docling 2.3.0__tar.gz → 2.4.0__tar.gz

{docling-2.3.0 → docling-2.4.0}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.3.0
-Summary: Docling PDF conversion package
+Version: 2.4.0
+Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Home-page: https://github.com/DS4SD/docling
 License: MIT
-Keywords: docling,convert,document,pdf,layout model,segmentation,table structure,table former
+Keywords: docling,convert,document,pdf,docx,html,markdown,layout model,segmentation,table structure,table former
 Author: Christoph Auer
 Author-email: cau@zurich.ibm.com
 Requires-Python: >=3.10,<4.0
@@ -23,9 +23,9 @@ Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.26.1,<0.27.0)
-Requires-Dist: docling-core (>=2.2.3,<3.0.0)
-Requires-Dist: docling-ibm-models (>=2.0.1,<3.0.0)
-Requires-Dist: docling-parse (>=2.0.0,<3.0.0)
+Requires-Dist: docling-core (>=2.3.0,<3.0.0)
+Requires-Dist: docling-ibm-models (>=2.0.3,<3.0.0)
+Requires-Dist: docling-parse (>=2.0.2,<3.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -41,10 +41,6 @@ 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)
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
-Requires-Dist: torch (>=2.2.2,<2.3.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
-Requires-Dist: torch (>=2.2.2,<3.0.0) ; sys_platform != "darwin" or platform_machine != "x86_64"
-Requires-Dist: torchvision (>=0,<1) ; sys_platform != "darwin" or platform_machine != "x86_64"
-Requires-Dist: torchvision (>=0.17.2,<0.18.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
 Description-Content-Type: text/markdown

{docling-2.3.0 → docling-2.4.0}/docling/cli/main.py

@@ -5,12 +5,15 @@ import time
 import warnings
 from enum import Enum
 from pathlib import Path
-from typing import Annotated, Dict, Iterable, List, Optional
+from typing import Annotated, Dict, Iterable, List, Optional, Type
 
 import typer
 from docling_core.utils.file import resolve_file_source
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docling.backend.pdf_backend import PdfDocumentBackend
+from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel.base_models import (
     ConversionStatus,
     FormatToExtensions,
@@ -22,6 +25,7 @@ from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrOptions,
     PdfPipelineOptions,
+    TableFormerMode,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
@@ -58,9 +62,10 @@ def version_callback(value: bool):
 
 
 # Define an enum for the backend options
-class Backend(str, Enum):
+class PdfBackend(str, Enum):
     PYPDFIUM2 = "pypdfium2"
-    DOCLING = "docling"
+    DLPARSE_V1 = "dlparse_v1"
+    DLPARSE_V2 = "dlparse_v2"
 
 
 # Define an enum for the ocr engines
@@ -90,28 +95,28 @@ def export_documents(
             # Export Deep Search document JSON format:
             if export_json:
                 fname = output_dir / f"{doc_filename}.json"
-                with fname.open("w") as fp:
+                with fname.open("w", encoding="utf8") as fp:
                     _log.info(f"writing JSON output to {fname}")
                     fp.write(json.dumps(conv_res.document.export_to_dict()))
 
             # Export Text format:
             if export_txt:
                 fname = output_dir / f"{doc_filename}.txt"
-                with fname.open("w") as fp:
+                with fname.open("w", encoding="utf8") as fp:
                     _log.info(f"writing Text output to {fname}")
                     fp.write(conv_res.document.export_to_markdown(strict_text=True))
 
             # Export Markdown format:
             if export_md:
                 fname = output_dir / f"{doc_filename}.md"
-                with fname.open("w") as fp:
+                with fname.open("w", encoding="utf8") as fp:
                     _log.info(f"writing Markdown output to {fname}")
                     fp.write(conv_res.document.export_to_markdown())
 
             # Export Document Tags format:
             if export_doctags:
                 fname = output_dir / f"{doc_filename}.doctags"
-                with fname.open("w") as fp:
+                with fname.open("w", encoding="utf8") as fp:
                     _log.info(f"writing Doc Tags output to {fname}")
                     fp.write(conv_res.document.export_to_document_tokens())
 
@@ -151,6 +156,17 @@ def convert(
     ocr_engine: Annotated[
         OcrEngine, typer.Option(..., help="The OCR engine to use.")
     ] = OcrEngine.EASYOCR,
+    pdf_backend: Annotated[
+        PdfBackend, typer.Option(..., help="The PDF backend to use.")
+    ] = PdfBackend.DLPARSE_V1,
+    table_mode: Annotated[
+        TableFormerMode,
+        typer.Option(..., help="The mode to use in the table structure model."),
+    ] = TableFormerMode.FAST,
+    artifacts_path: Annotated[
+        Optional[Path],
+        typer.Option(..., help="If provided, the location of the model artifacts."),
+    ] = None,
     abort_on_error: Annotated[
         bool,
         typer.Option(
@@ -217,11 +233,25 @@ def convert(
         do_table_structure=True,
     )
     pipeline_options.table_structure_options.do_cell_matching = True  # do_cell_matching
+    pipeline_options.table_structure_options.mode = table_mode
+
+    if artifacts_path is not None:
+        pipeline_options.artifacts_path = artifacts_path
+
+    match pdf_backend:
+        case PdfBackend.DLPARSE_V1:
+            backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
+        case PdfBackend.DLPARSE_V2:
+            backend = DoclingParseV2DocumentBackend
+        case PdfBackend.PYPDFIUM2:
+            backend = PyPdfiumDocumentBackend
+        case _:
+            raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
 
     format_options: Dict[InputFormat, FormatOption] = {
         InputFormat.PDF: PdfFormatOption(
             pipeline_options=pipeline_options,
-            backend=DoclingParseDocumentBackend,  # pdf_backend
+            backend=backend,  # pdf_backend
         )
     }
     doc_converter = DocumentConverter(

{docling-2.3.0 → docling-2.4.0}/docling/datamodel/pipeline_options.py

@@ -1,4 +1,4 @@
-from enum import Enum, auto
+from enum import Enum
 from pathlib import Path
 from typing import List, Literal, Optional, Union
 
@@ -6,8 +6,8 @@ from pydantic import BaseModel, ConfigDict, Field
 
 
 class TableFormerMode(str, Enum):
-    FAST = auto()
-    ACCURATE = auto()
+    FAST = "fast"
+    ACCURATE = "accurate"
 
 
 class TableStructureOptions(BaseModel):

{docling-2.3.0 → docling-2.4.0}/docling/document_converter.py

@@ -139,6 +139,10 @@ class DocumentConverter:
 
         self.initialized_pipelines: Dict[Type[BasePipeline], BasePipeline] = {}
 
+    def initialize_pipeline(self, format: InputFormat):
+        """Initialize the conversion pipeline for the selected format."""
+        self._get_pipeline(doc_format=format)
+
     @validate_call(config=ConfigDict(strict=True))
     def convert(
         self,
@@ -219,13 +223,13 @@ class DocumentConverter:
                 else:
                     _log.info(f"Skipped a document. We lost {elapsed:.2f} sec.")
 
-    def _get_pipeline(self, doc: InputDocument) -> Optional[BasePipeline]:
+    def _get_pipeline(self, doc_format: InputFormat) -> Optional[BasePipeline]:
         assert self.format_to_options is not None
 
-        fopt = self.format_to_options.get(doc.format)
+        fopt = self.format_to_options.get(doc_format)
 
         if fopt is None:
-            raise RuntimeError(f"Could not get pipeline for document {doc.file}")
+            raise RuntimeError(f"Could not get pipeline for {doc_format}")
         else:
             pipeline_class = fopt.pipeline_cls
             pipeline_options = fopt.pipeline_options
@@ -256,7 +260,7 @@ class DocumentConverter:
         self, in_doc: InputDocument, raises_on_error: bool
     ) -> ConversionResult:
         if in_doc.valid:
-            pipeline = self._get_pipeline(in_doc)
+            pipeline = self._get_pipeline(in_doc.format)
             if pipeline is None:  # Can't find a default pipeline. Should this raise?
                 if raises_on_error:
                     raise RuntimeError(

{docling-2.3.0 → docling-2.4.0}/pyproject.toml

@@ -1,13 +1,13 @@
 [tool.poetry]
 name = "docling"
-version = "2.3.0"  # DO NOT EDIT, updated automatically
-description = "Docling PDF conversion package"
-authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
+version = "2.4.0"  # DO NOT EDIT, updated automatically
+description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
+authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Panos Vagenas <pva@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
 readme = "README.md"
 repository = "https://github.com/DS4SD/docling"
 homepage = "https://github.com/DS4SD/docling"
-keywords= ["docling", "convert", "document", "pdf", "layout model", "segmentation", "table structure", "table former"]
+keywords= ["docling", "convert", "document", "pdf", "docx", "html", "markdown", "layout model", "segmentation", "table structure", "table former"]
  classifiers = [
      "License :: OSI Approved :: MIT License",
      "Operating System :: MacOS :: MacOS X",
@@ -21,24 +21,13 @@ keywords= ["docling", "convert", "document", "pdf", "layout model", "segmentatio
 packages = [{include = "docling"}]
 
 [tool.poetry.dependencies]
-##############
-# constraints:
-##############
-torch = [
-  {version = "^2.2.2", optional = true, markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'"},
-  {version = "~2.2.2", optional = true, markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'"}
-]
-torchvision = [
-  {version = "^0", optional = true, markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'"},
-  {version = "~0.17.2", optional = true, markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'"}
-]
 ######################
 # actual dependencies:
 ######################
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^2.2.3"
-docling-ibm-models = "^2.0.1"
+docling-core = "^2.3.0"
+docling-ibm-models = "^2.0.3"
 deepsearch-glm = "^0.26.1"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
@@ -47,7 +36,7 @@ huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = "^1.7"
 tesserocr = { version = "^2.7.1", optional = true }
-docling-parse = "^2.0.0"
+docling-parse = "^2.0.2"
 certifi = ">=2024.7.4"
 rtree = "^1.3.0"
 scipy = "^1.14.1"
@@ -84,16 +73,23 @@ mkdocs-jupyter = "^0.25.0"
 [tool.poetry.group.examples.dependencies]
 datasets = "^2.21.0"
 python-dotenv = "^1.0.1"
-# llama-index-readers-docling = { version = "^0.1.0", markers = 'python_version < "3.13"' }
-# llama-index-node-parser-docling = { version = "^0.1.0", markers = 'python_version < "3.13"' }
-# llama-index-readers-file = { version = "^0.2.2", markers = 'python_version < "3.13"' }
-# llama-index-embeddings-huggingface = { version = "^0.3.1", markers = 'python_version < "3.13"' }
-# llama-index-llms-huggingface-api = { version = "^0.2.0", markers = 'python_version < "3.13"' }
-# llama-index-vector-stores-milvus ={ version =  "^0.2.1", markers = 'python_version < "3.13"' }
 langchain-huggingface = "^0.0.3"
 langchain-milvus = "^0.1.4"
 langchain-text-splitters = "^0.2.4"
 
+[tool.poetry.group.mac_intel]
+optional = true
+
+[tool.poetry.group.mac_intel.dependencies]
+torch = [
+  {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2"},
+  {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2"}
+]
+torchvision = [
+  {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0"},
+  {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2"}
+]
+
 [tool.poetry.extras]
 tesserocr = ["tesserocr"]