mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-25 19:44:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
2f72167ff6
docling/tests/data/groundtruth/docling_v2
History
Maxim Lysak 2f72167ff6
feat: updated vlm pipeline (with latest changes from docling-core) (#1158) 
* Draft implementation of Doctag backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Updated VLM pipeline doctags to docling conversion, now properly supports lists

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* preparing to migrate to new doctags deserializer

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* re-using DocTagsDocument.from_doctags_and_image_pairs

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* satisfying mypy and other checks

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added support for force_backend_text parameter

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* removed unnecessary transformation

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Cleaned up

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Update tests

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

* Updated readme

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
2025-03-18 15:44:51 +01:00
..
2203.01017v2.doctags.txt feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
2203.01017v2.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2203.01017v2.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2203.01017v2.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2206.01062.doctags.txt feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
2206.01062.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2206.01062.md feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
2206.01062.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2305.03393v1-pg9.doctags.txt feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
2305.03393v1-pg9.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2305.03393v1-pg9.md feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
2305.03393v1-pg9.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2305.03393v1.doctags.txt feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
2305.03393v1.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
2305.03393v1.md feat: Use new TableFormer model weights and default to accurate model version (#1100) 2025-03-11 10:53:49 +01:00
2305.03393v1.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
amt_handbook_sample.doctags.txt fix: Revise DocTags, fix iterate_items to output content_layer in items (#965) 2025-02-17 14:11:55 +01:00
amt_handbook_sample.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
amt_handbook_sample.md docs: Add example for inspection of picture content (#624) 2025-01-29 10:39:00 +01:00
amt_handbook_sample.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
blocks.md.md fix: Pass tests, update docling-core to 2.22.0 (#1150) 2025-03-13 09:45:55 +01:00
bmj_sample.xml.itxt feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
bmj_sample.xml.json feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
bmj_sample.xml.md feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
code_and_formula.doctags.txt fix: Pass tests, update docling-core to 2.22.0 (#1150) 2025-03-13 09:45:55 +01:00
code_and_formula.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
code_and_formula.md feat: Implement new reading-order model (#916) 2025-02-20 17:51:17 +01:00
code_and_formula.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-comma-in-cell.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-comma-in-cell.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-comma-in-cell.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-comma.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-comma.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-comma.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-inconsistent-header.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-inconsistent-header.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-inconsistent-header.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-pipe.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-pipe.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-pipe.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-semicolon.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-semicolon.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-semicolon.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-tab.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-tab.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-tab.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-too-few-columns.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-too-few-columns.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-too-few-columns.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-too-many-columns.csv.itxt feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
csv-too-many-columns.csv.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
csv-too-many-columns.csv.md feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) 2025-02-14 08:55:09 +01:00
duck.md.md fix: fix single newline handling in MD backend (#824) 2025-01-28 19:05:55 +01:00
elife-56337.xml.itxt feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
elife-56337.xml.md feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
ending_with_table.md.md fix(markdown): fix parsing if doc ending with table (#873) 2025-02-03 14:38:38 +01:00
equations.docx.itxt feat: equations to latex in MSWord backend (with inline groups) (#1114) 2025-03-13 15:12:22 +01:00
equations.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
equations.docx.md feat: equations to latex in MSWord backend (with inline groups) (#1114) 2025-03-13 15:12:22 +01:00
example_01.html.itxt refactor: add the contentlayer to html-backend (#1040) 2025-03-02 10:37:53 -05:00
example_01.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_01.html.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_02.html.itxt refactor: add the contentlayer to html-backend (#1040) 2025-03-02 10:37:53 -05:00
example_02.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_02.html.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_03.html.itxt refactor: add the contentlayer to html-backend (#1040) 2025-03-02 10:37:53 -05:00
example_03.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_03.html.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_04.html.itxt fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
example_04.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_04.html.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_05.html.itxt fix: parse html with omitted body tag (#818) 2025-01-27 16:59:00 +01:00
example_05.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_05.html.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_06.html.itxt refactor: add the contentlayer to html-backend (#1040) 2025-03-02 10:37:53 -05:00
example_06.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_06.html.md fix(html): Parse text in div elements as TextItem (#1041) 2025-02-24 12:38:29 +01:00
example_07.html.itxt fix(html): handle nested empty lists (#1154) 2025-03-13 16:56:58 +01:00
example_07.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
example_07.html.md fix(html): handle nested empty lists (#1154) 2025-03-13 16:56:58 +01:00
ipa20180000016.itxt feat: create a backend to parse USPTO patents into DoclingDocument (#606) 2024-12-17 16:35:23 +01:00
ipa20180000016.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
ipa20180000016.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
ipa20200022300.itxt feat: create a backend to parse USPTO patents into DoclingDocument (#606) 2024-12-17 16:35:23 +01:00
ipa20200022300.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
ipa20200022300.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
lorem_ipsum.docx.itxt fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
lorem_ipsum.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
lorem_ipsum.docx.md fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
mixed.md.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
nested.md.md fix(markdown): handle nested lists (#910) 2025-02-07 12:55:12 +01:00
pa20010031492.itxt feat: create a backend to parse USPTO patents into DoclingDocument (#606) 2024-12-17 16:35:23 +01:00
pa20010031492.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
pa20010031492.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
pftaps057006474.itxt fix: Pass tests, update docling-core to 2.22.0 (#1150) 2025-03-13 09:45:55 +01:00
pftaps057006474.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
pftaps057006474.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
pg06442728.itxt feat: create a backend to parse USPTO patents into DoclingDocument (#606) 2024-12-17 16:35:23 +01:00
pg06442728.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
pg06442728.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
picture_classification.doctags.txt fix: Revise DocTags, fix iterate_items to output content_layer in items (#965) 2025-02-17 14:11:55 +01:00
picture_classification.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
picture_classification.md feat: New document picture classifier (#805) 2025-01-24 18:05:51 +01:00
picture_classification.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
pnas_sample.xml.itxt feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
pnas_sample.xml.json feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
pnas_sample.xml.md feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
pntd.0008301.xml.itxt feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
pntd.0008301.xml.md feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
pone.0234687.xml.itxt feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
pone.0234687.xml.md feat(xml-jats): parse XML JATS documents (#967) 2025-02-17 10:43:31 +01:00
powerpoint_sample.pptx.itxt feat: Extracting picture data for raster images found in PPTX (#349) 2024-11-18 15:22:28 +01:00
powerpoint_sample.pptx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
powerpoint_sample.pptx.md feat: Extracting picture data for raster images found in PPTX (#349) 2024-11-18 15:22:28 +01:00
powerpoint_with_image.pptx.itxt feat: Extracting picture data for raster images found in PPTX (#349) 2024-11-18 15:22:28 +01:00
powerpoint_with_image.pptx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
powerpoint_with_image.pptx.md feat: Extracting picture data for raster images found in PPTX (#349) 2024-11-18 15:22:28 +01:00
redp5110_sampled.doctags.txt fix: Pass tests, update docling-core to 2.22.0 (#1150) 2025-03-13 09:45:55 +01:00
redp5110_sampled.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
redp5110_sampled.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
redp5110_sampled.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
right_to_left_01.doctags.txt feat: Implement new reading-order model (#916) 2025-02-20 17:51:17 +01:00
right_to_left_01.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
right_to_left_01.md feat: Implement new reading-order model (#916) 2025-02-20 17:51:17 +01:00
right_to_left_01.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
right_to_left_02.doctags.txt fix: Revise DocTags, fix iterate_items to output content_layer in items (#965) 2025-02-17 14:11:55 +01:00
right_to_left_02.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
right_to_left_02.md fix: Test cases for RTL programmatic PDFs and fixes for the formula model (#903) 2025-02-07 08:43:31 +01:00
right_to_left_02.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
right_to_left_03.doctags.txt fix: Revise DocTags, fix iterate_items to output content_layer in items (#965) 2025-02-17 14:11:55 +01:00
right_to_left_03.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
right_to_left_03.md fix: Test cases for RTL programmatic PDFs and fixes for the formula model (#903) 2025-02-07 08:43:31 +01:00
right_to_left_03.pages.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
tablecell.docx.itxt fix: Fixes for wordx (#432) 2024-11-26 14:44:43 +01:00
tablecell.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
tablecell.docx.md fix: Fixes for wordx (#432) 2024-11-26 14:44:43 +01:00
test_01.asciidoc.md feat: Support AsciiDoc and Markdown input format (#168) 2024-10-23 16:14:26 +02:00
test_02.asciidoc.md feat: Support AsciiDoc and Markdown input format (#168) 2024-10-23 16:14:26 +02:00
test_emf_docx.docx.itxt fix: Fixes for wordx (#432) 2024-11-26 14:44:43 +01:00
test_emf_docx.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
test_emf_docx.docx.md fix: Fixes for wordx (#432) 2024-11-26 14:44:43 +01:00
test-01.xlsx.itxt fix: added extraction of byte-images in excel (#804) 2025-01-24 18:48:02 +01:00
test-01.xlsx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
test-01.xlsx.md fix: added extraction of byte-images in excel (#804) 2025-01-24 18:48:02 +01:00
unit_test_01.html.itxt fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
unit_test_01.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
unit_test_01.html.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
unit_test_headers_numbered.docx.itxt fix: Fixed docx import with headers that are also lists (#842) 2025-01-31 10:51:21 +01:00
unit_test_headers_numbered.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
unit_test_headers_numbered.docx.md fix: Fixed docx import with headers that are also lists (#842) 2025-01-31 10:51:21 +01:00
unit_test_headers.docx.itxt fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
unit_test_headers.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
unit_test_headers.docx.md fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
unit_test_lists.docx.itxt fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
unit_test_lists.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
unit_test_lists.docx.md fix: fix duplicate title and heading + add e2e tests for html and docx (#186) 2024-10-30 13:14:56 +01:00
wiki_duck.html.itxt refactor: add the contentlayer to html-backend (#1040) 2025-03-02 10:37:53 -05:00
wiki_duck.html.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
wiki_duck.html.md feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
wiki.md.md fix: fix single newline handling in MD backend (#824) 2025-01-28 19:05:55 +01:00
word_sample.docx.itxt fix: Fixing images in the input Word files (#330) 2024-11-14 13:33:34 +01:00
word_sample.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
word_sample.docx.md fix: Fixing images in the input Word files (#330) 2024-11-14 13:33:34 +01:00
word_sample.json fix: Fixes for wordx (#432) 2024-11-26 14:44:43 +01:00
word_sample.md fix: Fixes for wordx (#432) 2024-11-26 14:44:43 +01:00
word_sample.yaml fix: Fixes for wordx (#432) 2024-11-26 14:44:43 +01:00
word_tables.docx.html feat: updated vlm pipeline (with latest changes from docling-core) (#1158) 2025-03-18 15:44:51 +01:00
word_tables.docx.itxt fix(docx): merged table cells not properly converted (#857) 2025-02-03 10:20:03 +01:00
word_tables.docx.json feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905) 2025-03-18 10:38:19 +01:00
word_tables.docx.md fix(docx): merged table cells not properly converted (#857) 2025-02-03 10:20:03 +01:00