fixing double scaling in case of do_cell_matching is False
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
* sytle(xlsx): enforce type hints in XLSX backend
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* feat(xlsx): create a page for each worksheet in XLSX backend
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* docs(xlsx): add docstrings to XLSX backend module.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* docling(xlsx): add bounding boxes and page size information in cell units
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* build: Add ollama sdk dependency
Branch: OllamaVlmModel
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add option plumbing for OllamaVlmOptions in pipeline_options
Branch: OllamaVlmModel
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Full implementation of OllamaVlmModel
Branch: OllamaVlmModel
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Connect "granite_vision_ollama" pipeline option to CLI
Branch: OllamaVlmModel
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* Revert "build: Add ollama sdk dependency"
After consideration, we're going to use the generic OpenAI API instead
of the Ollama-specific API to avoid duplicate work.
This reverts commit bc6b366468cdd66b52540aac9c7d8b584ab48ad0.
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Move OpenAI API call logic into utils.utils
This will allow reuse of this logic in a generic VLM model
NOTE: There is a subtle change here in the ordering of the text prompt and
the image in the call to the OpenAI API. When run against Ollama, this
ordering makes a big difference. If the prompt comes before the image, the
result is terse and not usable whereas the prompt coming after the image
works as expected and matches the non-OpenAI chat API.
Branch: OllamaVlmModel
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Refactor from Ollama SDK to generic OpenAI API
Branch: OllamaVlmModel
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Linting, formatting, and bug fixes
The one bug fix was in the timeout arg to openai_image_request. Otherwise,
this is all style changes to get MyPy and black passing cleanly.
Branch: OllamaVlmModel
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* remove model from download enum
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* generalize input args for other API providers
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* rename and refactor
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add example
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* require flag for remote services
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* disable example from CI
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add examples to docs
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
* Fixes#1333
Signed-off-by: Joan Fabrégat <j@fabreg.at>
* fix for the (dumb) MyPy type checker
Signed-off-by: Joan Fabrégat <j@fabreg.at>
---------
Signed-off-by: Joan Fabrégat <j@fabreg.at>
logo parameter in docling cli, prints cute ascii logo
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
* Adding new latex symbols, simplifying how equations are added to text
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Identify headers through inhenrited style
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Log warning message instead of print
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Adding new latex symbols, simplifying how equations are added to text
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Identify headers through inhenrited style
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Log warning message instead of print
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix: Tesseract OCR CLI can't process images composed with numbers only (#1201)
fix wrong type text extracted by tesseract_ocr_cli_model
Signed-off-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Co-authored-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix(docx): Improve text parsing (#1268)
* chore: bump version to 2.28.4 [skip ci]
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Improve text parsing
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix: Tesseract OCR CLI can't process images composed with numbers only (#1201)
fix wrong type text extracted by tesseract_ocr_cli_model
Signed-off-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Co-authored-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Flexibilize heading detection
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Fix trailing space
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Remove trailing space
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
Signed-off-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Guilhem VERMOREL <83694424+guilhemvermorel@users.noreply.github.com>
Co-authored-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* docs: add visual grounding example (#1270)
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* feat(docx): add text formatting and hyperlink support (#630)
* feat: Enable markdown text formatting for docx
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Fix imports
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Use Formatting
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Handle hyperlink
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Handle formatting properly for DocItemLabel.PARAGRAPH
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Use inline group
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Handle bullet lists
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Strip elements
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Strip elements
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Run black and mypy
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Handle header and footer
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Use inline_fmt everywhere
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Run precommit
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Address feedback
Signed-off-by: SimJeg <sjegou@nvidia.com>
* Fix add_list_item
Signed-off-by: SimJeg <sjegou@nvidia.com>
* fix minor bugs, mark helper methods internal
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
---------
Signed-off-by: SimJeg <sjegou@nvidia.com>
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
Co-authored-by: Panos Vagenas <pva@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix(pptx): check if picture shape has an image attached (#1316)
Check if picture shape has an image attached in pptx backend
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* chore: update lock file (#1315)
chore: update lock
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* docs: add plugins docs (#1319)
add plugin docs
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* feat: handle <code> tags as code blocks (#1320)
handle <code> tags as code blocks
Signed-off-by: FernandoSSI <fernandosi2005@gmail.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Adding new latex symbols, simplifying how equations are added to text
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Identify headers through inhenrited style
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Log warning message instead of print
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Adding new latex symbols, simplifying how equations are added to text
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
Signed-off-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
Signed-off-by: SimJeg <sjegou@nvidia.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: FernandoSSI <fernandosi2005@gmail.com>
Co-authored-by: Guilhem VERMOREL <83694424+guilhemvermorel@users.noreply.github.com>
Co-authored-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Simon Jégou <SimJeg@users.noreply.github.com>
Co-authored-by: Panos Vagenas <pva@zurich.ibm.com>
Co-authored-by: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Fernando Santos <121275806+FernandoSSI@users.noreply.github.com>
Check if picture shape has an image attached in pptx backend
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
* chore: bump version to 2.28.4 [skip ci]
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Improve text parsing
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix: Tesseract OCR CLI can't process images composed with numbers only (#1201)
fix wrong type text extracted by tesseract_ocr_cli_model
Signed-off-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Co-authored-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Flexibilize heading detection
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Fix trailing space
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Remove trailing space
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
Signed-off-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Guilhem VERMOREL <83694424+guilhemvermorel@users.noreply.github.com>
Co-authored-by: gvl4 <Guilhem.VERMOREL@3ds.com>
fix wrong type text extracted by tesseract_ocr_cli_model
Signed-off-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Co-authored-by: gvl4 <Guilhem.VERMOREL@3ds.com>
Markdown fixes:
- properly propagate section header levels
- improve handling of list subroots without text
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
* Update document_converter.py
Fixing caching same class with different options by using composite key (class, options)
# TODO this will ignore if different options have been defined for the same pipeline class.
at row 292
Signed-off-by: mislavmartinic <mislav.martinic@pontistechnology.com>
* formatted script
* removed unnecessary hasattr check
* pre-commit chain run
---------
Signed-off-by: mislavmartinic <mislav.martinic@pontistechnology.com>
* Modifications to identify numbered headers
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Add style check
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* feat: Add PPTX notes slides
Presenter notes may have useful information and should also be extracted.
Signed-off-by: Maciej Wieczorek <maciej@wieczorek.co>
* feat: Move presenter notes into furniture
Signed-off-by: Maciej Wieczorek <maciej@wieczorek.co>
---------
Signed-off-by: Maciej Wieczorek <maciej@wieczorek.co>
* Fixing function return
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Add message
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Add DoclingParseV3 backend implementation
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Use docling-core with docling-parse types
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fixes and test updates
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix streams
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix streams
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Reset tests
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* update test cases
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* update test units
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add back DoclingParse v1 backend, pipeline options
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update locks
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: update docling-core to 2.22.0
Update dependency library docling-core to latest release 2.22.0
Fix regression tests and ground truth files
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Ground-truth files updated
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update tests, use TextCell.from_ocr property
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Text fixes, new test data
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Rename docling backend to v4
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Test all backends, fixes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Reset all tests to use docling-parse v1 for now
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fixes for DPv4 backend init, better test coverage
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* test_input_doc use default backend
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Equation groups
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix: Proper handling of orphan IDs in layout postprocessing (#1118)
* Fix the handling of orphan IDs in layout postprocessing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test cases
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* chore: bump version to 2.25.2 [skip ci]
* docs: add description of DOCLING_ARTIFACTS_PATH env var (#1124)
add env var in docs
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix(CLI): fix help message for abort options (#1130)
fix help message
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* perf: New revision code formula model and document picture classifier (#1140)
* new version code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new version document picture classifier
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* restored original code formula test pdf
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
---------
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* feat: Use new TableFormer model weights and default to accurate model version (#1100)
* feat: New tableformer model weights [WIP]
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
* Updated TF version
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Updated tests, after merging with Main, Switched to Accurate TF model by default
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* chore: bump version to 2.26.0 [skip ci]
* fix: Pass tests, update docling-core to 2.22.0 (#1150)
fix: update docling-core to 2.22.0
Update dependency library docling-core to latest release 2.22.0
Fix regression tests and ground truth files
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Updating content hash
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Matteo <43417658+Matteo-Omenetti@users.noreply.github.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
fix: update docling-core to 2.22.0
Update dependency library docling-core to latest release 2.22.0
Fix regression tests and ground truth files
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* feat: New tableformer model weights [WIP]
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
* Updated TF version
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Updated tests, after merging with Main, Switched to Accurate TF model by default
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
* new version code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new version document picture classifier
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* restored original code formula test pdf
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
---------
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* Fix the handling of orphan IDs in layout postprocessing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test cases
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* added the contentlayer to html-backend
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updated the handle_image function
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* reformatted code of html backend
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* test(html): add more info if a test case fails
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* refactor(html): put parsed item in body if doc has no header
In case an HTML does not have any header tag, all parsed items are placed in
DoclingDocument's body content layer.
HTML paragraphs ('p' tags) are parsed as text items with paragraph label.
Update test ground truth accoring to the changes above.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* chore: set TextItem label to 'text' instead of 'paragraph'
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* fix(html): use 'start' attribute in ordered lists
When parsing ordered lists in HTML, take into account the 'start' attribute if it exists.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* chore(html): reduce verbosity in HTML backend
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Skeleton for SmolDocling model and VLM Pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* wip smolDocling inference and vlm pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* WIP, first working code for inference of SmolDocling, and vlm pipeline assembly code, example included.
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Fixes to preserve page image and demo export to html
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Enabled figure support in vlm_pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Fix for table span compute in vlm_pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Properly propagating image data per page, together with predicted tags in VLM pipeline. This enables correct figure extraction and page numbers in provenances
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Cleaned up logs, added pages to vlm_pipeline, basic timing per page measurement in smol_docling models
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Replaced hardcoded otsl tokens with the ones from docling-core tokens.py enum
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Added tokens/sec measurement, improved example
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Added capability for vlm_pipeline to grab text from preconfigured backend
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Exposed "force_backend_text" as pipeline parameter
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Flipped keep_backend to True for vlm_pipeline assembly to work
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Updated vlm pipeline assembly and smol docling model code to support updated doctags
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Fixing doctags starting tag, that broke elements on first line during assembly
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* 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.
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Moved artifacts_path for SmolDocling into vlm_options instead of global pipeline option
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* New assembly code for latest model revision, updated prompt and parsing of doctags, updated logging
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Updated example of Smol Docling usage
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Added captions for the images for SmolDocling assembly code, improved provenance definition for all elements
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Update minimal smoldocling example
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix repo id
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Cleaned up unnecessary logging
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* More elegant solution in removing the input prompt
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* removed minimal_smol_docling example from CI checks
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Removed special html code wrapping when exporting to docling document, cleaned up comments
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Addressing PR comments, added enabled property to SmolDocling, and related VLM pipeline option, few other minor things
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Moved keep_backend = True to vlm pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* removed pipeline_options.generate_table_images from vlm_pipeline (deprecated in the pipelines)
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Added example on how to get original predicted doctags in minimal_smol_docling
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* removing changes from base_pipeline
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Replaced remaining strings to appropriate enums
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Updated poetry.lock
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* re-built poetry.lock
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* Generalize and refactor VLM pipeline and models
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Rename example
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Move imports
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Expose control over using flash_attention_2
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix VLM example exclusion in CI
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add back device_map and accelerate
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Make drawing code resilient against bad bboxes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* chore: clean up code and comments
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* chore: more cleanup
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* chore: fix leftover .to(device)
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: add proper table provenance
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
