docling 2.3.1__tar.gz → 2.4.1__tar.gz

{docling-2.3.1 → docling-2.4.1}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.3.1
-Summary: Docling PDF conversion package
+Version: 2.4.1
+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
@@ -53,6 +53,10 @@ Description-Content-Type: text/markdown
 
 # Docling
 
+<p align="center">
+  <a href="https://trendshift.io/repositories/12132" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12132" alt="DS4SD%2Fdocling | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+
 [![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://ds4sd.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
@@ -66,19 +70,22 @@ Description-Content-Type: text/markdown
 
 Docling parses documents and exports them to the desired format with ease and speed.
 
-
 ## Features
 
 * 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
-* 📝 Metadata extraction, including title, authors, references & language
-* 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
+* 🤖 Easy integration with LlamaIndex 🦙 & LangChain 🦜🔗 for powerful RAG / QA applications
 * 🔍 OCR support for scanned PDFs
 * 💻 Simple and convenient CLI
 
 Explore the [documentation](https://ds4sd.github.io/docling/) to discover plenty examples and unlock the full power of Docling!
 
+### Coming soon
+
+* ♾️ Equation & code extraction
+* 📝 Metadata extraction, including title, authors, references & language
+* 🦜🔗 Native LangChain extension
 
 ## Installation
 
@@ -104,16 +111,13 @@ result = converter.convert(source)
 print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
 ```
 
-
 Check out [Getting started](https://ds4sd.github.io/docling/).
 You will find lots of tuning options to leverage all the advanced capabilities.
 
-
 ## Get help and support
 
 Please feel free to connect with us using the [discussion section](https://github.com/DS4SD/docling/discussions).
 
-
 ## Technical report
 
 For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).
@@ -122,7 +126,6 @@ For more details on Docling's inner workings, check out the [Docling Technical R
 
 Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main/CONTRIBUTING.md) for details.
 
-
 ## References
 
 If you use Docling in your projects, please consider citing the following:
@@ -142,6 +145,10 @@ If you use Docling in your projects, please consider citing the following:
 
 ## License
 
-The Docling codebase is under MIT license. 
+The Docling codebase is under MIT license.
 For individual model usage, please refer to the model licenses found in the original packages.
 
+## IBM ❤️ Open Source AI
+
+Docling has been brought to you by IBM.
+

{docling-2.3.1 → docling-2.4.1}/README.md

@@ -6,6 +6,10 @@
 
 # Docling
 
+<p align="center">
+  <a href="https://trendshift.io/repositories/12132" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12132" alt="DS4SD%2Fdocling | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+
 [![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://ds4sd.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
@@ -19,19 +23,22 @@
 
 Docling parses documents and exports them to the desired format with ease and speed.
 
-
 ## Features
 
 * 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
-* 📝 Metadata extraction, including title, authors, references & language
-* 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
+* 🤖 Easy integration with LlamaIndex 🦙 & LangChain 🦜🔗 for powerful RAG / QA applications
 * 🔍 OCR support for scanned PDFs
 * 💻 Simple and convenient CLI
 
 Explore the [documentation](https://ds4sd.github.io/docling/) to discover plenty examples and unlock the full power of Docling!
 
+### Coming soon
+
+* ♾️ Equation & code extraction
+* 📝 Metadata extraction, including title, authors, references & language
+* 🦜🔗 Native LangChain extension
 
 ## Installation
 
@@ -57,16 +64,13 @@ result = converter.convert(source)
 print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
 ```
 
-
 Check out [Getting started](https://ds4sd.github.io/docling/).
 You will find lots of tuning options to leverage all the advanced capabilities.
 
-
 ## Get help and support
 
 Please feel free to connect with us using the [discussion section](https://github.com/DS4SD/docling/discussions).
 
-
 ## Technical report
 
 For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).
@@ -75,7 +79,6 @@ For more details on Docling's inner workings, check out the [Docling Technical R
 
 Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main/CONTRIBUTING.md) for details.
 
-
 ## References
 
 If you use Docling in your projects, please consider citing the following:
@@ -95,5 +98,9 @@ If you use Docling in your projects, please consider citing the following:
 
 ## License
 
-The Docling codebase is under MIT license. 
+The Docling codebase is under MIT license.
 For individual model usage, please refer to the model licenses found in the original packages.
+
+## IBM ❤️ Open Source AI
+
+Docling has been brought to you by IBM.

{docling-2.3.1 → docling-2.4.1}/docling/backend/docling_parse_backend.py

@@ -29,7 +29,7 @@ class DoclingParsePageBackend(PdfPageBackend):
             self._dpage = parsed_page["pages"][0]
         else:
             _log.info(
-                f"An error occured when loading page {page_no} of document {document_hash}."
+                f"An error occurred when loading page {page_no} of document {document_hash}."
             )
 
     def is_valid(self) -> bool:

{docling-2.3.1 → docling-2.4.1}/docling/backend/docling_parse_v2_backend.py

@@ -31,7 +31,7 @@ class DoclingParseV2PageBackend(PdfPageBackend):
             self._dpage = parsed_page["pages"][0]
         else:
             _log.info(
-                f"An error occured when loading page {page_no} of document {document_hash}."
+                f"An error occurred when loading page {page_no} of document {document_hash}."
             )
 
     def is_valid(self) -> bool:

{docling-2.3.1 → docling-2.4.1}/docling/backend/pypdfium2_backend.py

@@ -29,7 +29,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
             self._ppage: pdfium.PdfPage = pdfium_doc[page_no]
         except PdfiumError as e:
             _log.info(
-                f"An exception occured when loading page {page_no} of document {document_hash}.",
+                f"An exception occurred when loading page {page_no} of document {document_hash}.",
                 exc_info=True,
             )
             self.valid = False

{docling-2.3.1 → docling-2.4.1}/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-2.3.1 → docling-2.4.1}/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-2.3.1 → docling-2.4.1}/docling/models/tesseract_ocr_model.py

@@ -22,25 +22,37 @@ class TesseractOcrModel(BaseOcrModel):
         self.reader = None
 
         if self.enabled:
-            setup_errmsg = (
+            install_errmsg = (
                 "tesserocr is not correctly installed. "
                 "Please install it via `pip install tesserocr` to use this OCR engine. "
-                "Note that tesserocr might have to be manually compiled for working with"
+                "Note that tesserocr might have to be manually compiled for working with "
                 "your Tesseract installation. The Docling documentation provides examples for it. "
-                "Alternatively, Docling has support for other OCR engines. See the documentation."
+                "Alternatively, Docling has support for other OCR engines. See the documentation: "
+                "https://ds4sd.github.io/docling/installation/"
             )
+            missing_langs_errmsg = (
+                "tesserocr is not correctly configured. No language models have been detected. "
+                "Please ensure that the TESSDATA_PREFIX envvar points to tesseract languages dir. "
+                "You can find more information how to setup other OCR engines in Docling "
+                "documentation: "
+                "https://ds4sd.github.io/docling/installation/"
+            )
+
             try:
                 import tesserocr
             except ImportError:
-                raise ImportError(setup_errmsg)
-
+                raise ImportError(install_errmsg)
             try:
                 tesseract_version = tesserocr.tesseract_version()
-                _log.debug("Initializing TesserOCR: %s", tesseract_version)
             except:
-                raise ImportError(setup_errmsg)
+                raise ImportError(install_errmsg)
+
+            _, tesserocr_languages = tesserocr.get_languages()
+            if not tesserocr_languages:
+                raise ImportError(missing_langs_errmsg)
 
             # Initialize the tesseractAPI
+            _log.debug("Initializing TesserOCR: %s", tesseract_version)
             lang = "+".join(self.options.lang)
             if self.options.path is not None:
                 self.reader = tesserocr.PyTessBaseAPI(

{docling-2.3.1 → docling-2.4.1}/pyproject.toml

@@ -1,13 +1,13 @@
 [tool.poetry]
 name = "docling"
-version = "2.3.1"  # 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 = "2.4.1"  # 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",
@@ -73,12 +73,6 @@ 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"