* Keep page.parsed_page.textline_cells and page.cells in sync, including OCR
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Make page.parsed_page the only source of truth for text cells
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Small fix
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Correctly compute PDF boxes from pymupdf
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Use different OCR engine order
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add type hints and fix mypy
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* One more test fix
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Remove with pypdfium2_lock from caller sites
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix typing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* feat: adding new vlm-models support
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fixed the transformers
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* got microsoft/Phi-4-multimodal-instruct to work
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* working on vlm's
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* refactoring the VLM part
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* all working, now serious refacgtoring necessary
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* refactoring the download_model
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added the formulate_prompt
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* pixtral 12b runs via MLX and native transformers
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added the VlmPredictionToken
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* refactoring minimal_vlm_pipeline
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fixed the MyPy
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added pipeline_model_specializations file
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* need to get Phi4 working again ...
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* finalising last points for vlms support
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fixed the pipeline for Phi4
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* streamlining all code
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* reformatted the code
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fixing the tests
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added the html backend to the VLM pipeline
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fixed the static load_from_doctags
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* restore stable imports
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* use AutoModelForVision2Seq for Pixtral and review example (including rename)
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* remove unused value
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* refactor instances of VLM models
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* skip compare example in CI
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* use lowercase and uppercase only
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add new minimal_vlm example and refactor pipeline_options_vlm_model for cleaner import
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* rename pipeline_vlm_model_spec
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* move more argument to options and simplify model init
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add supported_devices
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* remove not-needed function
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* exclude minimal_vlm
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* missing file
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add message for transformers version
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* rename to specs
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* use module import and remove MLX from non-darwin
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* remove hf_vlm_model and add extra_generation_args
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* use single HF VLM model class
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* remove torch type
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add docs for vision models
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.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>
* test: update results with new docling-core
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* update all deps in the lock
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* fix table in test results
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* fix version for python3.13
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* latest poetry version in CI
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* activate py3.13 in CI
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* update docs about python 3.13
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* test with rapidocr only on python <3.13
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* chore: Add example for inspection of picture content
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Test case re-generation
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Test case re-generation only on CPU
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Add missing GT files
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* feat: Introduce automatic language detection in tesseract_ocr_cli model. Extend unit tests.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* docs: Add example how to use "auto" language with tesseract OCR engines
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Refactor the TesseractOcrModel and TesseractOcrCliModel to validate if the auto-detected
language is installed in the system and if not fall back to a default option without language.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---------
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* Add "auto" language for TesseractOcr
Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
* Add tesseract-ocr-script-latn installation for the "auto" language
Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
* Modify "auto" language in TesseractOcr to initialize the script readers lazily
Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
* Finalize script readers
Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
* Fix script models prefix for Linux
Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
---------
Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
* adding rapidocr engine for ocr in docling
Signed-off-by: swayam-singhal <swayam.singhal@inito.com>
* fixing styling format
Signed-off-by: Swaymaw <swaymaw@gmail.com>
* updating pyproject.toml and poetry.lock to fix ci bugs
Signed-off-by: Swaymaw <swaymaw@gmail.com>
* help poetry pinning for python3.9
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* simplifying rapidocr options so that device can be changed using a single option for all models
Signed-off-by: Swaymaw <swaymaw@gmail.com>
* fix styling issues and small bug in rapidOcrOptions
Signed-off-by: Swaymaw <swaymaw@gmail.com>
* use default device until we enable global management
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: swayam-singhal <swayam.singhal@inito.com>
Signed-off-by: Swaymaw <swaymaw@gmail.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: swayam-singhal <swayam.singhal@inito.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
* feat: add support for `ocrmac` OCR engine on macOS
- Integrates `ocrmac` as an OCR engine option for macOS users.
- Adds configuration options and dependencies for `ocrmac`.
- Updates documentation to reflect new engine support.
This change allows macOS users to utilize `ocrmac` for improved OCR performance and compatibility.
Signed-off-by: Suhwan Seo <nuridol@gmail.com>
* updated the poetry lock
Signed-off-by: Suhwan Seo <nuridol@gmail.com>
* Fix linting issues, update CLI docs, and add error for ocrmac use on non-Mac systems
- Resolved formatting and linting issues
- Updated `--ocr-engine` CLI option documentation for `ocrmac`
- Added RuntimeError for attempts to use `ocrmac` on non-Mac platforms
Signed-off-by: Suhwan Seo <nuridol@gmail.com>
* feat: add support for `ocrmac` OCR engine on macOS
- Integrates `ocrmac` as an OCR engine option for macOS users.
- Adds configuration options and dependencies for `ocrmac`.
- Updates documentation to reflect new engine support.
This change allows macOS users to utilize `ocrmac` for improved OCR performance and compatibility.
Signed-off-by: Suhwan Seo <nuridol@gmail.com>
* docs: update examples and installation for ocrmac support
- Added `OcrMacOptions` to `custom_convert.py` and `full_page_ocr.py` examples.
- Included usage comments and examples for `OcrMacOptions` in OCR pipelines.
- Updated installation guide to include instructions for installing `ocrmac`, noting macOS version requirements (10.15+).
- Highlighted that `ocrmac` leverages Apple's Vision framework as an OCR backend.
This enhances documentation for users working on macOS to leverage `ocrmac` effectively.
Signed-off-by: Suhwan Seo <nuridol@gmail.com>
* fix: update `ocrmac` dependency with macOS-specific marker
- Added `sys_platform == 'darwin'` marker to the `ocrmac` dependency in `pyproject.toml` to specify macOS compatibility.
- Updated the content hash in `poetry.lock` to reflect the changes.
This ensures the `ocrmac` dependency is only installed on macOS systems.
Signed-off-by: Suhwan Seo <nuridol@gmail.com>
---------
Signed-off-by: Suhwan Seo <nuridol@gmail.com>
Co-authored-by: Suhwan Seo <nuridol@gmail.com>
- When the OCR is forced, any existing PDF cells are rejected.
- Introduce the force-ocr cmd parameter in docling CLI.
- Update unit tests.
- Add the full_page_ocr.py example in mkdocs.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* feat(OCR tests): Introduce fuzziness in the text validation of OCR tests
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix(TesseractOcrCliModel): Send the stderr to devnull to avoid poluting the console with messages from tesseract cmd
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---------
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
