mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 12:34:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
162 Commits 36 Branches 112 Tags 287 MiB
800b16beff
Commit Graph

162 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Michele Dolfi
800b16beff keep only one example 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-08 18:36:53 +02:00
Nikos Livathinos
bb8cd0f7fc fix: Rename the tesseract OCR related classes and filenames 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 16:46:25 +02:00
Nikos Livathinos
70a8a2cc82 chore(OCR): Rename class names to use Tesseract for the tesserocr and TesseractCLI for the tesseract process 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 14:44:23 +02:00
Nikos Livathinos
074acd703c feat(OCR): Introduce support for the language path in the pipelines of both Tesseract OCR engines. 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 14:30:47 +02:00
Nikos Livathinos
118afee1f3 fix(TesserOcrModel): Fix cell coordinates 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 14:30:47 +02:00
Nikos Livathinos
29e65e911b fix(test): Introduce parameter in verify_conversion_result() to allow skipping the verification of the cells. It is used in case of OCR tests. 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 14:30:33 +02:00
Nikos Livathinos
072aaf6bb1 fix(test): Update test data for OCR 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 14:30:18 +02:00
Michele Dolfi
5bd64779d1 add docs for TESSDATA_PREFIX 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-08 11:37:24 +02:00
Michele Dolfi
ea3f720ef5 remove pydantic warning for model_ 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-08 11:32:54 +02:00
Michele Dolfi
67746044a9 Merge remote-tracking branch 'origin/main' into feat-multiple-ocr-engines 2024-10-08 10:55:08 +02:00
Michele Dolfi
73108d597c docs: explain OCR options 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-08 10:54:43 +02:00
Fasal Shah
d412c363d7
fixed unload pdf backend resources (#129) 
Signed-off-by: faisal shah <fashah@redhat.com>
Co-authored-by: faisal shah <fashah@redhat.com>
 2024-10-08 10:46:43 +02:00
Michele Dolfi
471daee277 reorder sections in custom_convert 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-08 09:53:52 +02:00
Nikos Livathinos
8ec8c38de8 fix(CI/CD): Use the eng language package location to set the TESSDATA_PREFIX envvar 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 07:08:51 +02:00
Nikos Livathinos
be6489bde0 fix(tests): Refactor the data_scanned with a very simple document that allows all OCR engines to produce the same result. 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-08 07:07:28 +02:00
Michele Dolfi
7532ede7f4 fix tessdata env 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-07 18:35:18 +02:00
Nikos Livathinos
bd1837f2f6 fix(CI/CD): Add envvar TESSDATA_PREFIX in the checks.yml to ensure that tesseract has the proper path for the language models. 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-07 17:26:58 +02:00
Nikos Livathinos
6faff146e0 fix(OCR): Skip zero area OCR cells for all OCR engines 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-07 17:26:58 +02:00
Nikos Livathinos
a9b22a8694 fix(BoundingBox): Fixing the BoundingBox.area() method to work for all values of CoordOrigin 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-07 17:26:58 +02:00
Michele Dolfi
9eb3afc16c expose easyocr arguments 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-07 15:17:40 +02:00
Michele Dolfi
99dfbf6107 add tesseract language packages 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-07 15:14:10 +02:00
Nikos Livathinos
49652eec54 feat(tests): Introduce fuzzy text comparison for OCR tests based on Levenshtein edit distance 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-04 14:13:24 +02:00
github-actions[bot]
9b82ae3324 chore: bump version to 1.18.0 [skip ci] 2024-10-03 17:16:00 +00:00
Michele Dolfi
544f298fb4 add missing install 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-03 19:05:48 +02:00
Michele Dolfi
b3293ffc75 update test results 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-03 19:04:02 +02:00
Michele Dolfi
2784d9c3b5 Merge remote-tracking branch 'origin/main' into feat-multiple-ocr-engines 2024-10-03 19:02:01 +02:00
Michele Dolfi
f57e4b2afb add tesseract in CI, improve error messages and allow to specify the tesseract cmd 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-03 18:59:29 +02:00
Maxim Lysak
2422f706a1
feat: new torch-based docling models (#120) 
---------

Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
 2024-10-03 18:42:33 +02:00
Nikos Livathinos
e571ab50ee fix(tests): Extend test_e2e_ocr_conversion to cover all OCR engines (easyocr, tesserocr, tesseract) 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-03 16:49:23 +02:00
Nikos Livathinos
7ab3b62c18 chore(data_scanned): Simplify the OCR test images. Add GT for easyocr, tesserocr, tesseract 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-03 16:46:51 +02:00
github-actions[bot]
9ebbbc1245 chore: bump version to 1.17.0 [skip ci] 2024-10-03 13:44:52 +00:00
Rui Dias Gomes
dde0aff8bd
update examples (#123) 
Signed-off-by: rmdg88 <rmdg88@gmail.com>
 2024-10-03 14:28:25 +02:00
Michele Dolfi
d44c62d7ce
feat: windows support (#122) 
* feat: windows support

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

* add Windows in README

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

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-03 14:23:47 +02:00
Nikos Livathinos
1d4517ffb4 fix(TesserOcrModel): Refactor code to catch exception in case of import error 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-03 14:23:07 +02:00
Michele Dolfi
81d176cd3d add message for failed easyocr import 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-03 13:38:01 +02:00
Nikos Livathinos
c28846a866 feat: Implement the TesserOcrModel. Introduce the test_e2e_ocr_conversion.py unit test. 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-02 18:12:32 +02:00
Nikos Livathinos
a0e72655f7 chore: Update the data_scanned to have recognitions per ocr engine 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-02 18:12:32 +02:00
Peter Staar
fed3323e25 tesseract is working 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2024-10-02 17:23:50 +02:00
Peter Staar
a3e2cf5473 fixed conflicts 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2024-10-02 17:01:34 +02:00
Michele Dolfi
0b76211eed add examples for swtching OCR engine and CLI support 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-02 16:57:48 +02:00
Peter Staar
8d1c1d6dd5 added the tesseract_model.py 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2024-10-02 16:40:24 +02:00
Nikos Livathinos
bfdc4e32cc chore: Add test data with scanned documents and their conversions usinga EasyOCR 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-02 13:35:38 +02:00
Nikos Livathinos
c211808742 feat: tesseract and tesserocr models. WIP. 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-02 13:35:00 +02:00
Nikos Livathinos
455d6ff70f chore: Add tesserocr in poetry 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
 2024-10-02 13:27:34 +02:00
Michele Dolfi
bbfc0617f2 feat: add options for choosing OCR engine 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-10-02 10:47:20 +02:00
github-actions[bot]
cde671cf34 chore: bump version to 1.16.1 [skip ci] 2024-09-27 14:36:40 +00:00
Michele Dolfi
34bd887a7f
fix: allow usage of opencv 4.6.x (#110) 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2024-09-27 15:51:43 +02:00
Panos Vagenas
c05b692d69
docs: document chunking (#111) 
[skip ci]

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
 2024-09-27 11:16:04 +02:00
github-actions[bot]
6760571fe1 chore: bump version to 1.16.0 [skip ci] 2024-09-27 06:21:15 +00:00
Christoph Auer
d6df76f90b
feat: Support tableformer model choice (#90) 
* Support tableformer model choice

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

* Update datamodel structure

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

* Update docs

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

* Cleanup

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

* Add test unit for table options

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

* Ensure import backwards-compatibility for PipelineOptions

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

* Update README

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

* Adjust parameters on custom_convert

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

* Update Dockerfile

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
 2024-09-26 21:37:08 +02:00