natural-pdf 0.1.10__tar.gz → 0.1.11__tar.gz

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.
Files changed (207) hide show
  1. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.gitignore +1 -0
  2. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/01-execute_notebooks.py +2 -1
  3. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/PKG-INFO +1 -2
  4. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/document-qa/index.ipynb +59 -59
  5. natural_pdf-0.1.11/docs/element-selection/index.ipynb +957 -0
  6. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/element-selection/index.md +1 -2
  7. natural_pdf-0.1.11/docs/interactive-widget/index.ipynb +967 -0
  8. natural_pdf-0.1.11/docs/layout-analysis/index.ipynb +1974 -0
  9. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/layout-analysis/index.md +1 -1
  10. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/pdf-navigation/index.ipynb +85 -60
  11. natural_pdf-0.1.11/docs/regions/index.ipynb +820 -0
  12. natural_pdf-0.1.11/docs/tables/index.ipynb +662 -0
  13. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tables/index.md +1 -1
  14. natural_pdf-0.1.11/docs/text-analysis/index.ipynb +370 -0
  15. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/text-extraction/index.ipynb +283 -321
  16. natural_pdf-0.1.11/docs/tutorials/01-loading-and-extraction.ipynb +1628 -0
  17. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/02-finding-elements.ipynb +46 -46
  18. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/03-extracting-blocks.ipynb +17 -17
  19. natural_pdf-0.1.11/docs/tutorials/04-table-extraction.ipynb +195 -0
  20. natural_pdf-0.1.11/docs/tutorials/04-table-extraction.md +39 -0
  21. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/05-excluding-content.ipynb +30 -30
  22. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/06-document-qa.ipynb +28 -28
  23. natural_pdf-0.1.11/docs/tutorials/07-layout-analysis.ipynb +269 -0
  24. natural_pdf-0.1.11/docs/tutorials/07-working-with-regions.ipynb +470 -0
  25. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/07-working-with-regions.md +23 -19
  26. natural_pdf-0.1.11/docs/tutorials/08-spatial-navigation.ipynb +513 -0
  27. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/09-section-extraction.ipynb +111 -111
  28. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/10-form-field-extraction.ipynb +52 -52
  29. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/11-enhanced-table-processing.ipynb +6 -6
  30. natural_pdf-0.1.11/docs/tutorials/12-ocr-integration.ipynb +3556 -0
  31. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/12-ocr-integration.md +3 -1
  32. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/13-semantic-search.ipynb +313 -313
  33. natural_pdf-0.1.11/docs/tutorials/14-categorizing-documents.ipynb +2399 -0
  34. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/14-categorizing-documents.md +15 -1
  35. natural_pdf-0.1.11/docs/visual-debugging/index.ipynb +2975 -0
  36. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/__init__.py +24 -40
  37. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/core/page.py +17 -17
  38. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/core/pdf.py +130 -12
  39. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/elements/collections.py +229 -29
  40. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/elements/region.py +2 -3
  41. natural_pdf-0.1.11/natural_pdf/exporters/data/pdf.ttf +0 -0
  42. natural_pdf-0.1.11/natural_pdf/exporters/data/sRGB.icc +0 -0
  43. natural_pdf-0.1.11/natural_pdf/exporters/hocr.py +540 -0
  44. natural_pdf-0.1.11/natural_pdf/exporters/hocr_font.py +142 -0
  45. natural_pdf-0.1.11/natural_pdf/exporters/original_pdf.py +130 -0
  46. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/exporters/searchable_pdf.py +3 -3
  47. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/engine_surya.py +1 -1
  48. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf.egg-info/PKG-INFO +1 -2
  49. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf.egg-info/SOURCES.txt +5 -0
  50. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf.egg-info/requires.txt +0 -1
  51. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pyproject.toml +0 -1
  52. natural_pdf-0.1.10/docs/element-selection/index.ipynb +0 -969
  53. natural_pdf-0.1.10/docs/interactive-widget/index.ipynb +0 -962
  54. natural_pdf-0.1.10/docs/layout-analysis/index.ipynb +0 -818
  55. natural_pdf-0.1.10/docs/regions/index.ipynb +0 -816
  56. natural_pdf-0.1.10/docs/tables/index.ipynb +0 -658
  57. natural_pdf-0.1.10/docs/text-analysis/index.ipynb +0 -370
  58. natural_pdf-0.1.10/docs/tutorials/01-loading-and-extraction.ipynb +0 -1628
  59. natural_pdf-0.1.10/docs/tutorials/04-table-extraction.ipynb +0 -119
  60. natural_pdf-0.1.10/docs/tutorials/04-table-extraction.md +0 -50
  61. natural_pdf-0.1.10/docs/tutorials/07-layout-analysis.ipynb +0 -269
  62. natural_pdf-0.1.10/docs/tutorials/07-working-with-regions.ipynb +0 -414
  63. natural_pdf-0.1.10/docs/tutorials/08-spatial-navigation.ipynb +0 -513
  64. natural_pdf-0.1.10/docs/tutorials/12-ocr-integration.ipynb +0 -3712
  65. natural_pdf-0.1.10/docs/tutorials/14-categorizing-documents.ipynb +0 -2365
  66. natural_pdf-0.1.10/docs/visual-debugging/index.ipynb +0 -2970
  67. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.cursor/rules/analysis_framework.mdc +0 -0
  68. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.cursor/rules/coding-style.mdc +0 -0
  69. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.cursor/rules/edit-md-instead-of-ipynb.mdc +0 -0
  70. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.cursor/rules/minimal-comments.mdc +0 -0
  71. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.cursor/rules/natural-pdf-overview.mdc +0 -0
  72. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.cursor/rules/user-friendly-library-code.mdc +0 -0
  73. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/.github/workflows/docs.yml +0 -0
  74. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/02-run_all_tutorials.sh +0 -0
  75. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/CLAUDE.md +0 -0
  76. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/LICENSE +0 -0
  77. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/MANIFEST.in +0 -0
  78. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/README.md +0 -0
  79. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/audit_packaging.py +0 -0
  80. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/check_run_md.sh +0 -0
  81. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/api/index.md +0 -0
  82. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/favicon.png +0 -0
  83. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/favicon.svg +0 -0
  84. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/javascripts/custom.js +0 -0
  85. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/logo.svg +0 -0
  86. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/sample-screen.png +0 -0
  87. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/social-preview.png +0 -0
  88. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/social-preview.svg +0 -0
  89. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/assets/stylesheets/custom.css +0 -0
  90. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/categorizing-documents/index.md +0 -0
  91. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/data-extraction/index.md +0 -0
  92. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/document-qa/index.md +0 -0
  93. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/finetuning/index.md +0 -0
  94. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/index.md +0 -0
  95. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/installation/index.md +0 -0
  96. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/interactive-widget/index.md +0 -0
  97. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/ocr/index.md +0 -0
  98. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/pdf-navigation/index.md +0 -0
  99. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/regions/index.md +0 -0
  100. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/text-analysis/index.md +0 -0
  101. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/text-extraction/index.md +0 -0
  102. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/01-loading-and-extraction.md +0 -0
  103. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/02-finding-elements.md +0 -0
  104. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/03-extracting-blocks.md +0 -0
  105. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/05-excluding-content.md +0 -0
  106. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/06-document-qa.md +0 -0
  107. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/07-layout-analysis.md +0 -0
  108. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/08-spatial-navigation.md +0 -0
  109. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/09-section-extraction.md +0 -0
  110. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/10-form-field-extraction.md +0 -0
  111. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/11-enhanced-table-processing.md +0 -0
  112. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/tutorials/13-semantic-search.md +0 -0
  113. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/visual-debugging/index.md +0 -0
  114. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/docs/visual-debugging/region.png +0 -0
  115. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/mkdocs.yml +0 -0
  116. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/__init__.py +0 -0
  117. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/__init__.py +0 -0
  118. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/base.py +0 -0
  119. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/docling.py +0 -0
  120. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/gemini.py +0 -0
  121. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/layout_analyzer.py +0 -0
  122. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/layout_manager.py +0 -0
  123. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/layout_options.py +0 -0
  124. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/paddle.py +0 -0
  125. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/pdfplumber_table_finder.py +0 -0
  126. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/surya.py +0 -0
  127. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/tatr.py +0 -0
  128. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/layout/yolo.py +0 -0
  129. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/text_options.py +0 -0
  130. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/text_structure.py +0 -0
  131. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/analyzers/utils.py +0 -0
  132. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/classification/manager.py +0 -0
  133. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/classification/mixin.py +0 -0
  134. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/classification/results.py +0 -0
  135. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/collections/mixins.py +0 -0
  136. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/collections/pdf_collection.py +0 -0
  137. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/core/__init__.py +0 -0
  138. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/core/element_manager.py +0 -0
  139. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/core/highlighting_service.py +0 -0
  140. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/elements/__init__.py +0 -0
  141. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/elements/base.py +0 -0
  142. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/elements/line.py +0 -0
  143. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/elements/rect.py +0 -0
  144. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/elements/text.py +0 -0
  145. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/export/mixin.py +0 -0
  146. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/exporters/__init__.py +0 -0
  147. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/exporters/base.py +0 -0
  148. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/exporters/paddleocr.py +0 -0
  149. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/extraction/manager.py +0 -0
  150. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/extraction/mixin.py +0 -0
  151. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/extraction/result.py +0 -0
  152. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/__init__.py +0 -0
  153. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/engine.py +0 -0
  154. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/engine_doctr.py +0 -0
  155. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/engine_easyocr.py +0 -0
  156. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/engine_paddle.py +0 -0
  157. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/ocr_factory.py +0 -0
  158. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/ocr_manager.py +0 -0
  159. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/ocr_options.py +0 -0
  160. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/ocr/utils.py +0 -0
  161. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/qa/__init__.py +0 -0
  162. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/qa/document_qa.py +0 -0
  163. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/search/__init__.py +0 -0
  164. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/search/haystack_search_service.py +0 -0
  165. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/search/haystack_utils.py +0 -0
  166. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/search/search_options.py +0 -0
  167. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/search/search_service_protocol.py +0 -0
  168. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/search/searchable_mixin.py +0 -0
  169. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/selectors/__init__.py +0 -0
  170. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/selectors/parser.py +0 -0
  171. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/templates/__init__.py +0 -0
  172. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/templates/finetune/fine_tune_paddleocr.md +0 -0
  173. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/templates/spa/css/style.css +0 -0
  174. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/templates/spa/index.html +0 -0
  175. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/templates/spa/js/app.js +0 -0
  176. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/templates/spa/words.txt +0 -0
  177. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/__init__.py +0 -0
  178. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/debug.py +0 -0
  179. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/highlighting.py +0 -0
  180. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/identifiers.py +0 -0
  181. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/locks.py +0 -0
  182. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/packaging.py +0 -0
  183. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/reading_order.py +0 -0
  184. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/text_extraction.py +0 -0
  185. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/tqdm_utils.py +0 -0
  186. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/utils/visualization.py +0 -0
  187. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/widgets/__init__.py +0 -0
  188. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/widgets/frontend/viewer.js +0 -0
  189. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf/widgets/viewer.py +0 -0
  190. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf.egg-info/dependency_links.txt +0 -0
  191. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/natural_pdf.egg-info/top_level.txt +0 -0
  192. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/noxfile.py +0 -0
  193. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/.gitkeep +0 -0
  194. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/01-practice.pdf +0 -0
  195. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/0500000US42001.pdf +0 -0
  196. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/0500000US42007.pdf +0 -0
  197. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/2014 Statistics.pdf +0 -0
  198. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/2019 Statistics.pdf +0 -0
  199. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/Atlanta_Public_Schools_GA_sample.pdf +0 -0
  200. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/cia-doc.pdf +0 -0
  201. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/pdfs/needs-ocr.pdf +0 -0
  202. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/publish.sh +0 -0
  203. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/sample-screen.png +0 -0
  204. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/setup.cfg +0 -0
  205. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/tests/exporters/test_paddleocr_exporter.py +0 -0
  206. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/tests/test_loading.py +0 -0
  207. {natural_pdf-0.1.10 → natural_pdf-0.1.11}/tests/test_optional_deps.py +0 -0
@@ -1,6 +1,7 @@
1
1
  .notebook_cache.json
2
2
  .venv
3
3
  output
4
+ output.pdf
4
5
  Untitled.ipynb
5
6
  conversation.md
6
7
  docs/tutorials/pdfs
@@ -30,6 +30,7 @@ EXCLUDE_PATTERNS = [
30
30
  "finetuning/index.md",
31
31
  "categorizing-documents/index.md",
32
32
  "data-extraction/index.md",
33
+ "*.ipynb_checkpoints*"
33
34
  ]
34
35
  MAX_WORKERS = os.cpu_count()
35
36
 
@@ -177,7 +178,7 @@ def process_notebook(md_file_path_str: str, log_level: int) -> Dict[str, Any]:
177
178
  client = NotebookClient(
178
179
  notebook,
179
180
  timeout=600,
180
- kernel_name="natural-pdf-venv",
181
+ kernel_name="natural-pdf",
181
182
  resources={"metadata": {"path": str(cwd)}},
182
183
  )
183
184
  client.execute() # Modifies 'notebook' object
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: natural-pdf
3
- Version: 0.1.10
3
+ Version: 0.1.11
4
4
  Summary: A more intuitive interface for working with PDFs
5
5
  Author-email: Jonathan Soma <jonathan.soma@gmail.com>
6
6
  License-Expression: MIT
@@ -91,7 +91,6 @@ Requires-Dist: torchvision; extra == "core-ml"
91
91
  Requires-Dist: transformers[sentencepiece]; extra == "core-ml"
92
92
  Requires-Dist: huggingface_hub; extra == "core-ml"
93
93
  Provides-Extra: ocr-export
94
- Requires-Dist: ocrmypdf; extra == "ocr-export"
95
94
  Requires-Dist: pikepdf; extra == "ocr-export"
96
95
  Provides-Extra: export-extras
97
96
  Requires-Dist: jupytext; extra == "export-extras"