+from docling_core.types.doc import BoundingBox, CoordOrigin, Size
 from docling_parse.docling_parse import pdf_parser
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage

docling/backend/html_backend.py

@@ -4,14 +4,14 @@ from pathlib import Path
 from typing import Set, Union
 
 from bs4 import BeautifulSoup
-from docling_core.types.experimental import (
+from docling_core.types.doc import (
     DescriptionItem,
     DoclingDocument,
     PictureData,
     TableCell,
     TableData,
 )
-from docling_core.types.experimental.labels import DocItemLabel, GroupLabel
+from docling_core.types.doc.labels import DocItemLabel, GroupLabel
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
 from docling.datamodel.base_models import InputFormat

docling/backend/mspowerpoint_backend.py

@@ -3,7 +3,7 @@ from io import BytesIO
 from pathlib import Path
 from typing import Set, Union
 
-from docling_core.types.experimental import (
+from docling_core.types.doc import (
     DescriptionItem,
     DocItemLabel,
     DoclingDocument,
@@ -14,7 +14,7 @@ from docling_core.types.experimental import (
     TableCell,
     TableData,
 )
-from docling_core.types.experimental.base import BoundingBox, CoordOrigin, Size
+from docling_core.types.doc.base import BoundingBox, CoordOrigin, Size
 from pptx import Presentation
 from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
 

docling/backend/msword_backend.py

@@ -4,7 +4,7 @@ from pathlib import Path
 from typing import Set, Union
 
 import docx
-from docling_core.types.experimental import (
+from docling_core.types.doc import (
     DescriptionItem,
     DocItemLabel,
     DoclingDocument,

docling/backend/pdf_backend.py

@@ -2,8 +2,8 @@ from abc import ABC, abstractmethod
 from io import BytesIO
 from typing import Iterable, Optional, Set, Union
 
-from docling_core.types.doc.doc_ocr import Path
+from docling_core.types.doc import BoundingBox, Size
-from docling_core.types.experimental import BoundingBox, Size
+from docling_core.types.legacy_doc.doc_ocr import Path
 from PIL import Image
 
 from docling.backend.abstract_backend import PaginatedDocumentBackend

docling/backend/pypdfium2_backend.py

@@ -6,7 +6,7 @@ from typing import Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
 import pypdfium2.raw as pdfium_c
-from docling_core.types.experimental import BoundingBox, CoordOrigin, Size
+from docling_core.types.doc import BoundingBox, CoordOrigin, Size
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfTextPage
 from pypdfium2._helpers.misc import PdfiumError

docling/cli/main.py

@@ -137,10 +137,10 @@ def convert(
     from_formats: List[InputFormat] = typer.Option(
         None,
         "--from",
-        help="Specify input formats " "to convert from. Defaults to all formats.",
+        help="Specify input formats to convert from. Defaults to all formats.",
     ),
     to_formats: List[OutputFormat] = typer.Option(
-        None, "--to", help="Specify output formats. " "Defaults to Markdown."
+        None, "--to", help="Specify output formats. Defaults to Markdown."
     ),
     ocr: Annotated[
         bool,
@@ -148,9 +148,6 @@ def convert(
             ..., help="If enabled, the bitmap content will be processed using OCR."
         ),
     ] = True,
-    # backend: Annotated[
-    #    Backend, typer.Option(..., help="The PDF backend to use.")
-    # ] = Backend.DOCLING,
     ocr_engine: Annotated[
         OcrEngine, typer.Option(..., help="The OCR engine to use.")
     ] = OcrEngine.EASYOCR,
@@ -196,16 +193,6 @@ def convert(
     export_txt = OutputFormat.TEXT in to_formats
     export_doctags = OutputFormat.DOCTAGS in to_formats
 
-    # match backend:
-    #     case Backend.PYPDFIUM2:
-    #         do_cell_matching = ocr  # only do cell matching when OCR enabled
-    #         pdf_backend = PyPdfiumDocumentBackend
-    #     case Backend.DOCLING:
-    #         do_cell_matching = True
-    #         pdf_backend = DoclingParseDocumentBackend
-    #     case _:
-    #         raise RuntimeError(f"Unexpected backend type {backend}")
-
     match ocr_engine:
         case OcrEngine.EASYOCR:
             ocr_options = EasyOcrOptions()

docling/datamodel/base_models.py

@@ -2,9 +2,9 @@ from enum import Enum, auto
 from io import BytesIO
 from typing import TYPE_CHECKING, Dict, List, Optional, Set, Union
 
-from docling_core.types.experimental import BoundingBox, Size
+from docling_core.types.doc import BoundingBox, Size
-from docling_core.types.experimental.document import PictureData, TableCell
+from docling_core.types.doc.document import PictureData, TableCell
-from docling_core.types.experimental.labels import DocItemLabel
+from docling_core.types.doc.labels import DocItemLabel
 from PIL.Image import Image
 from pydantic import BaseModel, ConfigDict
 

docling/datamodel/document.py

@@ -12,9 +12,7 @@ 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.doc.base import BoundingBox as DsBoundingBox
+from docling_core.types.doc import (
-from docling_core.types.doc.base import Figure, GlmTableCell, TableCell
-from docling_core.types.experimental import (
     DescriptionItem,
     DocItem,
     DocItemLabel,
@@ -24,7 +22,9 @@ from docling_core.types.experimental import (
     TableItem,
     TextItem,
 )
-from docling_core.types.experimental.document import ListItem
+from docling_core.types.doc.document import ListItem
+from docling_core.types.legacy_doc.base import BoundingBox as DsBoundingBox
+from docling_core.types.legacy_doc.base import Figure, GlmTableCell, TableCell
 from docling_core.utils.file import resolve_file_source
 from pydantic import BaseModel
 from typing_extensions import deprecated

docling/models/base_model.py

@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
 from typing import Any, Iterable
 
-from docling_core.types.experimental import DoclingDocument, NodeItem
+from docling_core.types.doc import DoclingDocument, NodeItem
 
 from docling.datamodel.base_models import Page
 

docling/models/base_ocr_model.py

@@ -4,7 +4,7 @@ from abc import abstractmethod
 from typing import Iterable, List, Tuple
 
 import numpy as np
-from docling_core.types.experimental import BoundingBox, CoordOrigin
+from docling_core.types.doc import BoundingBox, CoordOrigin
 from PIL import Image, ImageDraw
 from rtree import index
 from scipy.ndimage import find_objects, label

docling/models/ds_glm_model.py

@@ -15,10 +15,10 @@ 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.doc.base import BoundingBox as DsBoundingBox
+from docling_core.types.doc import BoundingBox, CoordOrigin
-from docling_core.types.doc.base import Figure, TableCell
+from docling_core.types.doc.document import DoclingDocument
-from docling_core.types.experimental import BoundingBox, CoordOrigin
+from docling_core.types.legacy_doc.base import BoundingBox as DsBoundingBox
-from docling_core.types.experimental.document import DoclingDocument
+from docling_core.types.legacy_doc.base import Figure, TableCell
 from PIL import ImageDraw
 from pydantic import BaseModel, ConfigDict
 

docling/models/dummy_picture_enrichment.py

@@ -1,10 +1,7 @@
 from typing import Any, Iterable
 
-from docling_core.types.experimental import DoclingDocument, NodeItem
+from docling_core.types.doc import DoclingDocument, NodeItem
-from docling_core.types.experimental.document import (
+from docling_core.types.doc.document import PictureClassificationData, PictureItem
-    PictureClassificationData,
-    PictureItem,
-)
 
 from docling.models.base_model import BaseEnrichmentModel
 

docling/models/easyocr_model.py

@@ -2,7 +2,7 @@ import logging
 from typing import Iterable
 
 import numpy
-from docling_core.types.experimental import BoundingBox, CoordOrigin
+from docling_core.types.doc import BoundingBox, CoordOrigin
 
 from docling.datamodel.base_models import OcrCell, Page
 from docling.datamodel.pipeline_options import EasyOcrOptions

docling/models/layout_model.py

@@ -5,8 +5,8 @@ import time
 from pathlib import Path
 from typing import Iterable, List
 
-from docling_core.types.experimental import CoordOrigin
+from docling_core.types.doc import CoordOrigin
-from docling_core.types.experimental.labels import DocItemLabel
+from docling_core.types.doc.labels import DocItemLabel
 from docling_ibm_models.layoutmodel.layout_predictor import LayoutPredictor
 from PIL import ImageDraw
 

docling/models/table_structure_model.py

@@ -3,9 +3,9 @@ from pathlib import Path
 from typing import Iterable, List
 
 import numpy
-from docling_core.types.experimental import BoundingBox
+from docling_core.types.doc import BoundingBox
-from docling_core.types.experimental.document import TableCell
+from docling_core.types.doc.document import TableCell
-from docling_core.types.experimental.labels import DocItemLabel
+from docling_core.types.doc.labels import DocItemLabel
 from docling_ibm_models.tableformer.data_management.tf_predictor import TFPredictor
 from PIL import ImageDraw
 

docling/models/tesseract_ocr_cli_model.py

@@ -5,7 +5,7 @@ from subprocess import DEVNULL, PIPE, Popen
 from typing import Iterable, Tuple
 
 import pandas as pd
-from docling_core.types.experimental import BoundingBox, CoordOrigin
+from docling_core.types.doc import BoundingBox, CoordOrigin
 
 from docling.datamodel.base_models import OcrCell, Page
 from docling.datamodel.pipeline_options import TesseractCliOcrOptions

docling/models/tesseract_ocr_model.py

@@ -1,7 +1,7 @@
 import logging
 from typing import Iterable
 
-from docling_core.types.experimental import BoundingBox, CoordOrigin
+from docling_core.types.doc import BoundingBox, CoordOrigin
 
 from docling.datamodel.base_models import OcrCell, Page
 from docling.datamodel.pipeline_options import TesseractCliOcrOptions

docling/pipeline/base_pipeline.py

@@ -5,7 +5,7 @@ import traceback
 from abc import ABC, abstractmethod
 from typing import Callable, Iterable, List
 
-from docling_core.types.experimental import DoclingDocument, NodeItem
+from docling_core.types.doc import DoclingDocument, NodeItem
 
 from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend

docling/utils/export.py

@@ -1,8 +1,8 @@
 import logging
 from typing import Any, Dict, Iterable, List, Tuple, Union
 
-from docling_core.types.doc.base import BaseCell, BaseText, Ref, Table
+from docling_core.types.doc import BoundingBox, CoordOrigin
-from docling_core.types.experimental import BoundingBox, CoordOrigin
+from docling_core.types.legacy_doc.base import BaseCell, BaseText, Ref, Table
 
 from docling.datamodel.base_models import OcrCell
 from docling.datamodel.document import ConversionResult, Page

docling/utils/layout_utils.py

@@ -2,7 +2,7 @@ import copy
 import logging
 
 import networkx as nx
-from docling_core.types.experimental.labels import DocItemLabel
+from docling_core.types.doc.labels import DocItemLabel
 
 logger = logging.getLogger("layout_utils")
 

examples/batch_convert.py

@@ -32,23 +32,23 @@ def export_documents(
             doc_filename = conv_res.input.file.stem
 
             if USE_V2:
-                # Export Docling document format to JSON (experimental):
+                # Export Docling document format to JSON:
                 with (output_dir / f"{doc_filename}.json").open("w") as fp:
                     fp.write(json.dumps(conv_res.document.export_to_dict()))
 
-                # Export Docling document format to YAML (experimental):
+                # Export Docling document format to YAML:
                 with (output_dir / f"{doc_filename}.yaml").open("w") as fp:
                     fp.write(yaml.safe_dump(conv_res.document.export_to_dict()))
 
-                # Export Docling document format to doctags (experimental):
+                # Export Docling document format to doctags:
                 with (output_dir / f"{doc_filename}.doctags.txt").open("w") as fp:
                     fp.write(conv_res.document.export_to_document_tokens())
 
-                # Export Docling document format to markdown (experimental):
+                # Export Docling document format to markdown:
                 with (output_dir / f"{doc_filename}.md").open("w") as fp:
                     fp.write(conv_res.document.export_to_markdown())
 
-                # Export Docling document format to text (experimental):
+                # Export Docling document format to text:
                 with (output_dir / f"{doc_filename}.txt").open("w") as fp:
                     fp.write(conv_res.document.export_to_markdown(strict_text=True))
 

examples/run_with_formats.py

@@ -58,8 +58,8 @@ for res in conv_results:
         f"Document {res.input.file.name} converted."
         f"\nSaved markdown output to: {str(out_path)}"
     )
-    # print(res.experimental.export_to_markdown())
+    # print(res.docdocument.export_to_markdown())
-    # Export Docling document format to markdown (experimental):
+    # Export Docling document format to markdowndoc:
     with (out_path / f"{res.input.file.name}.md").open("w") as fp:
         fp.write(res.document.export_to_markdown())
 

poetry.lock

@@ -885,7 +885,7 @@ files = []
 develop = false
 
 [package.dependencies]
-docling-core = {git = "https://github.com/DS4SD/docling-core.git", rev = "4ddecf80cf5afb4b1488172ecafcf12cb2b8cb9b"}
+docling-core = {git = "https://github.com/DS4SD/docling-core.git", rev = "6fee533a101ca08f62e88826218c33e0aab2f417"}
 docutils = "!=0.21"
 matplotlib = "^3.7.1"
 networkx = "^3.1"
@@ -909,8 +909,8 @@ toolkit = ["deepsearch-toolkit (>=0.31.0)"]
 [package.source]
 type = "git"
 url = "https://github.com/DS4SD/deepsearch-glm.git"
-reference = "58c589fc23d675e8098f24ec680a9bf93e2a796e"
+reference = "c13a6cdda25206911d63a5a28e990217ad823068"
-resolved_reference = "58c589fc23d675e8098f24ec680a9bf93e2a796e"
+resolved_reference = "c13a6cdda25206911d63a5a28e990217ad823068"
 
 [[package]]
 name = "dill"
@@ -958,8 +958,8 @@ tabulate = "^0.9.0"
 [package.source]
 type = "git"
 url = "https://github.com/DS4SD/docling-core.git"
-reference = "4ddecf80cf5afb4b1488172ecafcf12cb2b8cb9b"
+reference = "6fee533a101ca08f62e88826218c33e0aab2f417"
-resolved_reference = "4ddecf80cf5afb4b1488172ecafcf12cb2b8cb9b"
+resolved_reference = "6fee533a101ca08f62e88826218c33e0aab2f417"
 
 [[package]]
 name = "docling-ibm-models"
@@ -2296,22 +2296,18 @@ transformers = ">=4.39.0"
 
 [[package]]
 name = "langchain-milvus"
-version = "0.1.5"
+version = "0.1.6"
 description = "An integration package connecting Milvus and LangChain"
 optional = false
-python-versions = "<4.0,>=3.8.1"
+python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langchain_milvus-0.1.5-py3-none-any.whl", hash = "sha256:74aa487738afde4c3e1346433ef26f9556e599826161562b308d3357d86529fd"},
+    {file = "langchain_milvus-0.1.6-py3-none-any.whl", hash = "sha256:efab3fcf613bd6151735e2c75f3264dba9daecb317b9bb22604c2aac579049a9"},
-    {file = "langchain_milvus-0.1.5.tar.gz", hash = "sha256:1cceab384783ba264055102e5831451482fd726a68feb64258f6dbbd8d702557"},
+    {file = "langchain_milvus-0.1.6.tar.gz", hash = "sha256:155979a6e5aeb94b0e141a12d2fdb4c34a4d7a0e5da2cec1ae7c9bccf6649205"},
 ]
 
 [package.dependencies]
-langchain-core = {version = ">=0.2.38,<0.4", markers = "python_version >= \"3.9\""}
+langchain-core = ">=0.2.38,<0.4"
 pymilvus = ">=2.4.3,<3.0.0"
-scipy = [
-    {version = ">=1.9,<2.0", markers = "python_version >= \"3.12\""},
-    {version = ">=1.7,<2.0", markers = "python_version < \"3.12\""},
-]
 
 [[package]]
 name = "langchain-text-splitters"
@@ -2329,13 +2325,13 @@ langchain-core = ">=0.2.38,<0.3.0"
 
 [[package]]
 name = "langsmith"
-version = "0.1.134"
+version = "0.1.135"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langsmith-0.1.134-py3-none-any.whl", hash = "sha256:ada98ad80ef38807725f32441a472da3dd28394010877751f48f458d3289da04"},
+    {file = "langsmith-0.1.135-py3-none-any.whl", hash = "sha256:b1d1ca3bad483a4239745c57e9b9157b4d099fbf3149be21e3d112c94ede06ac"},
-    {file = "langsmith-0.1.134.tar.gz", hash = "sha256:23abee3b508875a0e63c602afafffc02442a19cfd88f9daae05b3e9054fd6b61"},
+    {file = "langsmith-0.1.135.tar.gz", hash = "sha256:7abed7e141386af99a2177f0b3600b124ae3ad1b482879ba0724ce92ef998a11"},
 ]
 
 [package.dependencies]
@@ -7118,4 +7114,4 @@ tesserocr = ["tesserocr"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "9678a9fb33ecbfbc6ec118fd3209aab5ab4e4c90d589e93c4dc7073dc9fb72ae"
+content-hash = "46f6c1eb76034223f7d65760f6ebe0989ba9e8aff46fcdbce82c147030fcb8be"

pyproject.toml

@@ -37,9 +37,9 @@ torchvision = [
 ######################
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = {git = "https://github.com/DS4SD/docling-core.git", rev = "4ddecf80cf5afb4b1488172ecafcf12cb2b8cb9b"}
+docling-core = {git = "https://github.com/DS4SD/docling-core.git", rev = "6fee533a101ca08f62e88826218c33e0aab2f417"}
 docling-ibm-models = {git = "https://github.com/DS4SD/docling-ibm-models.git", rev = "1d2e2a2e6eb152c237f1383cdba20cf85db80b97"}
-deepsearch-glm = {git = "https://github.com/DS4SD/deepsearch-glm.git", rev = "58c589fc23d675e8098f24ec680a9bf93e2a796e"}
+deepsearch-glm = {git = "https://github.com/DS4SD/deepsearch-glm.git", rev = "c13a6cdda25206911d63a5a28e990217ad823068"}
 docling-parse = "^1.5.1"
 
 filetype = "^1.2.0"

tests/test_backend_docling_parse.py

@@ -1,7 +1,7 @@
 from pathlib import Path
 
 import pytest
-from docling_core.types.experimental import BoundingBox
+from docling_core.types.doc import BoundingBox
 
 from docling.backend.docling_parse_backend import (
     DoclingParseDocumentBackend,

tests/test_backend_pdfium.py

@@ -1,7 +1,7 @@
 from pathlib import Path
 
 import pytest
-from docling_core.types.experimental.base import BoundingBox
+from docling_core.types.doc.base import BoundingBox
 
 from docling.backend.pypdfium2_backend import (
     PyPdfiumDocumentBackend,

tests/verify_utils.py

@@ -4,7 +4,7 @@ from pathlib import Path
 from typing import List
 
 from docling_core.types import Document as DsDocument
-from docling_core.types.experimental import DoclingDocument
+from docling_core.types.doc import DoclingDocument
 from pydantic import TypeAdapter
 from pydantic.json import pydantic_encoder