Commit Graph

  • 969115b1dd Use default layout model in model_downloader default args Christoph Auer 2025-07-23 08:51:07 +02:00
  • e0482723c4 Use default layout model in model_downloader default args Christoph Auer 2025-07-23 08:50:22 +02:00
  • a982995fb7 feat: Switch default layout model to DOCLING_LAYOUT_HERON. Update the unit test data. Nikos Livathinos 2025-07-22 17:30:16 +02:00
  • d32d2c97e1 chore: PR approval reminder (#2132) Michele Dolfi 2025-08-25 15:08:37 +02:00
  • 3f60a0fa78 feat: Upgrade to RapidOCR 3.x (#2088) geoHeil 2025-08-25 13:10:33 +03:00
  • 2aef5cf328 chore: bump version to 2.47.1 [skip ci] v2.47.1 github-actions[bot] 2025-08-23 14:11:33 +00:00
  • 488f6cdd2d fix: vllm extra only for linux x86_64 (#2126) Michele Dolfi 2025-08-23 13:33:15 +02:00
  • 6736e66bb4 style: show converted page count in PaginatedPipeline debug statement (#2124) Raphael Norman-Tenazas 2025-08-23 06:13:20 -04:00
  • b04e205d1e chore: bump version to 2.47.0 [skip ci] v2.47.0 github-actions[bot] 2025-08-22 14:15:39 +00:00
  • cdf079dd06 feat(CLI): Option to download arbitrary HuggingFace model (#2123) VIktor Kuropiantnyk 2025-08-22 15:23:29 +02:00
  • 449bde0a6c test: update docx reference results (#2122) Michele Dolfi 2025-08-22 14:26:36 +02:00
  • 3c660c0511 feat: batching support for VLMs in transformers backend, add initial VLLM backend (#2094) Christoph Auer 2025-08-22 13:17:33 +02:00
  • 3f03709885 fix: Improve numbered list detection for msword docs (#2100) Nikhil Verma 2025-08-22 14:08:34 +05:30
  • 94fcc46aa9 feat(html): Support formatting tags in HTML texts (#2111) krrome 2025-08-22 10:37:34 +02:00
  • e76298c40d docs: DPK pipeline example using docling library (#2112) Maroun Touma 2025-08-21 04:14:36 -04:00
  • cc66773890 draft for model and stages redesign adr-model-stages Michele Dolfi 2025-08-21 10:13:17 +02:00
  • 8996d612aa docs: add Getting Started page (#2113) Panos Vagenas 2025-08-21 08:44:53 +02:00
  • 555506d8e6 chore: bump version to 2.46.0 [skip ci] v2.46.0 github-actions[bot] 2025-08-20 15:25:07 +00:00
  • 76d2cb76b3 chore: update docling-core lock (#2110) Panos Vagenas 2025-08-20 16:41:48 +02:00
  • 684adc17df Add extra_processor_kwargs Christoph Auer 2025-08-20 14:19:50 +02:00
  • 5f57ff2a45 perf: Clean up resources with docling-parse v4, no parsed_page output by default (#2105) Christoph Auer 2025-08-20 10:46:31 +02:00
  • c5f2e2fdd6 fix(HTML): parse footer tag as a group in furniture content layer (#2106) Cesar Berrospi Ramis 2025-08-20 08:42:25 +02:00
  • 8820b5558b perf: speed up function _parse_orientation (#1934) mohammed ahmed 2025-08-19 11:55:18 +03:00
  • 956f82f115 chore: upgrade dependencies in lock file (#2093) Michele Dolfi 2025-08-19 10:11:44 +02:00
  • 6bbb8e6340 Add GoT OCR 2.0 Christoph Auer 2025-08-18 15:57:06 +02:00
  • b5b7e6dd5c Add GoT OCR 2.0 Christoph Auer 2025-08-18 15:57:06 +02:00
  • d2494da8b8 feat: new code formula model (#2042) Matteo 2025-08-18 16:01:46 +02:00
  • 4a107f4f57 Adjust example instatiation of multi-stage VLM pipeline Christoph Auer 2025-08-18 14:36:42 +02:00
  • 3d07f1c78e Cleanup hf_transformers_model batching impl Christoph Auer 2025-08-18 13:37:46 +02:00
  • c3a7d1d999 chore: bump version to 2.45.0 [skip ci] v2.45.0 github-actions[bot] 2025-08-18 10:25:51 +00:00
  • 31087f3fcc feat: add backend for METS with Google Books profile (#1989) Michele Dolfi 2025-08-18 11:43:20 +02:00
  • fead482e92 Merge from main, include decode_response Christoph Auer 2025-08-18 11:29:15 +02:00
  • e372cfe01a Small fixes Christoph Auer 2025-08-18 11:12:02 +02:00
  • 9687297262 feat(html): Support in-line anchor tags in HTML texts (#1659) krrome 2025-08-18 09:57:16 +02:00
  • 76c1fbd6e8 docs: Add docling Quarkus integration (#2083) Eric Deandrea 2025-08-18 00:55:51 -04:00
  • f42676aab9 Implement proper batch inference for HuggingFaceTransformersVlmModel Christoph Auer 2025-08-15 17:56:14 +02:00
  • 1aa522792a Tweak defaults Christoph Auer 2025-08-15 14:49:34 +02:00
  • 16fea9cd8b Add VLLM backend support, optimize process_images Christoph Auer 2025-08-15 13:18:02 +02:00
  • 18b1a43744 Fix KeyboardInterrupt behaviour Christoph Auer 2025-08-14 21:11:40 +02:00
  • 52b54b21c3 Remove prints Christoph Auer 2025-08-14 20:48:34 +02:00
  • c4de11bdb3 Add VLM task interpreters Christoph Auer 2025-08-14 20:48:10 +02:00
  • c8737f71da Add VLM task interpreters Christoph Auer 2025-08-14 20:44:23 +02:00
  • 78c13e1dad Add multithreaded VLM pipeline Christoph Auer 2025-08-13 14:54:23 +02:00
  • cffe1f0ae5 Adding feature to import drawingml objects in doclingdocument rtdl/drawingml_import Rafael Teixeira de Lima 2025-08-14 16:25:59 +02:00
  • 126944c7ee Prepare existing codes for use with new multi-stage VLM pipeline Christoph Auer 2025-08-13 14:02:19 +02:00
  • 5f050f94e1 feat(vlm): Ability to preprocess VLM response (#1907) Shkarupa Alex 2025-08-12 16:20:24 +03:00
  • ccfee05847 chore: bump version to 2.44.0 [skip ci] v2.44.0 github-actions[bot] 2025-08-12 09:51:35 +00:00
  • b09033cb73 feat: add convert_string to document-converter (#2069) Peter W. J. Staar 2025-08-12 11:02:38 +02:00
  • e2cca931be docs: add Langflow integration (#2068) Panos Vagenas 2025-08-11 17:03:29 +03:00
  • ed56f2de5d fix(html): Parse rawspan and colspan when they include non numerical values (#2048) Maroun Touma 2025-08-11 07:53:29 -04:00
  • bfda6d34d8 docs: Add Arconia integration (#2061) Thomas Vitale 2025-08-08 09:35:47 +02:00
  • c5f49dc2db chore: upgrade locked dependencies (#2024) Michele Dolfi 2025-07-31 16:05:27 +02:00
  • 0130e3ae96 fix: support new mlx-vlm module (#2001) TwoLeaves 2025-07-31 22:13:17 +10:00
  • 2eb760d060 fix: extend error reporting when verbose logging is enabled (#2017) Michele Dolfi 2025-07-30 11:23:26 +02:00
  • 86f70128aa fix(HTML): replace non-standard Unicode characters (#2006) Cesar Berrospi Ramis 2025-07-29 11:05:35 +02:00
  • aae42b37a8 chore: bump version to 2.43.0 [skip ci] v2.43.0 github-actions[bot] 2025-07-28 09:45:53 +00:00
  • aed772ab33 feat: Threaded PDF pipeline (#1951) Christoph Auer 2025-07-26 11:49:37 +02:00
  • aec29a7315 fix(markdown): ensure correct parsing of nested lists (#1995) Cesar Berrospi Ramis 2025-07-25 15:17:57 +02:00
  • 1985841a19 ci: Fixes for test GT (#1992) Christoph Auer 2025-07-25 12:28:06 +02:00
  • 945721a15d fix(HTML): remove an unnecessary print command (#1988) Cesar Berrospi Ramis 2025-07-25 08:45:15 +02:00
  • 8227841c1b chore: bump version to 2.42.2 [skip ci] v2.42.2 github-actions[bot] 2025-07-24 10:21:10 +00:00
  • 5132f061a8 fix(HTML): concatenation of child strings in table cells and list items (#1981) Cesar Berrospi Ramis 2025-07-24 11:19:25 +02:00
  • 7b5f86098d docs: add chat with dosu (#1984) Michele Dolfi 2025-07-24 11:07:36 +02:00
  • 0b83609531 fix(docx): Adding plain latex equations to table cells (#1986) Rafael Teixeira de Lima 2025-07-24 11:02:24 +02:00
  • 98e2fcff63 fix: Preserve PARTIAL_SUCCESS status when document timeout hits (#1975) Copilot 2025-07-23 13:50:40 +02:00
  • 8d50a59d48 fix: multi-page image support (tiff) (#1928) Copilot 2025-07-23 09:55:40 +02:00
  • ec971bbe68 chore: bump version to 2.42.1 [skip ci] v2.42.1 github-actions[bot] 2025-07-22 16:45:48 +00:00
  • 67441ca418 fix: Keep formula clusters also when empty (#1970) Christoph Auer 2025-07-22 17:02:12 +02:00
  • 90a7cc4bdd docs: enrich existing DoclingDocument (#1969) Michele Dolfi 2025-07-22 16:20:15 +02:00
  • a069b1175b refactor(HTML): handle text from styled html (#1960) Cesar Berrospi Ramis 2025-07-22 13:16:31 +02:00
  • 5d98bcea1b docs: add documentation for confidence scores (#1912) Fabiano Franz 2025-07-21 05:16:17 -03:00
  • 7561be537a chore: bump version to 2.42.0 [skip ci] v2.42.0 github-actions[bot] 2025-07-18 15:34:59 +00:00
  • cca05c45ea fix: Safe pipeline init, use device_map in transformers models (#1917) Christoph Auer 2025-07-18 15:14:36 +02:00
  • e1e3053695 fix: fix HTML table parser and JATS backend bugs (#1948) Cesar Berrospi Ramis 2025-07-16 10:49:24 +02:00
  • d6d2dbe2f9 docs: Fix typos (#1943) stephencox-ict 2025-07-15 19:51:56 +12:00
  • a436be7367 feat: Add option to control empty clusters in layout postprocessing (#1940) Christoph Auer 2025-07-14 18:32:01 +02:00
  • 95e70962f1 fix: KeyError: 'fPr' when processing latex fractions in DOCX files (#1926) Copilot 2025-07-11 09:52:14 +02:00
  • c5fb353f10 fix: Change granite vision model URL from preview to stable version (#1925) Copilot 2025-07-11 08:46:03 +02:00
  • 6c4bf9d087 chore: bump version to 2.41.0 [skip ci] v2.41.0 github-actions[bot] 2025-07-10 14:25:05 +00:00
  • f4c1836c96 functional working two-stage, need to implement a good prompt now to leverage bounding boxes dev/add-two-stage-vlm Peter Staar 2025-07-10 16:15:54 +02:00
  • b2d5c783ae working two-stage vlm approach from the cli Peter Staar 2025-07-10 15:38:15 +02:00
  • cc6193b3b9 test: Update tests to use default PDF backend (DPv4) (#1923) Christoph Auer 2025-07-10 15:16:56 +02:00
  • fb74d0c5b3 working TwoStageVlmModel Peter Staar 2025-07-10 15:11:53 +02:00
  • b2336830eb fixed the circular dependenciea Peter Staar 2025-07-10 10:35:47 +02:00
  • 70872e6539 merged with main and refactored the code to fix MyPy Peter Staar 2025-07-10 09:58:06 +02:00
  • e596143bf8 Merge branch 'main' into dev/add-two-stage-vlm Peter Staar 2025-07-10 06:52:31 +02:00
  • 0f395688b8 refactored the code and added vlm2stage as a cli option Peter Staar 2025-07-10 06:48:34 +02:00
  • 2b8616d6d5 feat: Layout model specification and multiple choices (#1910) Christoph Auer 2025-07-10 06:37:27 +02:00
  • ec588df971 feat: enable precision control in float serialization (#1914) Panos Vagenas 2025-07-09 16:39:17 +02:00
  • dcf6fd6a41 fixed the MyPy complaining Peter Staar 2025-07-09 06:48:03 +02:00
  • 931eb55b88 fix(ocr-utils): unit test and fix the rotate_bounding_box function (#1897) Clément Doumouro 2025-07-08 18:03:29 +02:00
  • c10e2920a4 refactoring redundant code and fixing mypy errors Peter Staar 2025-07-08 16:37:20 +02:00
  • b5479ab971 working on MyPy Peter Staar 2025-07-08 15:05:54 +02:00
  • 49e9a00c05 merged in layout-model-spec Peter Staar 2025-07-08 13:29:30 +02:00
  • 517230b9c4 Updated naming Christoph Auer 2025-07-08 13:07:56 +02:00
  • af0461e5b1 Move to pipeline_options.layout_options.model Christoph Auer 2025-07-08 11:24:06 +02:00
  • f2094f858b Establish layout_model spec and example instantations Christoph Auer 2025-07-08 10:23:18 +02:00
  • 810446c8dc feat: working on a two stage VLM model Peter Staar 2025-07-08 09:49:39 +02:00
  • 4eceefa47c feat: add TwoStageVlmModel Peter Staar 2025-07-08 07:38:48 +02:00
  • a07ba863c4 feat: add image-text-to-text models in transformers (#1772) geoHeil 2025-07-08 05:54:57 +02:00