mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity
530 Commits 36 Branches 112 Tags 287 MiB
0cb7520648
Commit Graph

530 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Michele Dolfi
0cb7520648 restore stable imports 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-06-01 09:06:41 +02:00
Peter Staar
a4e6777bb3 fixed the merge conflicts 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-23 16:30:18 +02:00
github-actions[bot]
2579d89510 chore: bump version to 2.34.0 [skip ci] 2025-05-22 18:44:45 +00:00
Said Gürbüz
c2f595d283
fix: fix ZeroDivisionError for cell_bbox.area() (#1636) 
fix ZeroDivisionError for cell_bbox.area()

Signed-off-by: Saidgurbuz <said.gurbuz@epfl.ch>
 2025-05-22 13:43:33 +02:00
Clément Doumouro
45265bf8b1
feat(ocr): auto-detect rotated pages in Tesseract (#1167) 
* fix(ocr): tesseract support mis-oriented documents

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): update missing test data

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): rotate image to the natural orientation before layout prediction

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): move bounding bow rotation util to orientation.py

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): refactor rotation utilities

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): revert layout updates

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): update e2e OCR test data

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): avoid to swallow tesseract errors causing orientation detection failures

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): revert layout updates

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): update e2e OCR test data

* chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrCliModel`

* chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrModel`

* chore(ocr): default `TesseractOcrCliModel._is_auto` to `False`

* fix(ocr): fix `TesseractOcrCliModel._is_auto` computation

* chore(ocr): improve logging in case of OSD failure in `TesseractOcrCliModel` and `TesseractOcrModel`

---------

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>
 2025-05-21 18:12:33 +02:00
Christoph Auer
90875247e5
feat: Establish confidence estimation for document and pages (#1313) 
* Establish confidence field, propagate layout confidence through

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add OCR confidence and parse confidence (stub)

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add parse quality rules, use 5% percentile for overall and parse scores

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Heuristic updates

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix garbage regex

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Move grade to page

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Introduce mean_score and low_score, consistent aggregate computations

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add confidence test

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
 2025-05-21 12:32:49 +02:00
Václav Vančura
14d4f5b109
fix(integration): update the Apify Actor integration (#1619) 
* fix(actor): remove references to missing docling_processor.py

Signed-off-by: Václav Vančura <commit@vancura.dev>

* chore(actor): update Actor README.md with recent repo URL changes

Signed-off-by: Václav Vančura <commit@vancura.dev>

* chore(actor): improve the Actor README.md local header link

Signed-off-by: Václav Vančura <commit@vancura.dev>

* chore(actor): bump the Actor version number

Signed-off-by: Václav Vančura <commit@vancura.dev>

* Update .actor/actor.json

Co-authored-by: Marek Trunkát <marek@trunkat.eu>
Signed-off-by: Jan Čurn <jan.curn@gmail.com>

---------

Signed-off-by: Václav Vančura <commit@vancura.dev>
Signed-off-by: Jan Čurn <jan.curn@gmail.com>
Co-authored-by: Jan Čurn <jan.curn@gmail.com>
Co-authored-by: Marek Trunkát <marek@trunkat.eu>
 2025-05-21 02:47:55 +02:00
github-actions[bot]
84d0889829 chore: bump version to 2.33.0 [skip ci] 2025-05-20 19:54:51 +00:00
MoheyElDin Badr
f4d9d4111b
fix: Fix issue with detecting docx files, and files with upper case extensions (#1609) 
fix detecting files with uppercase extensions

Signed-off-by: MoheyElDin Badr <moheyeldin.badr@gmail.com>
 2025-05-20 19:42:37 +02:00
Said Gürbüz
0e00a263fa
fix: load_from_doctags static usage (#1617) 
* fix load_from_doctags usage

Signed-off-by: Saidgurbuz <said.gurbuz@epfl.ch>

* update dependencies

Signed-off-by: Saidgurbuz <said.gurbuz@epfl.ch>

* fix lock file

Signed-off-by: Saidgurbuz <said.gurbuz@epfl.ch>

* revert lock file

Signed-off-by: Saidgurbuz <said.gurbuz@epfl.ch>

* update lock file

Signed-off-by: Saidgurbuz <said.gurbuz@epfl.ch>

---------

Signed-off-by: Saidgurbuz <said.gurbuz@epfl.ch>
 2025-05-20 15:06:12 +02:00
Krishnan
f2e9c0784c
fix: incorrect force_backend_text behaviour for VLM DocTag pipelines (#1371) 
* Fix force_backend_text

Signed-off-by: Krishnan Raghavan <krishnanraghavan@Krishnans-MacBook-Air.local>

* empty commit to retrigger CI

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

---------

Signed-off-by: Krishnan Raghavan <krishnanraghavan@Krishnans-MacBook-Air.local>
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
Co-authored-by: Krishnan Raghavan <krishnanraghavan@Krishnans-MacBook-Air.local>
Co-authored-by: Panos Vagenas <pva@zurich.ibm.com>
 2025-05-20 09:59:38 +02:00
Pedro Ribeiro
98b5eeb844
fix(pypdfium): resolve overlapping text when merging bounding boxes (#1549) 
get merged_text from boundingbox instead of merging it to prevent overlaps

Signed-off-by: Pedro Ribeiro <pedro_ribeiro_93@hotmail.com>
 2025-05-19 15:26:00 +02:00
AndrewTsai0406
12a0e64892
feat: add textbox content extraction in msword_backend (#1538) 
* feat: add textbox content extraction in msword_backend

Signed-off-by: Andrew <tsai247365@gmail.com>

* feat: add textbox content extraction in msword_backend

Signed-off-by: Andrew <tsai247365@gmail.com>

* feat: add textbox content extraction in msword_backend

Signed-off-by: Andrew <tsai247365@gmail.com>

---------

Signed-off-by: Andrew <tsai247365@gmail.com>
 2025-05-19 15:01:36 +02:00
Peter Staar
374ecd4890 fixed the static load_from_doctags 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-18 10:58:39 +02:00
Peter Staar
1ada7bfee7 added the html backend to the VLM pipeline 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-18 10:55:27 +02:00
Peter Staar
e93cc3ce09 fixing the tests 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-18 07:38:06 +02:00
Peter Staar
0c7c7c11c2 reformatted the code 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-16 16:31:11 +02:00
Peter Staar
d5b6c871cf streamlining all code 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-16 16:27:27 +02:00
Peter Staar
661f7c9780 fixed the pipeline for Phi4 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-16 15:55:49 +02:00
Peter Staar
d41b856961 finalising last points for vlms support 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-16 12:39:26 +02:00
Panos Vagenas
7c4c356e76
chore: fix chunking example data link (#1596) 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
 2025-05-16 08:44:47 +02:00
Peter Staar
fc61258273 merged with main 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-15 07:46:06 +02:00
Peter Staar
e2c95d09bc need to get Phi4 working again ... 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-15 07:32:55 +02:00
Peter Staar
15a8f328c2 added pipeline_model_specializations file 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-15 05:27:16 +02:00
Peter Staar
7c67d2b2fe fixed the MyPy 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-14 17:51:43 +02:00
github-actions[bot]
aeb0716bbb chore: bump version to 2.32.0 [skip ci] 2025-05-14 14:28:21 +00:00
Vinay R Damodaran
3a04f2a367
feat: Improve parallelization for remote services API calls (#1548) 
* Provide the option to make remote services call concurrent

Signed-off-by: Vinay Damodaran <vrdn@hey.com>

* Use yield from correctly?

Signed-off-by: Vinay Damodaran <vrdn@hey.com>

* not do amateur hour stuff

Signed-off-by: Vinay Damodaran <vrdn@hey.com>

---------

Signed-off-by: Vinay Damodaran <vrdn@hey.com>
 2025-05-14 15:47:55 +02:00
jimkarag02
9f8b479f17
fix(ocr): orig field in TesseractOcrCliModel as str (#1553) 
fix: ensure orig and text are both strings in TesseractOcrCliModel

Signed-off-by: Dimitris Karagatslis <dimo9.dk@gmail.com>
 2025-05-14 15:05:52 +02:00
Panos Vagenas
9f28abf061
docs: add advanced chunking & serialization example (#1589) 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
 2025-05-14 14:35:07 +02:00
Peter Staar
a3716b1961 refactoring minimal_vlm_pipeline 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-14 13:57:32 +02:00
Alex Sokolov
2efb7a7c06
fix(settings): fix nested settings load via environment variables (#1551) 
Signed-off-by: Alexander Sokolov <alsokoloff@gmail.com>
 2025-05-14 13:42:10 +02:00
Peter Staar
7c97b494ec added the VlmPredictionToken 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-14 12:23:46 +02:00
Elwin
12dab0a1e8
feat: support image/webp file type (#1415) 
* support image/webp file type

Signed-off-by: Elwin <61868295+hzhaoy@users.noreply.github.com>
Signed-off-by: Elwin <hzywong@gmail.com>

* docs: add webp image format in supported_formats.md

Signed-off-by: Elwin <61868295+hzhaoy@users.noreply.github.com>
Signed-off-by: Elwin <hzywong@gmail.com>

* test: add a test case for `image/webp` file

Signed-off-by: Elwin <hzywong@gmail.com>

* style: apply styling

Signed-off-by: Elwin <hzywong@gmail.com>

* test: update test case of converting `image/webp` file with more ocr engines

Signed-off-by: Elwin <hzywong@gmail.com>

* style: apply styling

Signed-off-by: Elwin <hzywong@gmail.com>

* rename test file

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Elwin <61868295+hzhaoy@users.noreply.github.com>
Signed-off-by: Elwin <hzywong@gmail.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-05-14 09:47:28 +02:00
Peter Staar
f159075b67 pixtral 12b runs via MLX and native transformers 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-14 07:39:20 +02:00
Peter Staar
054e01d8b3 added the formulate_prompt 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-14 06:26:16 +02:00
Peter Staar
4c0bc61e54 refactoring the download_model 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-14 05:31:54 +02:00
Peter Staar
3407955a47 all working, now serious refacgtoring necessary 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-13 18:23:55 +02:00
github-actions[bot]
23238c241f chore: bump version to 2.31.2 [skip ci] 2025-05-13 10:09:19 +00:00
Marco Fargetta
4046d0b2f3
fix: AsciiDoc header identification (#1562) (#1563) 
Fix regular expression to identify header lines in AsciiDoc avoiding to
match defined blocks.

Signed-off-by: Marco Fargetta <mfargett@redhat.com>
 2025-05-13 11:17:26 +02:00
Michele Dolfi
8baa85a49d
fix: restrict click version and update lock file (#1582) 
* fix click dependency and update lock file

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
 2025-05-13 10:40:08 +02:00
Peter Staar
96862bd326 refactoring the VLM part 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-13 10:01:37 +02:00
Peter Staar
ee01e3cff0 Merge branch 'main' into dev/add-other-vlm-models 2025-05-13 06:08:26 +02:00
Peter Staar
7fbe021359 working on vlm's 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-13 06:07:11 +02:00
Peter Staar
77eb21b235 got microsoft/Phi-4-multimodal-instruct to work 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-12 13:37:03 +02:00
Peter Staar
68747e3cad fixed the transformers 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-12 13:08:33 +02:00
github-actions[bot]
0d0fa6cbe3 chore: bump version to 2.31.1 [skip ci] 2025-05-12 09:44:26 +00:00
Michele Dolfi
127e38646f
fix: add smoldocling in download utils (#1577) 
add smoldocling in download utils

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-05-12 10:48:07 +02:00
Peter Staar
bd2d01f0ac Merge branch 'main' into dev/add-other-vlm-models 2025-05-12 08:52:52 +02:00
Oleg Lavrovsky
844babb390
docs: update links in data_prep_kit (#1559) 
Update data_prep_kit.md

The links were broken, since the repository was renamed. I also noticed that PDF2Parquet is now referred to as Docling2Parquet.

Signed-off-by: Oleg Lavrovsky <31819+loleg@users.noreply.github.com>
 2025-05-11 20:38:25 +02:00
Peter Staar
18e1ec4df2 feat: adding new vlm-models support 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-05-11 09:30:10 +02:00