docling 2.69.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of docling might be problematic. Click here for more details.

Files changed (138) hide show
  1. docling/__init__.py +0 -0
  2. docling/backend/__init__.py +0 -0
  3. docling/backend/abstract_backend.py +84 -0
  4. docling/backend/asciidoc_backend.py +443 -0
  5. docling/backend/csv_backend.py +125 -0
  6. docling/backend/docling_parse_backend.py +237 -0
  7. docling/backend/docling_parse_v2_backend.py +276 -0
  8. docling/backend/docling_parse_v4_backend.py +260 -0
  9. docling/backend/docx/__init__.py +0 -0
  10. docling/backend/docx/drawingml/utils.py +131 -0
  11. docling/backend/docx/latex/__init__.py +0 -0
  12. docling/backend/docx/latex/latex_dict.py +274 -0
  13. docling/backend/docx/latex/omml.py +459 -0
  14. docling/backend/html_backend.py +1502 -0
  15. docling/backend/image_backend.py +188 -0
  16. docling/backend/json/__init__.py +0 -0
  17. docling/backend/json/docling_json_backend.py +58 -0
  18. docling/backend/md_backend.py +618 -0
  19. docling/backend/mets_gbs_backend.py +399 -0
  20. docling/backend/msexcel_backend.py +686 -0
  21. docling/backend/mspowerpoint_backend.py +398 -0
  22. docling/backend/msword_backend.py +1663 -0
  23. docling/backend/noop_backend.py +51 -0
  24. docling/backend/pdf_backend.py +82 -0
  25. docling/backend/pypdfium2_backend.py +417 -0
  26. docling/backend/webvtt_backend.py +572 -0
  27. docling/backend/xml/__init__.py +0 -0
  28. docling/backend/xml/jats_backend.py +819 -0
  29. docling/backend/xml/uspto_backend.py +1905 -0
  30. docling/chunking/__init__.py +12 -0
  31. docling/cli/__init__.py +0 -0
  32. docling/cli/main.py +974 -0
  33. docling/cli/models.py +196 -0
  34. docling/cli/tools.py +17 -0
  35. docling/datamodel/__init__.py +0 -0
  36. docling/datamodel/accelerator_options.py +69 -0
  37. docling/datamodel/asr_model_specs.py +494 -0
  38. docling/datamodel/backend_options.py +102 -0
  39. docling/datamodel/base_models.py +493 -0
  40. docling/datamodel/document.py +699 -0
  41. docling/datamodel/extraction.py +39 -0
  42. docling/datamodel/layout_model_specs.py +91 -0
  43. docling/datamodel/pipeline_options.py +457 -0
  44. docling/datamodel/pipeline_options_asr_model.py +78 -0
  45. docling/datamodel/pipeline_options_vlm_model.py +136 -0
  46. docling/datamodel/settings.py +65 -0
  47. docling/datamodel/vlm_model_specs.py +365 -0
  48. docling/document_converter.py +559 -0
  49. docling/document_extractor.py +327 -0
  50. docling/exceptions.py +10 -0
  51. docling/experimental/__init__.py +5 -0
  52. docling/experimental/datamodel/__init__.py +1 -0
  53. docling/experimental/datamodel/table_crops_layout_options.py +13 -0
  54. docling/experimental/datamodel/threaded_layout_vlm_pipeline_options.py +45 -0
  55. docling/experimental/models/__init__.py +3 -0
  56. docling/experimental/models/table_crops_layout_model.py +114 -0
  57. docling/experimental/pipeline/__init__.py +1 -0
  58. docling/experimental/pipeline/threaded_layout_vlm_pipeline.py +439 -0
  59. docling/models/__init__.py +0 -0
  60. docling/models/base_layout_model.py +39 -0
  61. docling/models/base_model.py +230 -0
  62. docling/models/base_ocr_model.py +241 -0
  63. docling/models/base_table_model.py +45 -0
  64. docling/models/extraction/__init__.py +0 -0
  65. docling/models/extraction/nuextract_transformers_model.py +305 -0
  66. docling/models/factories/__init__.py +47 -0
  67. docling/models/factories/base_factory.py +122 -0
  68. docling/models/factories/layout_factory.py +7 -0
  69. docling/models/factories/ocr_factory.py +11 -0
  70. docling/models/factories/picture_description_factory.py +11 -0
  71. docling/models/factories/table_factory.py +7 -0
  72. docling/models/picture_description_base_model.py +149 -0
  73. docling/models/plugins/__init__.py +0 -0
  74. docling/models/plugins/defaults.py +60 -0
  75. docling/models/stages/__init__.py +0 -0
  76. docling/models/stages/code_formula/__init__.py +0 -0
  77. docling/models/stages/code_formula/code_formula_model.py +342 -0
  78. docling/models/stages/layout/__init__.py +0 -0
  79. docling/models/stages/layout/layout_model.py +249 -0
  80. docling/models/stages/ocr/__init__.py +0 -0
  81. docling/models/stages/ocr/auto_ocr_model.py +132 -0
  82. docling/models/stages/ocr/easyocr_model.py +200 -0
  83. docling/models/stages/ocr/ocr_mac_model.py +145 -0
  84. docling/models/stages/ocr/rapid_ocr_model.py +328 -0
  85. docling/models/stages/ocr/tesseract_ocr_cli_model.py +331 -0
  86. docling/models/stages/ocr/tesseract_ocr_model.py +262 -0
  87. docling/models/stages/page_assemble/__init__.py +0 -0
  88. docling/models/stages/page_assemble/page_assemble_model.py +156 -0
  89. docling/models/stages/page_preprocessing/__init__.py +0 -0
  90. docling/models/stages/page_preprocessing/page_preprocessing_model.py +145 -0
  91. docling/models/stages/picture_classifier/__init__.py +0 -0
  92. docling/models/stages/picture_classifier/document_picture_classifier.py +246 -0
  93. docling/models/stages/picture_description/__init__.py +0 -0
  94. docling/models/stages/picture_description/picture_description_api_model.py +66 -0
  95. docling/models/stages/picture_description/picture_description_vlm_model.py +123 -0
  96. docling/models/stages/reading_order/__init__.py +0 -0
  97. docling/models/stages/reading_order/readingorder_model.py +431 -0
  98. docling/models/stages/table_structure/__init__.py +0 -0
  99. docling/models/stages/table_structure/table_structure_model.py +305 -0
  100. docling/models/utils/__init__.py +0 -0
  101. docling/models/utils/generation_utils.py +157 -0
  102. docling/models/utils/hf_model_download.py +45 -0
  103. docling/models/vlm_pipeline_models/__init__.py +1 -0
  104. docling/models/vlm_pipeline_models/api_vlm_model.py +180 -0
  105. docling/models/vlm_pipeline_models/hf_transformers_model.py +391 -0
  106. docling/models/vlm_pipeline_models/mlx_model.py +325 -0
  107. docling/models/vlm_pipeline_models/vllm_model.py +344 -0
  108. docling/pipeline/__init__.py +0 -0
  109. docling/pipeline/asr_pipeline.py +431 -0
  110. docling/pipeline/base_extraction_pipeline.py +72 -0
  111. docling/pipeline/base_pipeline.py +326 -0
  112. docling/pipeline/extraction_vlm_pipeline.py +207 -0
  113. docling/pipeline/legacy_standard_pdf_pipeline.py +262 -0
  114. docling/pipeline/simple_pipeline.py +55 -0
  115. docling/pipeline/standard_pdf_pipeline.py +859 -0
  116. docling/pipeline/threaded_standard_pdf_pipeline.py +5 -0
  117. docling/pipeline/vlm_pipeline.py +416 -0
  118. docling/py.typed +1 -0
  119. docling/utils/__init__.py +0 -0
  120. docling/utils/accelerator_utils.py +97 -0
  121. docling/utils/api_image_request.py +205 -0
  122. docling/utils/deepseekocr_utils.py +388 -0
  123. docling/utils/export.py +146 -0
  124. docling/utils/glm_utils.py +361 -0
  125. docling/utils/layout_postprocessor.py +683 -0
  126. docling/utils/locks.py +3 -0
  127. docling/utils/model_downloader.py +168 -0
  128. docling/utils/ocr_utils.py +69 -0
  129. docling/utils/orientation.py +65 -0
  130. docling/utils/profiling.py +65 -0
  131. docling/utils/utils.py +65 -0
  132. docling/utils/visualization.py +85 -0
  133. docling-2.69.0.dist-info/METADATA +237 -0
  134. docling-2.69.0.dist-info/RECORD +138 -0
  135. docling-2.69.0.dist-info/WHEEL +5 -0
  136. docling-2.69.0.dist-info/entry_points.txt +6 -0
  137. docling-2.69.0.dist-info/licenses/LICENSE +21 -0
  138. docling-2.69.0.dist-info/top_level.txt +1 -0
@@ -0,0 +1,12 @@
1
+ #
2
+ # Copyright IBM Corp. 2024 - 2024
3
+ # SPDX-License-Identifier: MIT
4
+ #
5
+
6
+ from docling_core.transforms.chunker.base import BaseChunk, BaseChunker, BaseMeta
7
+ from docling_core.transforms.chunker.hierarchical_chunker import (
8
+ DocChunk,
9
+ DocMeta,
10
+ HierarchicalChunker,
11
+ )
12
+ from docling_core.transforms.chunker.hybrid_chunker import HybridChunker
File without changes