Commit Graph

Select branches

Hide Pull Requests

add-json-export-indentation

cau/dpv4-test-updates

cau/new-layout-processing

cau/pin-docling-parse-pre-3.2

cau/test-dp-word-lines

cau/test-pypdfium2-beta

cp_main_20250602

demo

dev/add-asr-pipeline

dev/add-granite-docling-preview

dev/add-r2l-tests

dev/add-reading-order-model

dev/add-two-stage-vlm

dev/doctag_backend

dev/fix_msword_backend_identify_text_after_image

dev/table-orientation

dev/update-html-parser-with-h1

extend-metadata-in-examples

feat-books-ocr

fix-print-raw-table

gh-pages

main

mao/doctags

mao1/code_formula_v1.0.1

mly/smol-docling-integration

nli/fix_glm_utils

nli/fix_ocr_tests

nli/layout_dfine

nli/layout_heron

nli/layout_rtdetr_v2

nli/layoutmodel_improvements

nli/tesseract_ocr_models

propagate-core-fixes-20250502

remodel-lists-2

revert-803-refactor_viz

rtdl/docx_latex

test-core-relative-exports

#1

#10

#100

#101

#1010

#1015

#1017

#102

#1021

#1024

#1027

#103

#1038

#1039

#1040

#1041

#1051

#1052

#1053

#1054

#1055

#1057

#1061

#1062

#1077

#1096

#1097

#1098

#11

#110

#1100

#1106

#1107

#111

#1114

#1115

#1118

#1124

#1130

#1140

#1141

#1147

#1150

#1152

#1154

#1156

#1158

#1160

#1165

#1167

#117

#1173

#118

#1182

#1183

#1194

#1196

#1197

#1199

#12

#120

#1201

#121

#1210

#122

#1220

#1222

#1223

#123

#1231

#1238

#1239

#1241

#1244

#1247

#1248

#1261

#1263

#1263

#1268

#1270

#1286

#129

#1294

#1295

#13

#131

#1313

#1315

#1316

#1319

#132

#1320

#1326

#1328

#1328

#1332

#1334

#1337

#134

#1340

#1346

#135

#1350

#1355

#1359

#1363

#1371

#1375

#1377

#1378

#1379

#138

#1381

#1382

#1383

#1389

#139

#1392

#1399

#14

#140

#1400

#1402

#1402

#141

#1411

#1415

#1416

#1419

#1427

#1428

#1428

#143

#1430

#1436

#1442

#1449

#145

#1458

#1459

#1463

#1465

#1486

#1486

#149

#1490

#1492

#1494

#1496

#15

#150

#1500

#151

#1511

#1512

#152

#1520

#1523

#1524

#1525

#1526

#1527

#1528

#153

#1530

#1536

#1538

#154

#1548

#1549

#155

#1551

#1553

#1556

#1559

#156

#1560

#1561

#1563

#1566

#157

#1570

#1576

#1577

#158

#1582

#1583

#1587

#1587

#1589

#159

#1593

#1596

#16

#160

#1600

#1609

#161

#1610

#1615

#1617

#1619

#162

#1636

#164

#1658

#1658

#1659

#1659

#1660

#1663

#1664

#1665

#1667

#1671

#1673

#1676

#1679

#168

#1683

#1684

#1688

#1689

#169

#1691

#1698

#17

#170

#1700

#1701

#1706

#1707

#171

#1711

#1717

#1718

#1723

#1724

#1725

#1728

#173

#1734

#1735

#1745

#1746

#1747

#175

#1759

#1763

#1769

#177

#1772

#1775

#1775

#178

#179

#1791

#1795

#18

#180

#1802

#1804

#1808

#1810

#1812

#1815

#1815

#1816

#1819

#182

#1820

#1821

#1824

#1824

#1825

#1827

#183

#1836

#1838

#184

#1844

#1850

#1851

#1852

#1856

#1857

#186

#1863

#1866

#1867

#187

#1870

#1874

#1875

#1876

#1876

#188

#1884

#189

#1897

#1898

#1898

#19

#190

#1902

#1904

#1905

#1907

#1907

#1908

#1908

#1910

#1912

#1914

#1917

#1923

#1925

#1926

#1928

#193

#1931

#1934

#1934

#1937

#1937

#194

#1940

#1943

#1948

#1951

#1952

#1952

#196

#1960

#1969

#1970

#1971

#1971

#1975

#1981

#1982

#1982

#1984

#1986

#1988

#1989

#1989

#1992

#1995

#2

#20

#2001

#2001

#2002

#2002

#2006

#2011

#2011

#2017

#2018

#2018

#203

#21

#214

#217

#217

#218

#218

#219

#22

#224

#226

#228

#229

#233

#234

#235

#240

#241

#248

#251

#259

#26

#27

#275

#276

#279

#28

#282

#286

#29

#290

#3

#302

#305

#307

#31

#310

#312

#314

#315

#316

#319

#32

#320

#322

#323

#325

#33

#330

#332

#334

#339

#34

#340

#341

#349

#35

#350

#36

#37

#371

#374

#375

#378

#379

#38

#384

#388

#39

#392

#393

#396

#4

#40

#401

#407

#408

#409

#415

#416

#42

#429

#43

#430

#432

#44

#442

#449

#45

#451

#456

#457

#46

#466

#467

#468

#47

#472

#474

#475

#482

#484

#487

#49

#490

#492

#495

#496

#497

#5

#50

#500

#501

#502

#504

#51

#511

#512

#513

#514

#517

#52

#528

#53

#530

#531

#532

#533

#534

#537

#54

#544

#549

#550

#551

#552

#555

#556

#557

#558

#56

#569

#57

#58

#59

#593

#6

#604

#606

#608

#613

#615

#616

#618

#624

#628

#63

#630

#631

#633

#642

#65

#650

#655

#656

#662

#675

#679

#68

#69

#691

#693

#694

#695

#697

#698

#7

#70

#700

#701

#702

#708

#71

#716

#717

#718

#719

#72

#733

#735

#739

#742

#75

#752

#759

#769

#772

#777

#783

#786

#788

#79

#793

#8

#80

#800

#801

#803

#804

#805

#808

#81

#811

#814

#815

#816

#817

#818

#819

#82

#820

#821

#824

#825

#826

#827

#83

#830

#831

#832

#837

#839

#84

#841

#842

#843

#850

#852

#853

#854

#855

#856

#857

#86

#862

#868

#869

#872

#873

#874

#875

#876

#878

#88

#880

#881

#883

#896

#897

#90

#901

#903

#905

#91

#910

#912

#916

#919

#92

#929

#93

#932

#935

#940

#941

#945

#948

#949

#95

#951

#958

#96

#965

#966

#967

#98

#99

#999

v0.1.1

v0.2.0

v0.3.0

v0.3.1

v0.4.0

v1.0.0

v1.0.1

v1.0.2

v1.1.0

v1.1.1

v1.1.2

v1.10.0

v1.11.0

v1.12.0

v1.12.1

v1.12.2

v1.13.0

v1.13.1

v1.14.0

v1.15.0

v1.16.0

v1.16.1

v1.17.0

v1.18.0

v1.19.0

v1.19.1

v1.2.0

v1.2.1

v1.20.0

v1.3.0

v1.4.0

v1.5.0

v1.6.0

v1.6.1

v1.6.2

v1.6.3

v1.7.0

v1.7.1

v1.8.0

v1.8.1

v1.8.2

v1.8.3

v1.8.4

v1.8.5

v1.9.0

v2.0.0

v2.1.0

v2.10.0

v2.11.0

v2.12.0

v2.13.0

v2.14.0

v2.15.0

v2.15.1

v2.16.0

v2.17.0

v2.18.0

v2.19.0

v2.2.0

v2.2.1

v2.20.0

v2.21.0

v2.22.0

v2.23.0

v2.23.1

v2.24.0

v2.25.0

v2.25.1

v2.25.2

v2.26.0

v2.27.0

v2.28.0

v2.28.1

v2.28.2

v2.28.3

v2.28.4

v2.29.0

v2.3.0

v2.3.1

v2.30.0

v2.31.0

v2.31.1

v2.31.2

v2.32.0

v2.33.0

v2.34.0

v2.35.0

v2.36.0

v2.36.1

v2.37.0

v2.38.0

v2.38.1

v2.39.0

v2.4.0

v2.4.1

v2.4.2

v2.40.0

v2.41.0

v2.42.0

v2.42.1

v2.42.2

v2.43.0

v2.5.0

v2.5.1

v2.5.2

v2.6.0

v2.7.0

v2.7.1

v2.8.0

v2.8.1

v2.8.2

v2.8.3

v2.9.0

Mono Color

• 249715a463 use different cache key in each job Michele Dolfi 2025-03-02 16:57:16 -0500
• 9e30fca4c0 more timeout Michele Dolfi 2025-03-02 16:14:39 -0500
• b3dbfad00a increase hf timeout Michele Dolfi 2025-03-02 15:55:59 -0500
• 74916565de warning for develop examples Michele Dolfi 2025-03-02 15:44:55 -0500
• 87d849792d use gh cache for huggingface models Michele Dolfi 2025-03-02 15:32:19 -0500
• 8dc0562542
  fix: enable locks for threadsafe pdfium (#1052) Michele Dolfi 2025-03-02 20:06:44 +0100
• e25d557c06
  refactor: add the contentlayer to html-backend (#1040) Peter W. J. Staar 2025-03-02 10:37:53 -0500
• b3cf5d4471 Merge remote-tracking branch 'origin/main' into fix-threadsafe-pypdfium Michele Dolfi 2025-03-02 09:58:27 -0500
• 346a49c283 fix deadlock in pypdfium2 backend Michele Dolfi 2025-03-02 09:58:06 -0500
• 3ea31b6111 chore: set TextItem label to 'text' instead of 'paragraph' Cesar Berrospi Ramis 2025-03-01 11:27:03 -0300
• 38d622f22c refactor(html): put parsed item in body if doc has no header Cesar Berrospi Ramis 2025-02-28 18:03:58 +0100
• 70e6b942e1 test(html): add more info if a test case fails Cesar Berrospi Ramis 2025-02-28 16:05:43 +0100
• 0cba30e254 reformatted code of html backend Peter Staar 2025-02-24 09:29:06 +0100
• e5e00674e1 updated the handle_image function Peter Staar 2025-02-24 09:26:30 +0100
• 252bd83066 added the contentlayer to html-backend Peter Staar 2025-02-23 07:01:18 +0100
• db3ceefd4a
  docs: improve docs on token limit warning triggered by HybridChunker (#1077) Panos Vagenas 2025-02-28 14:54:46 +0100
• 0426e4d682 docs: improve docs on token limit warning triggered by HybridChunker Panos Vagenas 2025-02-28 13:28:30 +0100
• de7b963b09
  fix(html): use 'start' attribute when parsing ordered lists from HTML docs (#1062) Cesar Berrospi Ramis 2025-02-27 09:46:57 +0100
• 252c185ae0 chore(html): reduce verbosity in HTML backend Cesar Berrospi Ramis 2025-02-26 15:50:12 +0100
• 413f6e8a88 fix(html): use 'start' attribute in ordered lists Cesar Berrospi Ramis 2025-02-26 15:47:12 +0100
• 37dd8c1cc7 chore: bump version to 2.25.0 [skip ci] v2.25.0 github-actions[bot] 2025-02-26 14:16:15 +0000
• 3c9fe76b70
  feat: [Experimental] Introduce VLM pipeline using HF AutoModelForVision2Seq, featuring SmolDocling model (#1054) Christoph Auer 2025-02-26 14:43:26 +0100
• 483d1bfab0 fix: add proper table provenance Christoph Auer 2025-02-26 14:02:22 +0100
• ab683e4fb6
  feat(cli): add option for downloading all models, refine help messages (#1061) Panos Vagenas 2025-02-26 13:27:29 +0100
• abd714b64b add --all flag to model download CLI Panos Vagenas 2025-02-26 13:00:49 +0100
• b88440a7c9 chore: fix leftover .to(device) Christoph Auer 2025-02-26 12:53:43 +0100
• 5cd0fdd258 chore: more cleanup Christoph Auer 2025-02-26 12:48:14 +0100
• c5873f2496 chore: clean up code and comments Christoph Auer 2025-02-26 12:46:41 +0100
• 34393e51a2 make options an explicit kwarg Panos Vagenas 2025-02-26 11:44:06 +0100
• 560164f613
  chore(cli): update download help messages Panos Vagenas 2025-02-26 11:32:39 +0100
• f994654918 Make drawing code resilient against bad bboxes Christoph Auer 2025-02-26 11:01:11 +0100
• e197225739
  fix: vlm using artifacts path (#1057) Michele Dolfi 2025-02-26 08:33:50 +0100
• d269c8596c Add back device_map and accelerate Christoph Auer 2025-02-25 19:19:23 +0100
• a6d406764a Fix VLM example exclusion in CI Christoph Auer 2025-02-25 16:00:39 +0100
• 10f64a948c Expose control over using flash_attention_2 Christoph Auer 2025-02-25 15:31:32 +0100
• 1553a125dc switch to create methods Panos Vagenas 2025-02-25 14:43:15 +0100
• b85caac0ec add granite vision to the download utils Michele Dolfi 2025-02-25 14:25:28 +0100
• 96d9fe19cd fix usage of artifacts path Michele Dolfi 2025-02-25 14:09:14 +0100
• eec896631e revert blacklist João 2025-02-25 10:05:56 -0300
• 84c77c9fcb Move imports Christoph Auer 2025-02-25 14:03:28 +0100
• 341806e54b Rename example Christoph Auer 2025-02-25 13:43:05 +0100
• 1cba96ecfd Generalize and refactor VLM pipeline and models Christoph Auer 2025-02-25 13:38:44 +0100
• c84b973959
  docs: extend chunking docs, add FAQ on token limit (#1053) Panos Vagenas 2025-02-25 13:07:38 +0100
• ecb3895f9a docs: extend chunking docs, add FAQ on token limit Panos Vagenas 2025-02-25 12:30:26 +0100
• 762a511d0a enable locks for threadsafe pdfium Michele Dolfi 2025-02-25 11:15:43 +0100
• 45b8cb7060
  small changes Navanit Dubey 2025-02-25 15:00:26 +0530
• 27fec3de6c
  Feature to use local vlm model too Navanit Dubey 2025-02-25 14:47:30 +0530
• 1c75b52f85 re-built poetry.lock mly/smol-docling-integration Maksym Lysak 2025-02-24 17:37:35 +0100
• 9ecec1d330 Updated poetry.lock Maksym Lysak 2025-02-24 17:27:50 +0100
• 923f766ada Replaced remaining strings to appropriate enums Maksym Lysak 2025-02-24 16:54:59 +0100
• a095a7c5b7 removing changes from base_pipeline Maksym Lysak 2025-02-24 15:13:59 +0100
• a7a1f32b10 Added example on how to get original predicted doctags in minimal_smol_docling Maksym Lysak 2025-02-24 14:39:18 +0100
• 1dbedcbb4e removed pipeline_options.generate_table_images from vlm_pipeline (deprecated in the pipelines) Maksym Lysak 2025-02-24 14:17:06 +0100
• 0c60ef199a Moved keep_backend = True to vlm pipeline Maksym Lysak 2025-02-13 17:53:03 +0100
• 853544ba11 Addressing PR comments, added enabled property to SmolDocling, and related VLM pipeline option, few other minor things Maksym Lysak 2025-02-13 17:19:53 +0100
• b0935daec4 Removed special html code wrapping when exporting to docling document, cleaned up comments Maksym Lysak 2025-02-13 10:29:37 +0100
• b12f5ba80f removed minimal_smol_docling example from CI checks Maksym Lysak 2025-02-13 09:42:45 +0100
• 66532eadb6 More elegant solution in removing the input prompt Maksym Lysak 2025-02-12 18:48:48 +0100
• e486eb1720 Cleaned up unnecessary logging Maksym Lysak 2025-02-12 17:56:37 +0100
• 55fa4eb4e3 Fix repo id Christoph Auer 2025-02-12 17:09:56 +0100
• 6f9f4f4aee Update minimal smoldocling example Christoph Auer 2025-02-12 17:07:00 +0100
• b1df461ca8 Added captions for the images for SmolDocling assembly code, improved provenance definition for all elements Maksym Lysak 2025-02-11 16:42:23 +0100
• d7abe1b1cd Updated example of Smol Docling usage Maksym Lysak 2025-02-11 13:53:19 +0100
• 479ee239aa New assembly code for latest model revision, updated prompt and parsing of doctags, updated logging Maksym Lysak 2025-02-11 13:34:14 +0100
• 7c4ab5c716 Moved artifacts_path for SmolDocling into vlm_options instead of global pipeline option Maksym Lysak 2025-01-21 18:00:05 +0100
• f2751e11f9 Introduced SmolDoclingOptions to configure model parameters (such as query and artifacts path) via client code, see example in minimal_smol_docling. Provisioning for other potential vlm all-in-one models. Maksym Lysak 2025-01-21 17:37:11 +0100
• 88b9ac6706 Fixing doctags starting tag, that broke elements on first line during assembly Maksym Lysak 2025-01-21 11:14:55 +0100
• 0fe12d819a Updated vlm pipeline assembly and smol docling model code to support updated doctags Maksym Lysak 2025-01-17 17:54:55 +0100
• f6d123a01c Flipped keep_backend to True for vlm_pipeline assembly to work Maksym Lysak 2025-01-16 16:51:27 +0100
• 9901729d8c Exposed "force_backend_text" as pipeline parameter Maksym Lysak 2025-01-16 14:23:59 +0100
• c687757c7c
  Merge pull request #7 from 0xCarbon/sync/upstream_24022025 jpcanesin 2025-02-24 09:00:50 -0300
• 9223023d13 Merge branch 'main' of github.com:DS4SD/docling into sync/upstream_24022025 João 2025-02-24 08:58:40 -0300
• 0dc3ac43b1 Added capability for vlm_pipeline to grab text from preconfigured backend Maksym Lysak 2025-01-16 10:44:49 +0100
• e0929781f4 Added tokens/sec measurement, improved example Maksym Lysak 2025-01-15 10:22:48 +0100
• 437053572d Replaced hardcoded otsl tokens with the ones from docling-core tokens.py enum Maksym Lysak 2025-01-14 16:07:37 +0100
• 2a43c199d5 Cleaned up logs, added pages to vlm_pipeline, basic timing per page measurement in smol_docling models Maksym Lysak 2025-01-14 14:04:47 +0100
• 61bb9dbba2 Properly propagating image data per page, together with predicted tags in VLM pipeline. This enables correct figure extraction and page numbers in provenances Maksym Lysak 2025-01-13 15:21:19 +0100
• 01c46e24b1 Fix for table span compute in vlm_pipeline Maksym Lysak 2025-01-10 16:30:12 +0100
• ef079e4e78 Enabled figure support in vlm_pipeline Maksym Lysak 2025-01-10 13:56:46 +0100
• 1b968e4984 Fixes to preserve page image and demo export to html Maksym Lysak 2025-01-10 10:50:35 +0100
• 3c4c647615 WIP, first working code for inference of SmolDocling, and vlm pipeline assembly code, example included. Maksym Lysak 2025-01-09 18:41:00 +0100
• 03c8d45790 wip smolDocling inference and vlm pipeline Maksym Lysak 2025-01-09 14:43:04 +0100
• 3844f2a5cb fix enable option Michele Dolfi 2025-02-24 12:53:46 +0100
• 1b0ead6907
  fix(html): Parse text in div elements as TextItem (#1041) Cesar Berrospi Ramis 2025-02-24 12:38:29 +0100
• dc3a388aa2 Skeleton for SmolDocling model and VLM Pipeline Christoph Auer 2025-01-08 10:16:54 +0100
• 3b9b675a4f add picture description factory Michele Dolfi 2025-02-24 11:13:14 +0100
• 8235a246c8 Merge remote-tracking branch 'origin/main' into feat-factory-plugins Michele Dolfi 2025-02-24 08:26:05 +0100
• 1d17e7397a
  test: avoid testing exact JSON in CSV backend (#1038) Suehtam 2025-02-24 07:10:40 +0000
• ca5d44ffe4 feat(html): Parse text in div elements as TextItem Cesar Berrospi Ramis 2025-02-23 19:53:31 +0100
• c075d8d765 fix: Improve markdown list parser Tobias Strebitzer 2025-02-23 13:35:37 +0800
• 1ea502ebd8
  feat: replace verify_export with verify_document in CSV conversion tests Matheus Abdias 2025-02-23 00:50:17 +0000
• 53451d18d6
  feat: updated verify_export Moved verify_export to verify_utils Reuse verify_export in tests Matheus Abdias 2025-02-23 00:39:42 +0000
• d8a81c3168 chore: bump version to 2.24.0 [skip ci] v2.24.0 github-actions[bot] 2025-02-20 18:31:20 +0000
• c93e36988f
  feat: Implement new reading-order model (#916) Christoph Auer 2025-02-20 17:51:17 +0100
• c031a7ae47 chore: bump version to 2.23.1 [skip ci] v2.23.1 github-actions[bot] 2025-02-20 16:26:41 +0000
• 3cdf1e5f8c chore: Delete empty file docling/models/ds_glm_model.py Nikos Livathinos 2025-02-20 17:17:30 +0100
• 1ac010354f
  test: avoid testing exact JSON (#1027) Cesar Berrospi Ramis 2025-02-20 16:20:07 +0100
• 6796f0a132
  fix: Runtime error when Pandas Series is not always of string type (#1024) fanszoro 2025-02-20 22:41:41 +0800
• 50979e4304 Fix content_layer assignment Christoph Auer 2025-02-20 14:33:56 +0100
• c686bc9908
  Update tests/test_backend_patent_uspto.py Cesar Berrospi Ramis 2025-02-20 14:23:56 +0100