docling 2.8.0__py3-none-any.whl → 2.8.1__py3-none-any.whl

docling/cli/main.py

@@ -32,6 +32,7 @@ from docling.datamodel.pipeline_options import (
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
+from docling.datamodel.settings import settings
 from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
 
 warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch")
@@ -212,6 +213,24 @@ def convert(
             help="Set the verbosity level. -v for info logging, -vv for debug logging.",
         ),
     ] = 0,
+    debug_visualize_cells: Annotated[
+        bool,
+        typer.Option(..., help="Enable debug output which visualizes the PDF cells"),
+    ] = False,
+    debug_visualize_ocr: Annotated[
+        bool,
+        typer.Option(..., help="Enable debug output which visualizes the OCR cells"),
+    ] = False,
+    debug_visualize_layout: Annotated[
+        bool,
+        typer.Option(
+            ..., help="Enable debug output which visualizes the layour clusters"
+        ),
+    ] = False,
+    debug_visualize_tables: Annotated[
+        bool,
+        typer.Option(..., help="Enable debug output which visualizes the table cells"),
+    ] = False,
     version: Annotated[
         Optional[bool],
         typer.Option(
@@ -229,6 +248,11 @@ def convert(
     elif verbose == 2:
         logging.basicConfig(level=logging.DEBUG)
 
+    settings.debug.visualize_cells = debug_visualize_cells
+    settings.debug.visualize_layout = debug_visualize_layout
+    settings.debug.visualize_tables = debug_visualize_tables
+    settings.debug.visualize_ocr = debug_visualize_ocr
+
     if from_formats is None:
         from_formats = [e for e in InputFormat]
 

{docling-2.8.0.dist-info → docling-2.8.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.8.0
+Version: 2.8.1
 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
@@ -39,7 +39,6 @@ Requires-Dist: onnxruntime (>=1.7.0,<1.20.0) ; (python_version < "3.10") and (ex
 Requires-Dist: onnxruntime (>=1.7.0,<2.0.0) ; (python_version >= "3.10") and (extra == "rapidocr")
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
-Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
 Requires-Dist: pydantic (>=2.0.0,<2.10)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
 Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)
@@ -60,7 +59,7 @@ Description-Content-Type: text/markdown
   </a>
 </p>
 
-# Docling
+# 🦆 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>
@@ -85,7 +84,7 @@ Docling parses documents and exports them to the desired format with ease and sp
 * 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, 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
-* 🤖 Easy integration with LlamaIndex 🦙 & LangChain 🦜🔗 for powerful RAG / QA applications
+* 🤖 Easy integration with 🦙 LlamaIndex & 🦜🔗 LangChain for powerful RAG / QA applications
 * 🔍 OCR support for scanned PDFs
 * 💻 Simple and convenient CLI
 
@@ -121,8 +120,24 @@ 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.
+More [advanced usage options](https://ds4sd.github.io/docling/usage/) are available in
+the docs.
+
+## Documentation
+
+Check out Docling's [documentation](https://ds4sd.github.io/docling/), for details on
+installation, usage, concepts, recipes, extensions, and more.
+
+## Examples
+
+Go hands-on with our [examples](https://ds4sd.github.io/docling/examples/),
+demonstrating how to address different application use cases with Docling.
+
+## Integrations
+
+To further accelerate your AI application development, check out Docling's native
+[integrations](https://ds4sd.github.io/docling/integrations/) with popular frameworks
+and tools.
 
 ## Get help and support
 

{docling-2.8.0.dist-info → docling-2.8.1.dist-info}/RECORD

@@ -12,7 +12,7 @@ docling/backend/msword_backend.py,sha256=VFHPr-gCak7w3NJToc5Cs-JaTb4Vm3a1JnnRIfJ
 docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
 docling/backend/pypdfium2_backend.py,sha256=B4bfv-dfzlWiKTfF8LN5fto_99YBu8A2c1_XIVwRUWI,8996
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=KxukTq155IFVkfc_aUpSL6laGG1KjnXE4oAau7B5xBA,10881
+docling/cli/main.py,sha256=AgPD32NfM0_bmHeKjx5-fqk57ahX5tN3AeoDOerhTuE,11808
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=6qlwPamDZ3XUsE2kTAyGKG6O2IJClVjCqaE7DZ74KHU,5533
 docling/datamodel/document.py,sha256=9dQf_J18X_MEWs-Mg3Ed6BykFPJ79ETmkkxcssY-vYo,20698
@@ -41,8 +41,8 @@ docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
 docling/utils/layout_utils.py,sha256=vlN0rc8i0ayRGn3WnaG-pdmqEL00KKGl2zez3Gj-hrk,32074
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.8.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.8.0.dist-info/METADATA,sha256=4XSleijcmMxpwEFyjiNIh71ScIZUTApiKIfKDdM660A,7236
-docling-2.8.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.8.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.8.0.dist-info/RECORD,,
+docling-2.8.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.8.1.dist-info/METADATA,sha256=auj5PtDj-UBB72sW8jk1CSVSwQpd9q0nYzoAYIItl8o,7682
+docling-2.8.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.8.1.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.8.1.dist-info/RECORD,,