docling 2.35.0__py3-none-any.whl → 2.36.0__py3-none-any.whl

{docling-2.35.0.dist-info → docling-2.36.0.dist-info}/METADATA

@@ -1,67 +1,68 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: docling
-Version: 2.35.0
+Version: 2.36.0
 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/docling-project/docling
-License: MIT
+Author-email: 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-Expression: MIT
+Project-URL: homepage, https://github.com/docling-project/docling
+Project-URL: repository, https://github.com/docling-project/docling
+Project-URL: issues, https://github.com/docling-project/docling/issues
+Project-URL: changelog, https://github.com/docling-project/docling/blob/main/CHANGELOG.md
 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: >=3.9,<4.0
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: Microsoft :: Windows
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: MacOS :: MacOS X
-Classifier: Operating System :: POSIX :: Linux
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Provides-Extra: ocrmac
-Provides-Extra: rapidocr
+Requires-Python: <4.0,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic<3.0.0,>=2.0.0
+Requires-Dist: docling-core[chunking]<3.0.0,>=2.29.0
+Requires-Dist: docling-ibm-models<4.0.0,>=3.4.4
+Requires-Dist: docling-parse<5.0.0,>=4.0.0
+Requires-Dist: filetype<2.0.0,>=1.2.0
+Requires-Dist: pypdfium2<5.0.0,>=4.30.0
+Requires-Dist: pydantic-settings<3.0.0,>=2.3.0
+Requires-Dist: huggingface_hub<1,>=0.23
+Requires-Dist: requests<3.0.0,>=2.32.2
+Requires-Dist: easyocr<2.0,>=1.7
+Requires-Dist: certifi>=2024.7.4
+Requires-Dist: rtree<2.0.0,>=1.3.0
+Requires-Dist: typer<0.16.0,>=0.12.5
+Requires-Dist: python-docx<2.0.0,>=1.1.2
+Requires-Dist: python-pptx<2.0.0,>=1.0.2
+Requires-Dist: beautifulsoup4<5.0.0,>=4.12.3
+Requires-Dist: pandas<3.0.0,>=2.1.4
+Requires-Dist: marko<3.0.0,>=2.1.2
+Requires-Dist: openpyxl<4.0.0,>=3.1.5
+Requires-Dist: lxml<6.0.0,>=4.0.0
+Requires-Dist: pillow<12.0.0,>=10.0.0
+Requires-Dist: tqdm<5.0.0,>=4.65.0
+Requires-Dist: pluggy<2.0.0,>=1.0.0
+Requires-Dist: pylatexenc<3.0,>=2.10
+Requires-Dist: click<8.2.0
+Requires-Dist: scipy<2.0.0,>=1.6.0
 Provides-Extra: tesserocr
+Requires-Dist: tesserocr<3.0.0,>=2.7.1; extra == "tesserocr"
+Provides-Extra: ocrmac
+Requires-Dist: ocrmac<2.0.0,>=1.0.0; sys_platform == "darwin" and extra == "ocrmac"
 Provides-Extra: vlm
-Requires-Dist: accelerate (>=1.2.1,<2.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
-Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
-Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: click (<8.2.0)
-Requires-Dist: docling-core[chunking] (>=2.31.2,<3.0.0)
-Requires-Dist: docling-ibm-models (>=3.4.0,<4.0.0)
-Requires-Dist: docling-parse (>=4.0.0,<5.0.0)
-Requires-Dist: easyocr (>=1.7,<2.0)
-Requires-Dist: filetype (>=1.2.0,<2.0.0)
-Requires-Dist: huggingface_hub (>=0.23,<1)
-Requires-Dist: lxml (>=4.0.0,<6.0.0)
-Requires-Dist: marko (>=2.1.2,<3.0.0)
-Requires-Dist: ocrmac (>=1.0.0,<2.0.0) ; (sys_platform == "darwin") and (extra == "ocrmac")
-Requires-Dist: onnxruntime (>=1.7.0,<1.20.0) ; (python_version < "3.10") and (extra == "rapidocr")
-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: pillow (>=10.0.0,<12.0.0)
-Requires-Dist: pluggy (>=1.0.0,<2.0.0)
-Requires-Dist: pydantic (>=2.0.0,<3.0.0)
-Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
-Requires-Dist: pylatexenc (>=2.10,<3.0)
-Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)
-Requires-Dist: python-docx (>=1.1.2,<2.0.0)
-Requires-Dist: python-pptx (>=1.0.2,<2.0.0)
-Requires-Dist: rapidocr-onnxruntime (>=1.4.0,<2.0.0) ; (python_version < "3.13") and (extra == "rapidocr")
-Requires-Dist: requests (>=2.32.2,<3.0.0)
-Requires-Dist: rtree (>=1.3.0,<2.0.0)
-Requires-Dist: scipy (>=1.6.0,<1.14.0) ; python_version < "3.10"
-Requires-Dist: scipy (>=1.6.0,<2.0.0) ; python_version >= "3.10"
-Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
-Requires-Dist: tqdm (>=4.65.0,<5.0.0)
-Requires-Dist: transformers (>=4.42.0,<4.43.0) ; (sys_platform == "darwin" and platform_machine == "x86_64") and (extra == "vlm")
-Requires-Dist: transformers (>=4.46.0,<5.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
-Requires-Dist: typer (>=0.12.5,<0.16.0)
-Project-URL: Repository, https://github.com/docling-project/docling
-Description-Content-Type: text/markdown
+Requires-Dist: transformers<5.0.0,>=4.46.0; extra == "vlm"
+Requires-Dist: accelerate<2.0.0,>=1.2.1; extra == "vlm"
+Requires-Dist: mlx-vlm>=0.1.22; (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "vlm"
+Provides-Extra: rapidocr
+Requires-Dist: rapidocr-onnxruntime<2.0.0,>=1.4.0; python_version < "3.13" and extra == "rapidocr"
+Requires-Dist: onnxruntime<2.0.0,>=1.7.0; extra == "rapidocr"
+Dynamic: license-file
 
 <p align="center">
   <a href="https://github.com/docling-project/docling">
@@ -79,9 +80,8 @@ Description-Content-Type: text/markdown
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://docling-project.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
-[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
@@ -101,7 +101,7 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔒 Local execution capabilities for sensitive data and air-gapped environments
 * 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
 * 🔍 Extensive OCR support for scanned PDFs and images
-* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) 🆕
+* 🥚 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
 * 💻 Simple and convenient CLI
 
 ### Coming soon
@@ -214,4 +214,3 @@ The project was started by the AI for knowledge team at IBM Research Zurich.
 [supported_formats]: https://docling-project.github.io/docling/usage/supported_formats/
 [docling_document]: https://docling-project.github.io/docling/concepts/docling_document/
 [integrations]: https://docling-project.github.io/docling/integrations/
-

{docling-2.35.0.dist-info → docling-2.36.0.dist-info}/RECORD

@@ -1,4 +1,7 @@
 docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/document_converter.py,sha256=bnUA9k1LCuCfNwCsneGQiGCvFdnX8W-vbpnu6U_fuuI,14003
+docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
+docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/abstract_backend.py,sha256=1lNxzwDTn303aXduPDVmTyXn-5ZIoWMLYqNxANGWmQQ,1658
 docling/backend/asciidoc_backend.py,sha256=W-4MRcID6AU9Ax23q8FwDwGG-OOCrBoqcNf2Ch_WPUc,14041
@@ -6,82 +9,86 @@ docling/backend/csv_backend.py,sha256=2g9famYG2W-ID9jEdZPxc6O8QGv1vWQfjN8pL-QMBE
 docling/backend/docling_parse_backend.py,sha256=bVSPmmiVXdCVfe-eLtDhbPQKBjkFR8rZJoRxdWIMdYU,7998
 docling/backend/docling_parse_v2_backend.py,sha256=R4YPCEs72GYg-Xc9VfizPv8QjtGmKOsQzVPNAU2RIK0,9376
 docling/backend/docling_parse_v4_backend.py,sha256=aWh-fd-lnuRGVGC_DG17QUptIsArv5V1gJo8QFbB5Ys,6263
-docling/backend/docx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/docx/latex/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/docx/latex/latex_dict.py,sha256=tFJp4ScT_AkY2ON7nLEa560p601Jq2glcZvMKxxjn7w,6593
-docling/backend/docx/latex/omml.py,sha256=nEpcfyyrOucJyj6cD7wfThrIa-q0CQCoqMb3dkrhCRg,12094
 docling/backend/html_backend.py,sha256=3K-l5SUAAyqISNEb7nPst_I51xzYOVOkgmwXh3lv9sw,21063
-docling/backend/json/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/json/docling_json_backend.py,sha256=LlFMVoZrrCfVwbDuRbNN4Xg96Lujh4xxrTBt9jGhY9I,1984
 docling/backend/md_backend.py,sha256=JkY1qTvQFXjKSZGfD-83d-fZelorUG_l6mpJdYGqvX8,17210
 docling/backend/msexcel_backend.py,sha256=3j0WQfqDpgPXdPMCguefdv7arcNVDedPD6gl54cmLn8,18110
 docling/backend/mspowerpoint_backend.py,sha256=RwqfvvzrtM56L9uf7PR9lvlHJ-LyYGpkS1iVxkTl72Q,17203
 docling/backend/msword_backend.py,sha256=iB2yRg8hXtET2-Wjkv5pq0p9Y1SGQYIVCcWtOtXUILU,44621
 docling/backend/pdf_backend.py,sha256=KE9TMuFO5WX-o5A_DAd4tEaLi4HMZ4XjKdpllItVkWM,2238
 docling/backend/pypdfium2_backend.py,sha256=fUGRBupwTYftEgdIDWKphA2zdfb-SrUoUGENK6j-q-0,11002
+docling/backend/docx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/docx/latex/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/docx/latex/latex_dict.py,sha256=tFJp4ScT_AkY2ON7nLEa560p601Jq2glcZvMKxxjn7w,6593
+docling/backend/docx/latex/omml.py,sha256=nEpcfyyrOucJyj6cD7wfThrIa-q0CQCoqMb3dkrhCRg,12094
+docling/backend/json/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/json/docling_json_backend.py,sha256=LlFMVoZrrCfVwbDuRbNN4Xg96Lujh4xxrTBt9jGhY9I,1984
 docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/xml/jats_backend.py,sha256=ghGi9bHjx3BvaOtmzLw86-wZy4UxpQPOPQL4e73-BI8,24927
 docling/backend/xml/uspto_backend.py,sha256=nyAMr5ht7dclxkVDwsKNeiOhLQrUtRLS8JdscB2AVJg,70924
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=KARZ1OJx4HvHb1D_95GPIAhKaIlhcYYSBa0t4PM-Xfk,27339
+docling/cli/main.py,sha256=fDGjepShl6KO_BdA6qUNyNBoCjqZUKRnmmkzesGtvVU,27202
 docling/cli/models.py,sha256=9yLGp6QRJGpR86U3SjmWAXDt3MvBaJLLY4xDVdsu3O8,4160
 docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=QJlzGJKUAO0kqM6DO2RZKlFi-lL2MpY8qt3Wdm02Slw,10460
+docling/datamodel/accelerator_options.py,sha256=wv6dOFTVAwr9onkE-0pfUqX_fDb6gX53iPPE6o8nKjI,2511
+docling/datamodel/base_models.py,sha256=bkooSG4brZy2jt2dndkin3DHvfZ5HFp0C94yBGmCWeI,10568
 docling/datamodel/document.py,sha256=vPwiVU5zWCKbVYMq-TSmb7LTjijrqJq0FyAgDBa0XGA,16154
-docling/datamodel/pipeline_options.py,sha256=uwjBvK4egrgcF1_w4B5EDxpGnl4IgBzmxP7dJ7zm394,13400
+docling/datamodel/pipeline_options.py,sha256=iMuwsa77hkAgjJWXBRAFEQGw9tGNMDQrPnSvE5mirNs,9081
+docling/datamodel/pipeline_options_vlm_model.py,sha256=-ZPAp2uSKMatDbjZPv9chT587B1aftfDVmi_FDb2aw8,1997
 docling/datamodel/settings.py,sha256=ajMz7Ao2m0ZGYkfArqTDDbiF89O408mtgeh06PUi0MA,1900
-docling/document_converter.py,sha256=PRRr65nigQ3LZDl4G2fBMkOtJyswT7xyGt7fpUeDO3w,13849
-docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
+docling/datamodel/vlm_model_specs.py,sha256=--jZexGeu-s_lWp7y_WwWEf6CD1J4XqADrS1-OY_pWM,4737
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/models/api_vlm_model.py,sha256=TuLUR-EeUcoUkQKz5Tv6rvphhJKyQShpb99d7bVTdJE,2728
+docling/models/api_vlm_model.py,sha256=w3P1wOsr3JvZsawbK1Z4uwnD5ehUMbcKGkyhcX83Okc,2738
 docling/models/base_model.py,sha256=Zx_nByGYkubTvvYiQxwiB6P8lc7wOD4ZTC2QIw6vCEg,2950
-docling/models/base_ocr_model.py,sha256=_iD8QCKQdv2VWrIuSRPyGP4oCz94h84WriHg9F2k-Z0,7172
-docling/models/code_formula_model.py,sha256=9cplJFvP7jcJGz-p-MmL8_lqUhmaXZu7wKyX2aOTujs,11504
-docling/models/document_picture_classifier.py,sha256=tyOnyM0vh8-pjh9PiHa_67YpK-3pc_vGQKlnfAyraBs,6255
-docling/models/easyocr_model.py,sha256=3rgXMeB7LbMjevCAVDMG3voe3PQhQ7B-RyYrXzefUlQ,7365
+docling/models/base_ocr_model.py,sha256=c6a2QzZnAMfQECQDz1JASecl_Z2F3i6P3ax6kHWcz6o,7221
+docling/models/code_formula_model.py,sha256=5uWh-eI-Ejmv3DujKJoKKgJBuvPLokt7AJ_ybt8VHEw,11373
+docling/models/document_picture_classifier.py,sha256=fkJLV7pMy3v6iNwOzVb6zdBU1dGtBM1ARHLIRPfoAG4,6124
+docling/models/easyocr_model.py,sha256=bTK-AQYc-WTzX8SRoMRwVjqlMigaJKGloaLUcH6RCKU,7406
+docling/models/layout_model.py,sha256=KdGhS4EMWKP6BwlhUJ0mdbhk2Fc78qwzqEZbTxyrbFM,8508
+docling/models/ocr_mac_model.py,sha256=CJOwz9h84crvZd3kQMLxYntpXz-1w2eLDjhGUnGIwMQ,5415
+docling/models/page_assemble_model.py,sha256=TvN1naez7dUodLxpUUBzpuMCpqZBTf6YSpewxgjzmrg,6323
+docling/models/page_preprocessing_model.py,sha256=8cdhR9n3zcC8JxDen8WdPBx_GNk_5VICeHJo1-kP518,5186
+docling/models/picture_description_api_model.py,sha256=o3EkV5aHW_6WzE_fdj_VRnNCrS_btclO_ZCLAUqrfl0,2377
+docling/models/picture_description_base_model.py,sha256=kLthLhdlgwhootQ4_xhhcAk6A-vso5-qcsFJ3TcYfO0,2991
+docling/models/picture_description_vlm_model.py,sha256=7LeCx9ZdPxsmWJ468OtxCdAkH48A1HD0iwH9cs_7-1Q,3800
+docling/models/rapid_ocr_model.py,sha256=miTPn1YTWKtXUuddiVv0SjgkuNWHXCW3CZ6epDUmKjI,5935
+docling/models/readingorder_model.py,sha256=S9ru2ApY9sE-Uue3hptWHmbmElwo36bUbAikxCFpHYs,14574
+docling/models/table_structure_model.py,sha256=dQf6u_zn5fHCkHzmTwYfCbRtZCBddsyAM0WNVBUUQzk,12473
+docling/models/tesseract_ocr_cli_model.py,sha256=oQZVWXQ6wRrFonRFwbWeW9nJ9FLQZdzSWErOp0mEff0,12698
+docling/models/tesseract_ocr_model.py,sha256=AjrZNwgVbV0IbzBJwI35YP0KxvqWJWJE0v_lgHJiQrk,10606
 docling/models/factories/__init__.py,sha256=x_EM5dDg_A3HBcBYzOoqwmA2AFLtJ1IzYDPX-R1A-Sg,868
 docling/models/factories/base_factory.py,sha256=MfWIljMETi5aaVR-6qLTelW8u1gwDAQsOwg3fu7O4Qc,4028
 docling/models/factories/ocr_factory.py,sha256=G5RkmkKvkl-ihpo6qSj8WC77VdlVSQ1s0ekwUX2ILts,316
 docling/models/factories/picture_description_factory.py,sha256=Ru3-TnVVEKf5O07C_UpGf2HCOHc7j20AJzfficw3agM,385
-docling/models/hf_mlx_model.py,sha256=B_B4hFU-jU0g_DQtQD8w4Ejorn10mkDuFI93wR_WhGk,4897
-docling/models/hf_vlm_model.py,sha256=SiPMTLghMUjJ66dA2yN4UujpLO6PiOhLEPInWtXV_5s,6912
-docling/models/layout_model.py,sha256=1LLDS3hBfdJXA16L_PrjA_1rM_A2r5rNFkHVbLBCl_8,8639
-docling/models/ocr_mac_model.py,sha256=A3TlEbvvwhkWiq9YARos3Y9yNcpPYQ7JGc_4hFtAK-8,5370
-docling/models/page_assemble_model.py,sha256=TvN1naez7dUodLxpUUBzpuMCpqZBTf6YSpewxgjzmrg,6323
-docling/models/page_preprocessing_model.py,sha256=8cdhR9n3zcC8JxDen8WdPBx_GNk_5VICeHJo1-kP518,5186
-docling/models/picture_description_api_model.py,sha256=kCuAFOGEuI5QsRul7Pc1LccxWN7WIvIUhXEmSICYegw,2332
-docling/models/picture_description_base_model.py,sha256=FbBVXzAOB87xpJN28tuGCxoAdcf6mZNUOqJR7ljUg5g,2946
-docling/models/picture_description_vlm_model.py,sha256=DiTjnehVy1n0N04xPUvZl8rx4TiNHzHn9Cnzy_ePGts,4177
 docling/models/plugins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/plugins/defaults.py,sha256=qslXGnRX07Z3GGttNriqaox0v0vXp4zs4KLurHCZjp4,858
-docling/models/rapid_ocr_model.py,sha256=Tq_1Egu5Hjx7Y69Vox17QTtRXztSyflB1fhN08CWQwY,5894
-docling/models/readingorder_model.py,sha256=S9ru2ApY9sE-Uue3hptWHmbmElwo36bUbAikxCFpHYs,14574
-docling/models/table_structure_model.py,sha256=1gxLaooK0IKMrnmS8nT1BItKqt1GAKghfpmLKb3i53g,12566
-docling/models/tesseract_ocr_cli_model.py,sha256=e55MkaDdsseKcfX5lxIt0iv5jR6pDFBzWBZHTvl2Jws,12653
-docling/models/tesseract_ocr_model.py,sha256=vS4And5NHe_uLNb6ZBi2CQzWUITBdc1E1zlsojrSZpM,10561
+docling/models/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/models/utils/hf_model_download.py,sha256=scBEfsM4yl7xPzqe7UtPvDh9RfQZQnuOhqQKilYBHls,984
+docling/models/vlm_models_inline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/models/vlm_models_inline/hf_transformers_model.py,sha256=SXSu6spu8zNCsrD32RU_irLs59ltF6PqbLVfpjDujmE,7285
+docling/models/vlm_models_inline/mlx_model.py,sha256=CFe1UNxQufZd5K4iaOW3HsplQBPb_1cENf3KIwWUSWw,5702
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_pipeline.py,sha256=DnuxAf7EQusdSRae0QUVth-0f2mSff8JZjX-2vazk00,8751
 docling/pipeline/simple_pipeline.py,sha256=TXZOwR7hZRji462ZTIpte0VJjzbxvNVE8dbLFANDhSU,2253
 docling/pipeline/standard_pdf_pipeline.py,sha256=itCZPj7nMFAQtAlStfmWthpCIHZFUm9W5uTgvVi6PkQ,12738
-docling/pipeline/vlm_pipeline.py,sha256=ZW1WGd6jeLqTCWR0S0cj6H_qVMUXELaFCrJVpvZp6Co,9684
-docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+docling/pipeline/vlm_pipeline.py,sha256=IrjDbajCPmUPep_jATKNiABST4tQ8mvpkQz9mtBQ8qQ,15279
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/utils/accelerator_utils.py,sha256=ONNRrC8fH-8E93WUCNhfOq1t7WrQ1T7-YsmExTOY5f0,2292
+docling/utils/accelerator_utils.py,sha256=Fww4UiTiuIB91iuPgUZTy-DYpCGRMI8YuCYKhFb0gjA,2905
 docling/utils/api_image_request.py,sha256=_CgdzmPqdsyXmyYUFGLZcXcoH586qC6A1p5vsNbj1Q0,1416
 docling/utils/export.py,sha256=VwVUnYDk3mhGmISDbVm306fwpGNnoojouStBD4UajXI,4673
 docling/utils/glm_utils.py,sha256=TKOWQqWAHsX_w4fvoAA7_2xCi_urhnp1DsmjY8_sk5w,12274
 docling/utils/layout_postprocessor.py,sha256=3WCmkPsPJ80xfWzAUeWb5L9BmuwJ79ztctvbbUs8AfI,24068
 docling/utils/locks.py,sha256=RzqQtD5UispgV71pGN_nU6GYfeN11BN0Sh_Dq9ycqGo,52
-docling/utils/model_downloader.py,sha256=ocvud3G3qlBQhzMo69Q3RJMnvq5HPZ2DwNbMuEp8RCs,4142
+docling/utils/model_downloader.py,sha256=6TDxFOvMRYT8JyYyaQS_wXMJzNga61ImY3sFdks66qM,4004
 docling/utils/ocr_utils.py,sha256=AOaDAHr5S74d-IRVR_LKhKynUTIurAwLJ3wNeY58gPA,2326
 docling/utils/orientation.py,sha256=xXlOfowL54FKwjsTFrM7y3ogk1wChLNn_-u74tYIf1s,2011
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.35.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.35.0.dist-info/METADATA,sha256=SMuVHjV5ouB773e4tFnu7fqpvEdygq3ksNbESerk0Ao,10138
-docling-2.35.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.35.0.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
-docling-2.35.0.dist-info/RECORD,,
+docling-2.36.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.36.0.dist-info/METADATA,sha256=QvDUpjcs-p-AzrU8qJWl2xCadZtCXcBJj5S7uKh0QsY,10063
+docling-2.36.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+docling-2.36.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
+docling-2.36.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
+docling-2.36.0.dist-info/RECORD,,

{docling-2.35.0.dist-info → docling-2.36.0.dist-info}/WHEEL

@@ -1,4 +1,5 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
+

docling-2.36.0.dist-info/entry_points.txt

@@ -0,0 +1,6 @@
+[console_scripts]
+docling = docling.cli.main:app
+docling-tools = docling.cli.tools:app
+
+[docling]
+docling_defaults = docling.models.plugins.defaults

docling-2.36.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+docling

docling/models/hf_vlm_model.py

@@ -1,182 +0,0 @@
-import logging
-import time
-from collections.abc import Iterable
-from pathlib import Path
-from typing import Optional
-
-from docling.datamodel.base_models import Page, VlmPrediction
-from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
-    AcceleratorOptions,
-    HuggingFaceVlmOptions,
-)
-from docling.models.base_model import BasePageModel
-from docling.utils.accelerator_utils import decide_device
-from docling.utils.profiling import TimeRecorder
-
-_log = logging.getLogger(__name__)
-
-
-class HuggingFaceVlmModel(BasePageModel):
-    def __init__(
-        self,
-        enabled: bool,
-        artifacts_path: Optional[Path],
-        accelerator_options: AcceleratorOptions,
-        vlm_options: HuggingFaceVlmOptions,
-    ):
-        self.enabled = enabled
-
-        self.vlm_options = vlm_options
-
-        if self.enabled:
-            import torch
-            from transformers import (  # type: ignore
-                AutoModelForVision2Seq,
-                AutoProcessor,
-                BitsAndBytesConfig,
-            )
-
-            device = decide_device(accelerator_options.device)
-            self.device = device
-
-            _log.debug(f"Available device for HuggingFace VLM: {device}")
-
-            repo_cache_folder = vlm_options.repo_id.replace("/", "--")
-
-            # PARAMETERS:
-            if artifacts_path is None:
-                artifacts_path = self.download_models(self.vlm_options.repo_id)
-            elif (artifacts_path / repo_cache_folder).exists():
-                artifacts_path = artifacts_path / repo_cache_folder
-
-            self.param_question = vlm_options.prompt  # "Perform Layout Analysis."
-            self.param_quantization_config = BitsAndBytesConfig(
-                load_in_8bit=vlm_options.load_in_8bit,  # True,
-                llm_int8_threshold=vlm_options.llm_int8_threshold,  # 6.0
-            )
-            self.param_quantized = vlm_options.quantized  # False
-
-            self.processor = AutoProcessor.from_pretrained(artifacts_path)
-            if not self.param_quantized:
-                self.vlm_model = AutoModelForVision2Seq.from_pretrained(
-                    artifacts_path,
-                    device_map=device,
-                    torch_dtype=torch.bfloat16,
-                    _attn_implementation=(
-                        "flash_attention_2"
-                        if self.device.startswith("cuda")
-                        and accelerator_options.cuda_use_flash_attention2
-                        else "eager"
-                    ),
-                )  # .to(self.device)
-
-            else:
-                self.vlm_model = AutoModelForVision2Seq.from_pretrained(
-                    artifacts_path,
-                    device_map=device,
-                    torch_dtype="auto",
-                    quantization_config=self.param_quantization_config,
-                    _attn_implementation=(
-                        "flash_attention_2"
-                        if self.device.startswith("cuda")
-                        and accelerator_options.cuda_use_flash_attention2
-                        else "eager"
-                    ),
-                )  # .to(self.device)
-
-    @staticmethod
-    def download_models(
-        repo_id: str,
-        local_dir: Optional[Path] = None,
-        force: bool = False,
-        progress: bool = False,
-    ) -> Path:
-        from huggingface_hub import snapshot_download
-        from huggingface_hub.utils import disable_progress_bars
-
-        if not progress:
-            disable_progress_bars()
-        download_path = snapshot_download(
-            repo_id=repo_id,
-            force_download=force,
-            local_dir=local_dir,
-            # revision="v0.0.1",
-        )
-
-        return Path(download_path)
-
-    def __call__(
-        self, conv_res: ConversionResult, page_batch: Iterable[Page]
-    ) -> Iterable[Page]:
-        for page in page_batch:
-            assert page._backend is not None
-            if not page._backend.is_valid():
-                yield page
-            else:
-                with TimeRecorder(conv_res, "vlm"):
-                    assert page.size is not None
-
-                    hi_res_image = page.get_image(scale=2.0)  # 144dpi
-                    # hi_res_image = page.get_image(scale=1.0)  # 72dpi
-
-                    if hi_res_image is not None:
-                        im_width, im_height = hi_res_image.size
-
-                    # populate page_tags with predicted doc tags
-                    page_tags = ""
-
-                    if hi_res_image:
-                        if hi_res_image.mode != "RGB":
-                            hi_res_image = hi_res_image.convert("RGB")
-
-                    messages = [
-                        {
-                            "role": "user",
-                            "content": [
-                                {
-                                    "type": "text",
-                                    "text": "This is a page from a document.",
-                                },
-                                {"type": "image"},
-                                {"type": "text", "text": self.param_question},
-                            ],
-                        }
-                    ]
-                    prompt = self.processor.apply_chat_template(
-                        messages, add_generation_prompt=False
-                    )
-                    inputs = self.processor(
-                        text=prompt, images=[hi_res_image], return_tensors="pt"
-                    )
-                    inputs = {k: v.to(self.device) for k, v in inputs.items()}
-
-                    start_time = time.time()
-                    # Call model to generate:
-                    generated_ids = self.vlm_model.generate(
-                        **inputs, max_new_tokens=4096, use_cache=True
-                    )
-
-                    generation_time = time.time() - start_time
-                    generated_texts = self.processor.batch_decode(
-                        generated_ids[:, inputs["input_ids"].shape[1] :],
-                        skip_special_tokens=False,
-                    )[0]
-
-                    num_tokens = len(generated_ids[0])
-                    page_tags = generated_texts
-
-                    _log.debug(
-                        f"Generated {num_tokens} tokens in time {generation_time:.2f} seconds."
-                    )
-
-                    # inference_time = time.time() - start_time
-                    # tokens_per_second = num_tokens / generation_time
-                    # print("")
-                    # print(f"Page Inference Time: {inference_time:.2f} seconds")
-                    # print(f"Total tokens on page: {num_tokens:.2f}")
-                    # print(f"Tokens/sec: {tokens_per_second:.2f}")
-                    # print("")
-                    page.predictions.vlm_response = VlmPrediction(text=page_tags)
-
-                yield page

docling-2.35.0.dist-info/entry_points.txt

@@ -1,7 +0,0 @@
-[console_scripts]
-docling=docling.cli.main:app
-docling-tools=docling.cli.tools:app
-
-[docling]
-docling_defaults=docling.models.plugins.defaults
-