docling-pipelines 1.0.0.dev1__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.
Files changed (547) hide show
  1. docling_pipelines-1.0.0.dev1.dist-info/METADATA +113 -0
  2. docling_pipelines-1.0.0.dev1.dist-info/RECORD +547 -0
  3. docling_pipelines-1.0.0.dev1.dist-info/WHEEL +4 -0
  4. docling_pipelines-1.0.0.dev1.dist-info/entry_points.txt +3 -0
  5. docling_pipelines-1.0.0.dev1.dist-info/licenses/LICENSE +21 -0
  6. docpipe/__init__.py +1 -0
  7. docpipe/api/__init__.py +5 -0
  8. docpipe/api/api_router.py +27 -0
  9. docpipe/api/auth/__init__.py +1 -0
  10. docpipe/api/auth/dependencies.py +158 -0
  11. docpipe/api/auth/jwt_handler.py +72 -0
  12. docpipe/api/auth/ldap_auth.py +136 -0
  13. docpipe/api/auth/models.py +25 -0
  14. docpipe/api/auth/oauth2_config.py +101 -0
  15. docpipe/api/auth/oauth2_provider.py +342 -0
  16. docpipe/api/auth/oauth2_routes.py +197 -0
  17. docpipe/api/dependencies.py +36 -0
  18. docpipe/api/dto/__init__.py +0 -0
  19. docpipe/api/dto/authoring_flow_dto.py +448 -0
  20. docpipe/api/dto/document_dto.py +126 -0
  21. docpipe/api/dto/document_library_dto.py +468 -0
  22. docpipe/api/dto/document_library_mapper.py +194 -0
  23. docpipe/api/dto/document_set_dto.py +540 -0
  24. docpipe/api/dto/error_dto.py +289 -0
  25. docpipe/api/dto/field_definitions.py +677 -0
  26. docpipe/api/dto/flow_dto.py +1063 -0
  27. docpipe/api/dto/job_run_dto.py +598 -0
  28. docpipe/api/dto/job_stats_dto.py +263 -0
  29. docpipe/api/dto/mappers/__init__.py +0 -0
  30. docpipe/api/dto/mappers/flow_mapper.py +228 -0
  31. docpipe/api/dto/mappers/job_stats_mapper.py +94 -0
  32. docpipe/api/dto/mappers/node_stats_mapper.py +95 -0
  33. docpipe/api/dto/node_stats_dto.py +209 -0
  34. docpipe/api/dto/operator_dto.py +288 -0
  35. docpipe/api/main.py +419 -0
  36. docpipe/api/middleware/__init__.py +9 -0
  37. docpipe/api/middleware/api_logging_middleware.py +39 -0
  38. docpipe/api/middleware/error_handler.py +282 -0
  39. docpipe/api/middleware/payload_validation.py +35 -0
  40. docpipe/api/middleware/transaction_middleware.py +110 -0
  41. docpipe/api/routes/__init__.py +5 -0
  42. docpipe/api/routes/document_libraries.py +924 -0
  43. docpipe/api/routes/document_set_utils.py +89 -0
  44. docpipe/api/routes/document_sets.py +420 -0
  45. docpipe/api/routes/documents.py +322 -0
  46. docpipe/api/routes/flows.py +1180 -0
  47. docpipe/api/routes/job_runs.py +508 -0
  48. docpipe/api/routes/operators.py +232 -0
  49. docpipe/api/routes/validation.py +191 -0
  50. docpipe/api/services/__init__.py +0 -0
  51. docpipe/api/services/acl_query_builder.py +196 -0
  52. docpipe/api/services/opensearch_service.py +136 -0
  53. docpipe/cli/__init__.py +1 -0
  54. docpipe/cli/docpipe_cli.py +493 -0
  55. docpipe/core/README.md +37 -0
  56. docpipe/core/__init__.py +1 -0
  57. docpipe/core/adapters/__init__.py +21 -0
  58. docpipe/core/adapters/huggingface/__init__.py +7 -0
  59. docpipe/core/adapters/huggingface/huggingface_adapter.py +105 -0
  60. docpipe/core/adapters/litellm/__init__.py +9 -0
  61. docpipe/core/adapters/litellm/litellm_adapter.py +348 -0
  62. docpipe/core/adapters/llm_adapter_factory.py +299 -0
  63. docpipe/core/adapters/watsonx/__init__.py +9 -0
  64. docpipe/core/adapters/watsonx/watsonx_adapter.py +598 -0
  65. docpipe/core/assets/__init__.py +0 -0
  66. docpipe/core/assets/document_libraries/__init__.py +10 -0
  67. docpipe/core/assets/document_libraries/adapters/__init__.py +1 -0
  68. docpipe/core/assets/document_libraries/adapters/duckdb/__init__.py +7 -0
  69. docpipe/core/assets/document_libraries/adapters/duckdb/metadata_repository.py +767 -0
  70. docpipe/core/assets/document_libraries/adapters/repositories/__init__.py +1 -0
  71. docpipe/core/assets/document_libraries/adapters/repositories/duckdb_document_library_metadata_repository.py +716 -0
  72. docpipe/core/assets/document_libraries/adapters/storage/__init__.py +1 -0
  73. docpipe/core/assets/document_libraries/adapters/storage/duckdb_storage.py +221 -0
  74. docpipe/core/assets/document_libraries/application/__init__.py +1 -0
  75. docpipe/core/assets/document_libraries/application/services/__init__.py +1 -0
  76. docpipe/core/assets/document_libraries/application/services/document_library_service.py +678 -0
  77. docpipe/core/assets/document_libraries/domain/__init__.py +5 -0
  78. docpipe/core/assets/document_libraries/domain/models/__init__.py +1 -0
  79. docpipe/core/assets/document_libraries/domain/models/document_library.py +327 -0
  80. docpipe/core/assets/document_libraries/domain/ports/__init__.py +1 -0
  81. docpipe/core/assets/document_libraries/domain/ports/document_library_repository.py +295 -0
  82. docpipe/core/assets/document_libraries/domain/types.py +39 -0
  83. docpipe/core/assets/document_libraries/factories/__init__.py +7 -0
  84. docpipe/core/assets/document_libraries/factories/document_library_repository_factory.py +182 -0
  85. docpipe/core/assets/document_sets/__init__.py +0 -0
  86. docpipe/core/assets/document_sets/adapters/__init__.py +16 -0
  87. docpipe/core/assets/document_sets/adapters/duckdb/__init__.py +17 -0
  88. docpipe/core/assets/document_sets/adapters/duckdb/data_store.py +382 -0
  89. docpipe/core/assets/document_sets/adapters/duckdb/metadata_repository.py +515 -0
  90. docpipe/core/assets/document_sets/adapters/filesystem/__init__.py +1 -0
  91. docpipe/core/assets/document_sets/application/__init__.py +0 -0
  92. docpipe/core/assets/document_sets/application/services/__init__.py +0 -0
  93. docpipe/core/assets/document_sets/application/services/document_set_service.py +741 -0
  94. docpipe/core/assets/document_sets/domain/__init__.py +0 -0
  95. docpipe/core/assets/document_sets/domain/models/__init__.py +7 -0
  96. docpipe/core/assets/document_sets/domain/models/data_card.py +67 -0
  97. docpipe/core/assets/document_sets/domain/models/document_set.py +282 -0
  98. docpipe/core/assets/document_sets/domain/models/storage_reference.py +57 -0
  99. docpipe/core/assets/document_sets/domain/ports/__init__.py +10 -0
  100. docpipe/core/assets/document_sets/domain/ports/data_store.py +180 -0
  101. docpipe/core/assets/document_sets/domain/ports/metadata_repository.py +220 -0
  102. docpipe/core/assets/document_sets/domain/types.py +61 -0
  103. docpipe/core/assets/document_sets/factories/__init__.py +23 -0
  104. docpipe/core/assets/document_sets/factories/data_store_factory.py +178 -0
  105. docpipe/core/assets/document_sets/factories/metadata_repository_factory.py +181 -0
  106. docpipe/core/assets/flows/__init__.py +9 -0
  107. docpipe/core/assets/flows/adapters/__init__.py +3 -0
  108. docpipe/core/assets/flows/adapters/config/__init__.py +5 -0
  109. docpipe/core/assets/flows/adapters/config/repository_factory.py +127 -0
  110. docpipe/core/assets/flows/adapters/repositories/__init__.py +5 -0
  111. docpipe/core/assets/flows/adapters/repositories/flow_filesystem_utils.py +166 -0
  112. docpipe/core/assets/flows/adapters/repositories/local/__init__.py +6 -0
  113. docpipe/core/assets/flows/adapters/repositories/local/file_lock_manager.py +164 -0
  114. docpipe/core/assets/flows/adapters/repositories/local/local_flow_repository.py +845 -0
  115. docpipe/core/assets/flows/application/__init__.py +3 -0
  116. docpipe/core/assets/flows/application/services/__init__.py +6 -0
  117. docpipe/core/assets/flows/application/services/authoring_compiler.py +284 -0
  118. docpipe/core/assets/flows/application/services/flow_service.py +770 -0
  119. docpipe/core/assets/flows/application/services/validation_service.py +411 -0
  120. docpipe/core/assets/flows/domain/__init__.py +3 -0
  121. docpipe/core/assets/flows/domain/models/__init__.py +15 -0
  122. docpipe/core/assets/flows/domain/models/authoring_flow.py +403 -0
  123. docpipe/core/assets/flows/domain/models/flow.py +176 -0
  124. docpipe/core/assets/flows/domain/ports/__init__.py +5 -0
  125. docpipe/core/assets/flows/domain/ports/flow_repository.py +153 -0
  126. docpipe/core/constants/__init__.py +63 -0
  127. docpipe/core/constants/constants.py +662 -0
  128. docpipe/core/constants/operator_constants.py +1017 -0
  129. docpipe/core/data_access/__init__.py +6 -0
  130. docpipe/core/data_access/data_access_utils.py +79 -0
  131. docpipe/core/data_access/docpipe_data_access_local.py +83 -0
  132. docpipe/core/document_classes/__init__.py +3 -0
  133. docpipe/core/document_classes/acord_insurance_form.json +619 -0
  134. docpipe/core/document_classes/bank_statements.json +279 -0
  135. docpipe/core/document_classes/bill_of_lading.json +265 -0
  136. docpipe/core/document_classes/business_licenses_permits.json +193 -0
  137. docpipe/core/document_classes/claimant_s_statement.json +483 -0
  138. docpipe/core/document_classes/client_success_case_study.json +309 -0
  139. docpipe/core/document_classes/credit_card_statements.json +363 -0
  140. docpipe/core/document_classes/customer_data_table.json +247 -0
  141. docpipe/core/document_classes/customerinfo.json +121 -0
  142. docpipe/core/document_classes/customs_form.json +249 -0
  143. docpipe/core/document_classes/delivery_receipt.json +201 -0
  144. docpipe/core/document_classes/diploma_certification.json +183 -0
  145. docpipe/core/document_classes/driver_license.json +365 -0
  146. docpipe/core/document_classes/expense_reports.json +287 -0
  147. docpipe/core/document_classes/federal_law_cs.json +54 -0
  148. docpipe/core/document_classes/financial_statement.json +381 -0
  149. docpipe/core/document_classes/i_9_form.json +257 -0
  150. docpipe/core/document_classes/initial_claimant_s_statement_for_income_replacement_waiver_of_premium_benefits.json +899 -0
  151. docpipe/core/document_classes/insurance_claim.json +285 -0
  152. docpipe/core/document_classes/invoice.json +886 -0
  153. docpipe/core/document_classes/life_insurance_authorization_form.json +175 -0
  154. docpipe/core/document_classes/management_quarterly_cs.json +109 -0
  155. docpipe/core/document_classes/mortgage_lending_document.json +259 -0
  156. docpipe/core/document_classes/national_id_card.json +221 -0
  157. docpipe/core/document_classes/order_request_form.json +376 -0
  158. docpipe/core/document_classes/passport.json +293 -0
  159. docpipe/core/document_classes/patient_intake_form.json +265 -0
  160. docpipe/core/document_classes/purchase_order.json +802 -0
  161. docpipe/core/document_classes/receipt.json +249 -0
  162. docpipe/core/document_classes/remittance_payment_advice.json +275 -0
  163. docpipe/core/document_classes/sales_agreements.json +58 -0
  164. docpipe/core/document_classes/schooladmissonform.json +173 -0
  165. docpipe/core/document_classes/tax_forms_w_9_1099_941_1120.json +229 -0
  166. docpipe/core/document_classes/transcripts.json +238 -0
  167. docpipe/core/document_classes/utility_bill.json +451 -0
  168. docpipe/core/document_classes/w_4_form.json +193 -0
  169. docpipe/core/incremental_metadata/__init__.py +33 -0
  170. docpipe/core/incremental_metadata/adapters/__init__.py +25 -0
  171. docpipe/core/incremental_metadata/adapters/config/__init__.py +19 -0
  172. docpipe/core/incremental_metadata/adapters/config/incremental_metadata_factory.py +399 -0
  173. docpipe/core/incremental_metadata/adapters/stores/__init__.py +13 -0
  174. docpipe/core/incremental_metadata/adapters/stores/filesystem/__init__.py +9 -0
  175. docpipe/core/incremental_metadata/adapters/stores/filesystem/filesystem_incremental_store.py +385 -0
  176. docpipe/core/incremental_metadata/adapters/stores/postgres/__init__.py +11 -0
  177. docpipe/core/incremental_metadata/adapters/stores/postgres/models.py +29 -0
  178. docpipe/core/incremental_metadata/adapters/stores/postgres/postgres_incremental_store.py +260 -0
  179. docpipe/core/incremental_metadata/application/__init__.py +12 -0
  180. docpipe/core/incremental_metadata/application/services/__init__.py +12 -0
  181. docpipe/core/incremental_metadata/application/services/incremental_update_service.py +345 -0
  182. docpipe/core/incremental_metadata/domain/__init__.py +13 -0
  183. docpipe/core/incremental_metadata/domain/models/__init__.py +11 -0
  184. docpipe/core/incremental_metadata/domain/models/incremental_record.py +54 -0
  185. docpipe/core/incremental_metadata/domain/ports/__init__.py +11 -0
  186. docpipe/core/incremental_metadata/domain/ports/incremental_metadata_store.py +124 -0
  187. docpipe/core/job_management/__init__.py +64 -0
  188. docpipe/core/job_management/adapters/__init__.py +35 -0
  189. docpipe/core/job_management/adapters/config/__init__.py +22 -0
  190. docpipe/core/job_management/adapters/config/job_management_factory.py +545 -0
  191. docpipe/core/job_management/adapters/frameworks/__init__.py +19 -0
  192. docpipe/core/job_management/adapters/frameworks/default_job_run_manager.py +175 -0
  193. docpipe/core/job_management/adapters/services/__init__.py +17 -0
  194. docpipe/core/job_management/adapters/services/job_tracker_service.py +1384 -0
  195. docpipe/core/job_management/adapters/stores/__init__.py +26 -0
  196. docpipe/core/job_management/adapters/stores/duckdb/__init__.py +9 -0
  197. docpipe/core/job_management/adapters/stores/duckdb/duckdb_job_stats_store.py +798 -0
  198. docpipe/core/job_management/adapters/stores/inmemory/__init__.py +0 -0
  199. docpipe/core/job_management/adapters/stores/inmemory/inmemory_job_stats_store.py +455 -0
  200. docpipe/core/job_management/adapters/stores/json/__init__.py +0 -0
  201. docpipe/core/job_management/adapters/stores/json/json_job_stats_store.py +667 -0
  202. docpipe/core/job_management/adapters/stores/postgres/__init__.py +10 -0
  203. docpipe/core/job_management/adapters/stores/postgres/dal/__init__.py +11 -0
  204. docpipe/core/job_management/adapters/stores/postgres/dal/base_dao.py +267 -0
  205. docpipe/core/job_management/adapters/stores/postgres/dal/job_stats_dal.py +162 -0
  206. docpipe/core/job_management/adapters/stores/postgres/dal/node_stats_dal.py +243 -0
  207. docpipe/core/job_management/adapters/stores/postgres/database.py +208 -0
  208. docpipe/core/job_management/adapters/stores/postgres/mappers.py +129 -0
  209. docpipe/core/job_management/adapters/stores/postgres/migrations/alembic.ini +148 -0
  210. docpipe/core/job_management/adapters/stores/postgres/migrations/env.py +154 -0
  211. docpipe/core/job_management/adapters/stores/postgres/migrations/script.py.mako +30 -0
  212. docpipe/core/job_management/adapters/stores/postgres/migrations/versions/20260422_001_initial_schema.py +188 -0
  213. docpipe/core/job_management/adapters/stores/postgres/models.py +322 -0
  214. docpipe/core/job_management/adapters/stores/postgres/postgres_job_stats_store.py +379 -0
  215. docpipe/core/job_management/application/__init__.py +13 -0
  216. docpipe/core/job_management/application/aggregation/__init__.py +16 -0
  217. docpipe/core/job_management/application/aggregation/aggregator.py +263 -0
  218. docpipe/core/job_management/application/aggregation/batch_aggregator.py +810 -0
  219. docpipe/core/job_management/application/aggregation/strategies.py +104 -0
  220. docpipe/core/job_management/application/services/__init__.py +13 -0
  221. docpipe/core/job_management/application/services/job_management_service.py +505 -0
  222. docpipe/core/job_management/application/services/node_stats_aggregator.py +139 -0
  223. docpipe/core/job_management/domain/__init__.py +18 -0
  224. docpipe/core/job_management/domain/models/__init__.py +18 -0
  225. docpipe/core/job_management/domain/models/job_stats.py +63 -0
  226. docpipe/core/job_management/domain/models/node_stats.py +79 -0
  227. docpipe/core/job_management/domain/ports/__init__.py +15 -0
  228. docpipe/core/job_management/domain/ports/job_run_manager.py +121 -0
  229. docpipe/core/job_management/domain/ports/job_stats_service.py +551 -0
  230. docpipe/core/job_management/domain/ports/job_stats_store.py +220 -0
  231. docpipe/core/job_management/domain/utils/__init__.py +10 -0
  232. docpipe/core/job_management/domain/utils/normalization.py +40 -0
  233. docpipe/core/models/__init__.py +0 -0
  234. docpipe/core/models/session_info.py +74 -0
  235. docpipe/core/operators/__init__.py +1 -0
  236. docpipe/core/operators/abstract_operator.py +116 -0
  237. docpipe/core/operators/acl/__init__.py +31 -0
  238. docpipe/core/operators/acl/acl_operator.py +512 -0
  239. docpipe/core/operators/acl/adapters/__init__.py +15 -0
  240. docpipe/core/operators/acl/adapters/outbound/__init__.py +17 -0
  241. docpipe/core/operators/acl/adapters/outbound/factories/__init__.py +14 -0
  242. docpipe/core/operators/acl/adapters/outbound/factories/acl_adapter_factory.py +165 -0
  243. docpipe/core/operators/acl/adapters/outbound/sharepoint_adapter.py +812 -0
  244. docpipe/core/operators/acl/domain/__init__.py +19 -0
  245. docpipe/core/operators/acl/domain/models.py +145 -0
  246. docpipe/core/operators/acl/ports/__init__.py +13 -0
  247. docpipe/core/operators/acl/ports/outbound/__init__.py +13 -0
  248. docpipe/core/operators/acl/ports/outbound/acl_extraction.py +184 -0
  249. docpipe/core/operators/application/__init__.py +1 -0
  250. docpipe/core/operators/application/services/__init__.py +1 -0
  251. docpipe/core/operators/application/services/operator_metadata_service.py +152 -0
  252. docpipe/core/operators/document_sets/__init__.py +12 -0
  253. docpipe/core/operators/document_sets/document_set_operator.py +331 -0
  254. docpipe/core/operators/extract/__init__.py +5 -0
  255. docpipe/core/operators/extract/adapters/__init__.py +6 -0
  256. docpipe/core/operators/extract/adapters/outbound/__init__.py +27 -0
  257. docpipe/core/operators/extract/adapters/outbound/entity_extraction/__init__.py +6 -0
  258. docpipe/core/operators/extract/adapters/outbound/entity_extraction/docling_entity_adapter.py +459 -0
  259. docpipe/core/operators/extract/adapters/outbound/entity_extraction/llm_entity_adapter.py +486 -0
  260. docpipe/core/operators/extract/adapters/outbound/factories/__init__.py +13 -0
  261. docpipe/core/operators/extract/adapters/outbound/factories/entity_extraction_adapter_factory.py +221 -0
  262. docpipe/core/operators/extract/adapters/outbound/factories/text_extraction_adapter_factory.py +384 -0
  263. docpipe/core/operators/extract/adapters/outbound/text_extraction/__init__.py +19 -0
  264. docpipe/core/operators/extract/adapters/outbound/text_extraction/docling_adapter.py +281 -0
  265. docpipe/core/operators/extract/adapters/outbound/text_extraction/docling_serve_adapter.py +224 -0
  266. docpipe/core/operators/extract/domain/__init__.py +19 -0
  267. docpipe/core/operators/extract/domain/models.py +173 -0
  268. docpipe/core/operators/extract/extract_operator.py +1095 -0
  269. docpipe/core/operators/extract/ports/__init__.py +1 -0
  270. docpipe/core/operators/extract/ports/outbound/__init__.py +6 -0
  271. docpipe/core/operators/extract/ports/outbound/entity_extraction.py +180 -0
  272. docpipe/core/operators/extract/ports/outbound/text_extraction.py +524 -0
  273. docpipe/core/operators/extract/services/__init__.py +0 -0
  274. docpipe/core/operators/extract/services/entity_extraction_service.py +652 -0
  275. docpipe/core/operators/functional/__init__.py +17 -0
  276. docpipe/core/operators/functional/branching_operator.py +357 -0
  277. docpipe/core/operators/functional/chunker.py +1368 -0
  278. docpipe/core/operators/functional/chunker_validator.py +300 -0
  279. docpipe/core/operators/functional/doc_id_hash.py +138 -0
  280. docpipe/core/operators/functional/embeddings/__init__.py +37 -0
  281. docpipe/core/operators/functional/embeddings/adapters/__init__.py +1 -0
  282. docpipe/core/operators/functional/embeddings/adapters/outbound/__init__.py +18 -0
  283. docpipe/core/operators/functional/embeddings/adapters/outbound/factories/__init__.py +1 -0
  284. docpipe/core/operators/functional/embeddings/adapters/outbound/factories/llm_adapter_factory.py +100 -0
  285. docpipe/core/operators/functional/embeddings/adapters/outbound/huggingface_adapter.py +92 -0
  286. docpipe/core/operators/functional/embeddings/adapters/outbound/litellm_adapter.py +166 -0
  287. docpipe/core/operators/functional/embeddings/adapters/outbound/ollama_adapter.py +183 -0
  288. docpipe/core/operators/functional/embeddings/adapters/outbound/watsonx_adapter.py +174 -0
  289. docpipe/core/operators/functional/embeddings/domain/__init__.py +5 -0
  290. docpipe/core/operators/functional/embeddings/domain/models.py +54 -0
  291. docpipe/core/operators/functional/embeddings/embeddings_operator.py +1019 -0
  292. docpipe/core/operators/functional/embeddings/ports/__init__.py +1 -0
  293. docpipe/core/operators/functional/embeddings/ports/outbound/__init__.py +1 -0
  294. docpipe/core/operators/functional/embeddings/ports/outbound/llm_service.py +90 -0
  295. docpipe/core/operators/functional/entity_curation/__init__.py +5 -0
  296. docpipe/core/operators/functional/entity_curation/entity_curation_operator.py +266 -0
  297. docpipe/core/operators/functional/entity_curation/schema_processor.py +409 -0
  298. docpipe/core/operators/functional/entity_curation/transforms/__init__.py +29 -0
  299. docpipe/core/operators/functional/entity_curation/transforms/currency_to_numeric.py +169 -0
  300. docpipe/core/operators/functional/entity_curation/transforms/make_date_uniform.py +100 -0
  301. docpipe/core/operators/functional/entity_curation/transforms/to_number.py +178 -0
  302. docpipe/core/operators/functional/entity_curation/transforms/weight_to_numeric.py +301 -0
  303. docpipe/core/operators/functional/merge.py +466 -0
  304. docpipe/core/operators/functional/noop.py +83 -0
  305. docpipe/core/operators/functional/summarization_service.py +389 -0
  306. docpipe/core/operators/ingest/__init__.py +0 -0
  307. docpipe/core/operators/ingest/adapters/__init__.py +1 -0
  308. docpipe/core/operators/ingest/adapters/outbound/__init__.py +1 -0
  309. docpipe/core/operators/ingest/adapters/outbound/sources/__init__.py +24 -0
  310. docpipe/core/operators/ingest/adapters/outbound/sources/box/README.md +200 -0
  311. docpipe/core/operators/ingest/adapters/outbound/sources/box/__init__.py +10 -0
  312. docpipe/core/operators/ingest/adapters/outbound/sources/box/adapter.py +308 -0
  313. docpipe/core/operators/ingest/adapters/outbound/sources/box/config.py +79 -0
  314. docpipe/core/operators/ingest/adapters/outbound/sources/factories/__init__.py +5 -0
  315. docpipe/core/operators/ingest/adapters/outbound/sources/factories/source_factory.py +146 -0
  316. docpipe/core/operators/ingest/adapters/outbound/sources/filesystem/__init__.py +6 -0
  317. docpipe/core/operators/ingest/adapters/outbound/sources/filesystem/adapter.py +296 -0
  318. docpipe/core/operators/ingest/adapters/outbound/sources/filesystem/config.py +76 -0
  319. docpipe/core/operators/ingest/adapters/outbound/sources/filesystem/example_usage.py +138 -0
  320. docpipe/core/operators/ingest/adapters/outbound/sources/google_drive/README.md +446 -0
  321. docpipe/core/operators/ingest/adapters/outbound/sources/google_drive/__init__.py +6 -0
  322. docpipe/core/operators/ingest/adapters/outbound/sources/google_drive/adapter.py +566 -0
  323. docpipe/core/operators/ingest/adapters/outbound/sources/google_drive/config.py +137 -0
  324. docpipe/core/operators/ingest/adapters/outbound/sources/onedrive/README.md +260 -0
  325. docpipe/core/operators/ingest/adapters/outbound/sources/onedrive/__init__.py +6 -0
  326. docpipe/core/operators/ingest/adapters/outbound/sources/onedrive/adapter.py +367 -0
  327. docpipe/core/operators/ingest/adapters/outbound/sources/onedrive/config.py +106 -0
  328. docpipe/core/operators/ingest/adapters/outbound/sources/s3/README.md +488 -0
  329. docpipe/core/operators/ingest/adapters/outbound/sources/s3/__init__.py +6 -0
  330. docpipe/core/operators/ingest/adapters/outbound/sources/s3/adapter.py +643 -0
  331. docpipe/core/operators/ingest/adapters/outbound/sources/s3/config.py +145 -0
  332. docpipe/core/operators/ingest/adapters/outbound/sources/sharepoint/README.md +296 -0
  333. docpipe/core/operators/ingest/adapters/outbound/sources/sharepoint/__init__.py +6 -0
  334. docpipe/core/operators/ingest/adapters/outbound/sources/sharepoint/adapter.py +370 -0
  335. docpipe/core/operators/ingest/adapters/outbound/sources/sharepoint/config.py +106 -0
  336. docpipe/core/operators/ingest/adapters/outbound/sources/web/README.md +213 -0
  337. docpipe/core/operators/ingest/adapters/outbound/sources/web/__init__.py +6 -0
  338. docpipe/core/operators/ingest/adapters/outbound/sources/web/adapter.py +277 -0
  339. docpipe/core/operators/ingest/adapters/outbound/sources/web/config.py +97 -0
  340. docpipe/core/operators/ingest/domain/__init__.py +1 -0
  341. docpipe/core/operators/ingest/domain/models.py +138 -0
  342. docpipe/core/operators/ingest/ingest_local.py +537 -0
  343. docpipe/core/operators/ingest/ingest_source.py +960 -0
  344. docpipe/core/operators/ingest/ingest_utils.py +50 -0
  345. docpipe/core/operators/ingest/ports/__init__.py +1 -0
  346. docpipe/core/operators/ingest/ports/outbound/__init__.py +1 -0
  347. docpipe/core/operators/ingest/ports/outbound/document_source.py +153 -0
  348. docpipe/core/operators/operator_metadata.py +349 -0
  349. docpipe/core/operators/operator_registry.py +111 -0
  350. docpipe/core/operators/operator_utils.py +1296 -0
  351. docpipe/core/operators/quality/__init__.py +1 -0
  352. docpipe/core/operators/quality/classification/__init__.py +1 -0
  353. docpipe/core/operators/quality/classification/classification_service.py +291 -0
  354. docpipe/core/operators/quality/classification/document_classifier.py +859 -0
  355. docpipe/core/operators/quality/classification/domain/__init__.py +1 -0
  356. docpipe/core/operators/quality/classification/domain/models.py +103 -0
  357. docpipe/core/operators/quality/de +66 -0
  358. docpipe/core/operators/quality/doc_quality.py +149 -0
  359. docpipe/core/operators/quality/ededup.py +124 -0
  360. docpipe/core/operators/quality/en +403 -0
  361. docpipe/core/operators/quality/es +68 -0
  362. docpipe/core/operators/quality/fr +91 -0
  363. docpipe/core/operators/quality/ja +180 -0
  364. docpipe/core/operators/quality/language_detection/__init__.py +1 -0
  365. docpipe/core/operators/quality/language_detection/adapters/__init__.py +1 -0
  366. docpipe/core/operators/quality/language_detection/adapters/outbound/__init__.py +14 -0
  367. docpipe/core/operators/quality/language_detection/adapters/outbound/factories/__init__.py +1 -0
  368. docpipe/core/operators/quality/language_detection/adapters/outbound/factories/language_adapter_factory.py +99 -0
  369. docpipe/core/operators/quality/language_detection/adapters/outbound/fasttext_adapter.py +116 -0
  370. docpipe/core/operators/quality/language_detection/adapters/outbound/langdetect_adapter.py +86 -0
  371. docpipe/core/operators/quality/language_detection/domain/__init__.py +5 -0
  372. docpipe/core/operators/quality/language_detection/domain/models.py +21 -0
  373. docpipe/core/operators/quality/language_detection/lang_id.py +241 -0
  374. docpipe/core/operators/quality/language_detection/ports/__init__.py +1 -0
  375. docpipe/core/operators/quality/language_detection/ports/outbound/__init__.py +1 -0
  376. docpipe/core/operators/quality/language_detection/ports/outbound/language_service.py +52 -0
  377. docpipe/core/operators/quality/ml_enrichment.py +294 -0
  378. docpipe/core/operators/quality/pii_and_hap/__init__.py +1 -0
  379. docpipe/core/operators/quality/pii_and_hap/domain/__init__.py +1 -0
  380. docpipe/core/operators/quality/pii_and_hap/domain/models.py +67 -0
  381. docpipe/core/operators/quality/pii_and_hap/local_pii_hap_detect.py +163 -0
  382. docpipe/core/operators/quality/pii_and_hap/pii_and_hap_annotator.py +768 -0
  383. docpipe/core/operators/quality/pii_and_hap/pii_and_hap_helper.py +429 -0
  384. docpipe/core/operators/quality/pii_and_hap/pii_prompt_examples.json +136 -0
  385. docpipe/core/operators/quality/pii_and_hap/services/__init__.py +5 -0
  386. docpipe/core/operators/quality/pii_and_hap/services/pii_hap_service.py +298 -0
  387. docpipe/core/operators/quality/readability/__init__.py +8 -0
  388. docpipe/core/operators/quality/readability/easy_words.txt +2941 -0
  389. docpipe/core/operators/quality/readability/readability_metrics.py +213 -0
  390. docpipe/core/operators/quality/readability/readability_operator.py +213 -0
  391. docpipe/core/operators/quality/redaction.py +193 -0
  392. docpipe/core/operators/quality/sql_filter.py +690 -0
  393. docpipe/core/operators/storage/__init__.py +1 -0
  394. docpipe/core/operators/vectordb/__init__.py +33 -0
  395. docpipe/core/operators/vectordb/adapters/__init__.py +1 -0
  396. docpipe/core/operators/vectordb/adapters/outbound/__init__.py +25 -0
  397. docpipe/core/operators/vectordb/adapters/outbound/factories/__init__.py +1 -0
  398. docpipe/core/operators/vectordb/adapters/outbound/factories/vector_store_factory.py +278 -0
  399. docpipe/core/operators/vectordb/adapters/outbound/milvus/__init__.py +21 -0
  400. docpipe/core/operators/vectordb/adapters/outbound/milvus/adapter.py +267 -0
  401. docpipe/core/operators/vectordb/adapters/outbound/milvus/batch_processor.py +317 -0
  402. docpipe/core/operators/vectordb/adapters/outbound/milvus/client.py +262 -0
  403. docpipe/core/operators/vectordb/adapters/outbound/milvus/index_manager.py +544 -0
  404. docpipe/core/operators/vectordb/adapters/outbound/opensearch/__init__.py +13 -0
  405. docpipe/core/operators/vectordb/adapters/outbound/opensearch/adapter.py +241 -0
  406. docpipe/core/operators/vectordb/adapters/outbound/opensearch/batch_processor.py +408 -0
  407. docpipe/core/operators/vectordb/adapters/outbound/opensearch/client.py +230 -0
  408. docpipe/core/operators/vectordb/adapters/outbound/opensearch/index_manager.py +1056 -0
  409. docpipe/core/operators/vectordb/domain/__init__.py +13 -0
  410. docpipe/core/operators/vectordb/domain/models.py +113 -0
  411. docpipe/core/operators/vectordb/ports/__init__.py +1 -0
  412. docpipe/core/operators/vectordb/ports/outbound/__init__.py +1 -0
  413. docpipe/core/operators/vectordb/ports/outbound/vector_store.py +140 -0
  414. docpipe/core/operators/vectordb/schemas/default_schema.v1.json +56 -0
  415. docpipe/core/operators/vectordb/schemas/full_schema.v1.json +57 -0
  416. docpipe/core/operators/vectordb/schemas/template_with_content_analyzer.v1.json +89 -0
  417. docpipe/core/operators/vectordb/vectordb_operator.py +686 -0
  418. docpipe/core/orchestration/__init__.py +0 -0
  419. docpipe/core/orchestration/abstract_flow_execution_event_handler.py +85 -0
  420. docpipe/core/orchestration/abstract_operator_executor.py +467 -0
  421. docpipe/core/orchestration/abstract_orchestrator.py +663 -0
  422. docpipe/core/orchestration/batch_manager.py +287 -0
  423. docpipe/core/orchestration/cmdline/__init__.py +0 -0
  424. docpipe/core/orchestration/cmdline/cmd_line_operator_executor.py +24 -0
  425. docpipe/core/orchestration/feature_propagation/__init__.py +19 -0
  426. docpipe/core/orchestration/feature_propagation/features_propagator.py +685 -0
  427. docpipe/core/orchestration/feature_propagation/models.py +262 -0
  428. docpipe/core/orchestration/flow_execution_event_handler.py +493 -0
  429. docpipe/core/orchestration/flow_executor.py +238 -0
  430. docpipe/core/orchestration/flow_validator.py +1297 -0
  431. docpipe/core/orchestration/futured_list.py +61 -0
  432. docpipe/core/orchestration/global_config_metadata.py +196 -0
  433. docpipe/core/orchestration/operator_factory.py +257 -0
  434. docpipe/core/orchestration/operator_loader/__init__.py +5 -0
  435. docpipe/core/orchestration/operator_loader/adapters/__init__.py +10 -0
  436. docpipe/core/orchestration/operator_loader/adapters/factories/__init__.py +1 -0
  437. docpipe/core/orchestration/operator_loader/adapters/factories/operator_source_factory.py +152 -0
  438. docpipe/core/orchestration/operator_loader/adapters/filesystem_adapter.py +240 -0
  439. docpipe/core/orchestration/operator_loader/adapters/package_adapter.py +322 -0
  440. docpipe/core/orchestration/operator_loader/adapters/s3_adapter.py +195 -0
  441. docpipe/core/orchestration/operator_loader/loader_service.py +289 -0
  442. docpipe/core/orchestration/operator_loader/ports/__init__.py +1 -0
  443. docpipe/core/orchestration/operator_loader/ports/operator_source.py +110 -0
  444. docpipe/core/orchestration/operator_loader/validator.py +158 -0
  445. docpipe/core/orchestration/orchestrator_factory.py +56 -0
  446. docpipe/core/orchestration/prefect/__init__.py +19 -0
  447. docpipe/core/orchestration/prefect/adapters/__init__.py +0 -0
  448. docpipe/core/orchestration/prefect/adapters/factories/__init__.py +0 -0
  449. docpipe/core/orchestration/prefect/adapters/factories/batch_execution_factory.py +232 -0
  450. docpipe/core/orchestration/prefect/adapters/thread_pool_adapter.py +80 -0
  451. docpipe/core/orchestration/prefect/adapters/work_pool_adapter.py +1115 -0
  452. docpipe/core/orchestration/prefect/batch_subflow.py +241 -0
  453. docpipe/core/orchestration/prefect/config/__init__.py +0 -0
  454. docpipe/core/orchestration/prefect/config/work_pool_config.py +99 -0
  455. docpipe/core/orchestration/prefect/domain/__init__.py +0 -0
  456. docpipe/core/orchestration/prefect/domain/models.py +143 -0
  457. docpipe/core/orchestration/prefect/ports/__init__.py +0 -0
  458. docpipe/core/orchestration/prefect/ports/batch_execution_port.py +73 -0
  459. docpipe/core/orchestration/prefect/prefect_engine.py +753 -0
  460. docpipe/core/orchestration/python/__init__.py +0 -0
  461. docpipe/core/orchestration/python/python_operator_executor.py +191 -0
  462. docpipe/core/orchestration/python/python_orchestrator.py +50 -0
  463. docpipe/core/ports/llm_embedding_port.py +89 -0
  464. docpipe/core/ports/llm_inference_port.py +79 -0
  465. docpipe/core/ports/text_detection_port.py +74 -0
  466. docpipe/exceptions/__init__.py +1 -0
  467. docpipe/exceptions/docpipe_exceptions.py +707 -0
  468. docpipe/exceptions/error_codes.py +99 -0
  469. docpipe/exceptions/error_messages.py +127 -0
  470. docpipe/integrations/__init__.py +1 -0
  471. docpipe/integrations/base_llm_client.py +286 -0
  472. docpipe/integrations/docling/__init__.py +1 -0
  473. docpipe/integrations/docling/client.py +450 -0
  474. docpipe/integrations/docling/vlm_pipeline_options_provider.py +637 -0
  475. docpipe/integrations/huggingface/__init__.py +1 -0
  476. docpipe/integrations/huggingface/client.py +384 -0
  477. docpipe/integrations/litellm/__init__.py +1 -0
  478. docpipe/integrations/litellm/client.py +415 -0
  479. docpipe/integrations/ollama/__init__.py +1 -0
  480. docpipe/integrations/ollama/client.py +915 -0
  481. docpipe/integrations/ollama/embeddings.py +69 -0
  482. docpipe/integrations/rest_client.py +463 -0
  483. docpipe/integrations/watsonx/__init__.py +9 -0
  484. docpipe/integrations/watsonx/client.py +324 -0
  485. docpipe/integrations/watsonx/model_validator.py +132 -0
  486. docpipe/integrations/watsonx/rest_client.py +551 -0
  487. docpipe/lib/__init__.py +0 -0
  488. docpipe/lib/docpipe_flow_manager.py +453 -0
  489. docpipe/storage/__init__.py +36 -0
  490. docpipe/storage/duck_db/__init__.py +9 -0
  491. docpipe/storage/duck_db/connection.py +6 -0
  492. docpipe/storage/duck_db/key_value_storage.py +278 -0
  493. docpipe/storage/duck_db/table_storage.py +499 -0
  494. docpipe/storage/duck_db/utils.py +52 -0
  495. docpipe/storage/exceptions.py +32 -0
  496. docpipe/storage/factory.py +86 -0
  497. docpipe/storage/file_system/__init__.py +5 -0
  498. docpipe/storage/file_system/key_value_storage.py +213 -0
  499. docpipe/storage/file_system/utils.py +3 -0
  500. docpipe/storage/interfaces/__init__.py +9 -0
  501. docpipe/storage/interfaces/key_value_storage.py +113 -0
  502. docpipe/storage/interfaces/table_storage.py +130 -0
  503. docpipe/utils/__init__.py +1 -0
  504. docpipe/utils/core/__init__.py +50 -0
  505. docpipe/utils/core/collections.py +128 -0
  506. docpipe/utils/core/datetime.py +13 -0
  507. docpipe/utils/core/docpipe_utils.py +25 -0
  508. docpipe/utils/core/memmap_file_utils.py +419 -0
  509. docpipe/utils/core/patterns.py +20 -0
  510. docpipe/utils/core/strings.py +115 -0
  511. docpipe/utils/core/validation.py +441 -0
  512. docpipe/utils/data/__init__.py +22 -0
  513. docpipe/utils/data/incremental_metadata_store.py +0 -0
  514. docpipe/utils/data/pyarrow_handler.py +172 -0
  515. docpipe/utils/data/schema_utils.py +93 -0
  516. docpipe/utils/data/transform.py +13 -0
  517. docpipe/utils/document_class_utils.py +561 -0
  518. docpipe/utils/duckdb/__init__.py +5 -0
  519. docpipe/utils/duckdb/connection_manager.py +87 -0
  520. docpipe/utils/global_config/__init__.py +5 -0
  521. docpipe/utils/global_config/display.py +159 -0
  522. docpipe/utils/infrastructure/__init__.py +41 -0
  523. docpipe/utils/infrastructure/caching.py +78 -0
  524. docpipe/utils/infrastructure/concurrency.py +124 -0
  525. docpipe/utils/infrastructure/config.py +226 -0
  526. docpipe/utils/infrastructure/error_formatter.py +277 -0
  527. docpipe/utils/infrastructure/fasttext_model_manager.py +279 -0
  528. docpipe/utils/infrastructure/filesystem.py +55 -0
  529. docpipe/utils/infrastructure/flow_execution_reporter.py +658 -0
  530. docpipe/utils/infrastructure/iam_token_manager.py +229 -0
  531. docpipe/utils/infrastructure/logging.py +333 -0
  532. docpipe/utils/infrastructure/nltk_data_manager.py +204 -0
  533. docpipe/utils/infrastructure/performance.py +137 -0
  534. docpipe/utils/infrastructure/rate_limiter.py +329 -0
  535. docpipe/utils/infrastructure/retry.py +104 -0
  536. docpipe/utils/operators/__init__.py +18 -0
  537. docpipe/utils/operators/binary_content_fetcher.py +291 -0
  538. docpipe/utils/operators/config_validation.py +59 -0
  539. docpipe/utils/operators/display.py +221 -0
  540. docpipe/utils/operators/logging.py +298 -0
  541. docpipe/utils/operators/vectordb_utils.py +138 -0
  542. docpipe/utils/orchestration/__init__.py +45 -0
  543. docpipe/utils/orchestration/deleted_rows_tracker.py +150 -0
  544. docpipe/utils/orchestration/elyra_converter.py +1169 -0
  545. docpipe/utils/orchestration/flow_utils.py +115 -0
  546. docpipe/utils/orchestration/prefect_config.py +151 -0
  547. docpipe/utils/summarization_util.py +263 -0
@@ -0,0 +1,113 @@
1
+ Metadata-Version: 2.4
2
+ Name: docling-pipelines
3
+ Version: 1.0.0.dev1
4
+ Summary: This repository contains the docpipe operators.
5
+ Maintainer-email: Jojo Joseph <jjojo@in.ibm.com>, Aditya Rohan Singh <adityars@ibm.com>, Anudeep Dunaboyina <anudeep.dunaboyina@ibm.com>, Ashok Kumar Angadi <asangadi@in.ibm.com>, Harshad Nehate <Harshad.Nehate@ibm.com>, Kurian Kevin <Kurian.Kevin@ibm.com>, Nipun Bayas <nipun.bayas@ibm.com>, Paul Baby <Paul.Baby1@ibm.com>, Prasad Madugundu <smadugun@in.ibm.com>, Remya P <remya.p@ibm.com>, Sahil Berwal <Sahil.Berwal@ibm.com>, Sanchit Rote <Sanchit.Rote@ibm.com>, Yash Bopardikar <ybopard@us.ibm.com>, Benson Fernandes <benferna@in.ibm.com>, Manish Soni <Manish.Soni3@ibm.com>, Docling Pipeline Team <docling_pipeline_team-dg@ibm.com>
6
+ License-File: LICENSE
7
+ Requires-Python: <3.13,>=3.12
8
+ Requires-Dist: accelerate==1.13.0
9
+ Requires-Dist: aiohttp==3.14.1
10
+ Requires-Dist: alembic==1.18.4
11
+ Requires-Dist: azure-storage-blob==12.28.0
12
+ Requires-Dist: babel==2.18.0
13
+ Requires-Dist: boto3==1.42.55
14
+ Requires-Dist: botocore==1.42.55
15
+ Requires-Dist: box-sdk-gen==1.17.0
16
+ Requires-Dist: data-prep-toolkit-transforms==1.1.8
17
+ Requires-Dist: datatrove==0.3.0
18
+ Requires-Dist: datefinder==1.0.0
19
+ Requires-Dist: docling[rapidocr]==2.105.0
20
+ Requires-Dist: duckdb==1.3.2
21
+ Requires-Dist: fastapi==0.136.3
22
+ Requires-Dist: fasttext-wheel==0.9.2
23
+ Requires-Dist: filelock==3.24.2
24
+ Requires-Dist: ftfy==6.3.1
25
+ Requires-Dist: google-api-python-client==2.190.0
26
+ Requires-Dist: google-auth-httplib2==0.3.0
27
+ Requires-Dist: google-auth-oauthlib==1.2.4
28
+ Requires-Dist: google-cloud-storage==3.9.0
29
+ Requires-Dist: google-re2==1.1.20251105
30
+ Requires-Dist: griffe==1.15.0
31
+ Requires-Dist: httpx==0.28.1
32
+ Requires-Dist: ibm-cos-sdk==2.14.3
33
+ Requires-Dist: ibm-watsonx-ai==1.5.10
34
+ Requires-Dist: idna==3.15
35
+ Requires-Dist: langchain-classic==1.0.7
36
+ Requires-Dist: langchain-community==0.4.1
37
+ Requires-Dist: langchain-core==1.4.6
38
+ Requires-Dist: langchain-experimental==0.4.1
39
+ Requires-Dist: langchain-text-splitters==1.1.2
40
+ Requires-Dist: langchain==1.3.9
41
+ Requires-Dist: langdetect==1.0.9
42
+ Requires-Dist: langsmith==0.8.4
43
+ Requires-Dist: litellm==1.84.0
44
+ Requires-Dist: lxml==6.1.0
45
+ Requires-Dist: mako==1.3.12
46
+ Requires-Dist: mlx==0.30.6; sys_platform == 'darwin'
47
+ Requires-Dist: msal==1.37.0
48
+ Requires-Dist: nltk==3.10.0
49
+ Requires-Dist: o365==2.1.9
50
+ Requires-Dist: ollama==0.6.1
51
+ Requires-Dist: openai==2.33.0
52
+ Requires-Dist: opensearch-py==3.1.0
53
+ Requires-Dist: orjson==3.11.7
54
+ Requires-Dist: pandas==2.3.3
55
+ Requires-Dist: passlib[bcrypt]==1.7.4
56
+ Requires-Dist: pillow==12.2.0
57
+ Requires-Dist: polars==1.32.3
58
+ Requires-Dist: prefect==3.7.1
59
+ Requires-Dist: psycopg2-binary==2.9.12
60
+ Requires-Dist: pyarrow==24.0.0
61
+ Requires-Dist: pyasn1==0.6.3
62
+ Requires-Dist: pydantic-settings==2.14.0
63
+ Requires-Dist: pydantic==2.12.5
64
+ Requires-Dist: pygments==2.20.0
65
+ Requires-Dist: pyiceberg-core==0.7.0
66
+ Requires-Dist: pyiceberg[glue]==0.9.1
67
+ Requires-Dist: pyjwt==2.13.0
68
+ Requires-Dist: pymilvus==2.6.13
69
+ Requires-Dist: pyopenssl==26.3.0
70
+ Requires-Dist: pypdf==6.13.3
71
+ Requires-Dist: pyphen==0.17.2
72
+ Requires-Dist: python-dotenv==1.2.1
73
+ Requires-Dist: python-jose[cryptography]==3.5.0
74
+ Requires-Dist: python-ldap==3.4.5
75
+ Requires-Dist: pyyaml==6.0.3
76
+ Requires-Dist: requests==2.32.5
77
+ Requires-Dist: sentence-transformers==5.4.1
78
+ Requires-Dist: setuptools==81.0.0
79
+ Requires-Dist: sqlalchemy==2.0.49
80
+ Requires-Dist: sqlglot==27.13.2
81
+ Requires-Dist: sqlmodel==0.0.38
82
+ Requires-Dist: starlette==1.3.1
83
+ Requires-Dist: tabulate==0.9.0
84
+ Requires-Dist: tenacity==8.3.0
85
+ Requires-Dist: toml==0.10.2
86
+ Requires-Dist: torch==2.12.1
87
+ Requires-Dist: transformers==5.8.1
88
+ Requires-Dist: unicategories==0.1.2
89
+ Requires-Dist: unicodedataplus==16.0.0.post1
90
+ Requires-Dist: urllib3==2.7.0
91
+ Requires-Dist: uvicorn[standard]==0.40.0
92
+ Provides-Extra: dev
93
+ Requires-Dist: black==26.1.0; extra == 'dev'
94
+ Requires-Dist: detect-secrets==1.5.0; extra == 'dev'
95
+ Requires-Dist: faker==40.8.0; extra == 'dev'
96
+ Requires-Dist: flake8==7.3.0; extra == 'dev'
97
+ Requires-Dist: httpx==0.28.1; extra == 'dev'
98
+ Requires-Dist: mypy==1.19.1; extra == 'dev'
99
+ Requires-Dist: pre-commit==4.5.1; extra == 'dev'
100
+ Requires-Dist: pytest-asyncio==1.4.0; extra == 'dev'
101
+ Requires-Dist: pytest-cov==7.0.0; extra == 'dev'
102
+ Requires-Dist: pytest-mock==3.15.1; extra == 'dev'
103
+ Requires-Dist: pytest==9.0.2; extra == 'dev'
104
+ Requires-Dist: ruff==0.15.5; extra == 'dev'
105
+ Provides-Extra: notebooks
106
+ Requires-Dist: ipykernel==7.3.0; extra == 'notebooks'
107
+ Requires-Dist: jupyter==1.1.1; extra == 'notebooks'
108
+ Requires-Dist: matplotlib==3.11.0; extra == 'notebooks'
109
+ Requires-Dist: nbconvert==7.17.1; extra == 'notebooks'
110
+ Requires-Dist: nbformat==5.10.4; extra == 'notebooks'
111
+ Requires-Dist: seaborn==0.13.2; extra == 'notebooks'
112
+ Provides-Extra: vlm-asr
113
+ Requires-Dist: docling[asr,vlm]; extra == 'vlm-asr'