* Expose `rec_keys_path` in RapidOcrOptions to support custom dictionaries
- Added `rec_keys_path` to `RapidOcrOptions` to align with RapidOCR's capability to use custom character dictionaries.
- Passed `rec_keys_path` to `RapidOcrModel` initialization, ensuring the recognition model can load the correct dictionary (e.g., for Latin characters).
Signed-off-by: Yorick Terweijden <yorick@spread.ai>
* style(rapidocr-options): fix alignment of `rec_keys_path` comment
Adjusted the alignment of the comment for `rec_keys_path` to maintain consistent formatting. No functional changes were made.
Signed-off-by: Yorick Terweijden <yorick@spread.ai>
---------
Signed-off-by: Yorick Terweijden <yorick@spread.ai>
* 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>
* Upgraded Layout Postprocessing, sending old code back to ERZ
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Implement hierachical cluster layout processing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Pass nested cluster processing through full pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Pass nested clusters through GLM as payload
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Move to_docling_document from ds-glm to this repo
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Clean up imports again
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* feat(Accelerator): Introduce options to control the num_threads and device from API, envvars, CLI.
- Introduce the AcceleratorOptions, AcceleratorDevice and use them to set the device where the models run.
- Introduce the accelerator_utils with function to decide the device and resolve the AUTO setting.
- Refactor the way how the docling-ibm-models are called to match the new init signature of models.
- Translate the accelerator options to the specific inputs for third-party models.
- Extend the docling CLI with parameters to set the num_threads and device.
- Add new unit tests.
- Write new example how to use the accelerator options.
* fix: Improve the pydantic objects in the pipeline_options and imports.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: TableStructureModel: Refactor the artifacts path to use the new structure for fast/accurate model
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* Updated test ground-truth
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Updated test ground-truth (again), bugfix for empty layout
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Do proper check to set the device in EasyOCR, RapidOCR.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Correct the way to set GPU for EasyOCR, RapidOCR
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Ocr AccleratorDevice
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* Merge pull request #556 from DS4SD/cau/layout-processing-improvement
feat: layout processing improvements and bugfixes
* Update lockfile
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update tests
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update HF model ref, reset test generate
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Repin to release package versions
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Many layout processing improvements, add document index type
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update pinnings to docling-core
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test GT
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix table box snapping
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fixes for cluster pre-ordering
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Introduce OCR confidence, propagate to orphan in post-processing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix form and key value area groups
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Adjust confidence in EasyOcr
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Roll back CLI changes from main
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test GT
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update docling-core pinning
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Annoying fixes for historical python versions
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Updated test GT for legacy
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Comment cleanup
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Co-authored-by: Nikos Livathinos <nli@zurich.ibm.com>
* Update easyocr_model.py
Added this line of code to get recog_network of easyocr parameter
recog_network = self.options.recog_network
Signed-off-by: itsainii <aininawawii@gmail.com>
* Update pipeline_options.py
Added this line in EasyOcrOptions function
recog_network: Optional[str] = 'standard'
Signed-off-by: itsainii <aininawawii@gmail.com>
* Add Easyocr recog_network parameter
Signed-off-by: itsainii <aininawawii@gmail.com>
---------
Signed-off-by: itsainii <aininawawii@gmail.com>
* Upgraded Layout Postprocessing, sending old code back to ERZ
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Implement hierachical cluster layout processing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Pass nested cluster processing through full pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Pass nested clusters through GLM as payload
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Move to_docling_document from ds-glm to this repo
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Clean up imports again
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* feat(Accelerator): Introduce options to control the num_threads and device from API, envvars, CLI.
- Introduce the AcceleratorOptions, AcceleratorDevice and use them to set the device where the models run.
- Introduce the accelerator_utils with function to decide the device and resolve the AUTO setting.
- Refactor the way how the docling-ibm-models are called to match the new init signature of models.
- Translate the accelerator options to the specific inputs for third-party models.
- Extend the docling CLI with parameters to set the num_threads and device.
- Add new unit tests.
- Write new example how to use the accelerator options.
* fix: Improve the pydantic objects in the pipeline_options and imports.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: TableStructureModel: Refactor the artifacts path to use the new structure for fast/accurate model
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* Updated test ground-truth
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Updated test ground-truth (again), bugfix for empty layout
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Do proper check to set the device in EasyOCR, RapidOCR.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* Rollback changes from main
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test gt
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Remove unused debug settings
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Review fixes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Nail the accelerator defaults for MPS
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
* Move to_docling_document from ds-glm to this repo
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Upgrade to ds-glm 1.0 and docling-parse 3.0
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update lock
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix DP2 backend code, change CLI default backend
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* 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>
fix(EasyOcrModel): Support the use_gpu pipeline parameter in EasyOcrModel. Initialize easyocr without GPU if MPS is available.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
fix(TesseractOcrModel): Raise Exception if tesserocr has not loaded any languages. Provide a descriptive error message.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* Add settings to turn visualization on or off
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add profiling code to all models
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Refactor and fix profiling codes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Visualization codes output PNG to debug dir
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fixes for time logging
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Optimize imports
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update lockfile
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add start_timestamps to ProfilingItem
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@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>
* 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>
* add the pytests
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* renamed the test folder and added the toplevel test
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updated the toplevel function test
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* need to start running all tests successfully
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added the reference converted documents
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added first test for json and md output
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* ran pre-commit
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* replaced deprecated json function with model_dump_json
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* replaced deprecated json function with model_dump_json
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* reformatted code
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* Fix backend tests
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* commented out the drawing
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* ci: avoid duplicate runs
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
* commented out json verification for now
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added verification of input cells
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* reformat code
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added test to verify the cells in the pages
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added test to verify the cells in the pages (2)
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added test to verify the cells in the pages (3)
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* run all examples in CI
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* make sure examples return failures
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* raise a failure if examples fail
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* fix examples
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* run examples after tests
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* Add tests and update top_level_tests using only datamodels
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Remove unnecessary code
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Validate conversion status on e2e test
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* package verify utils and add more tests
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* reduce docs in example, since they are already in the tests
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* skip batch_convert
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* pin docling-parse 1.1.2
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* updated the error messages
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* commented out the json verification for now
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* bumped GLM version
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* Fix lockfile
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Pin new docling-parse v1.1.3
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
- fields `output` & `assembled` need not be optional
- introduced "synonym" `ConversionResult` for `ConvertedDocument` & deprecated the latter
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
