docling 2.4.0__tar.gz → 2.4.2__tar.gz

{docling-2.4.0 → docling-2.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.4.0
+Version: 2.4.2
 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
@@ -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-2.4.0 → docling-2.4.2}/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-2.4.0 → docling-2.4.2}/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-2.4.0 → docling-2.4.2}/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-2.4.0 → docling-2.4.2}/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-2.4.0 → docling-2.4.2}/docling/models/easyocr_model.py

@@ -2,6 +2,7 @@ import logging
 from typing import Iterable
 
 import numpy
+import torch
 from docling_core.types.doc import BoundingBox, CoordOrigin
 
 from docling.datamodel.base_models import OcrCell, Page
@@ -30,8 +31,12 @@ class EasyOcrModel(BaseOcrModel):
                     "Alternatively, Docling has support for other OCR engines. See the documentation."
                 )
 
+            use_gpu = (
+                False if torch.backends.mps.is_available() else self.options.use_gpu
+            )
             self.reader = easyocr.Reader(
                 lang_list=self.options.lang,
+                gpu=use_gpu,
                 model_storage_directory=self.options.model_storage_directory,
                 download_enabled=self.options.download_enabled,
             )

{docling-2.4.0 → docling-2.4.2}/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-2.4.0 → docling-2.4.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.4.0"  # DO NOT EDIT, updated automatically
+version = "2.4.2"  # 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"