* scaffolding in place
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* doing scaffolding for audio pipeline
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* WIP: got first transcription working
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* all working, time to start cleaning up
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* first working ASR pipeline
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added openai-whisper as a first transcription model
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updating with asr_options
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* finalised the first working ASR pipeline with Whisper
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* use whisper from the latest git commit
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* Update docling/datamodel/pipeline_options.py
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Peter W. J. Staar <91719829+PeterStaar-IBM@users.noreply.github.com>
* Update docling/datamodel/pipeline_options.py
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Peter W. J. Staar <91719829+PeterStaar-IBM@users.noreply.github.com>
* updated comment
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* AudioBackend -> DummyBackend
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* file rename
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Rename to NoOpBackend, add test for ASR pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Support every format in NoOpBackend
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add missing audio file and test
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Install ffmpeg system dependency for ASR test
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Peter W. J. Staar <91719829+PeterStaar-IBM@users.noreply.github.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
* Image scale moved to base vlm options.
Added max_size image limit (options and vlm models).
* DCO Remediation Commit for Shkarupa Alex <shkarupa.alex@gmail.com>
I, Shkarupa Alex <shkarupa.alex@gmail.com>, hereby add my Signed-off-by to this commit: e93602a0d02fdb6f6dea1f65686cffcc4c616011
Signed-off-by: Shkarupa Alex <shkarupa.alex@gmail.com>
---------
Signed-off-by: Shkarupa Alex <shkarupa.alex@gmail.com>
* 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>
* Provide the option to make remote services call concurrent
Signed-off-by: Vinay Damodaran <vrdn@hey.com>
* Use yield from correctly?
Signed-off-by: Vinay Damodaran <vrdn@hey.com>
* not do amateur hour stuff
Signed-off-by: Vinay Damodaran <vrdn@hey.com>
---------
Signed-off-by: Vinay Damodaran <vrdn@hey.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>
* 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>
* 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>
* 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>
* chore(xml-jats): separate authors and affiliations
In XML PubMed (JATS) backend, convert authors and affiliations as they
are typically rendered on PDFs.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* fix(xml-jats): replace new line character by a space
Instead of removing new line character from text, replace it by a space character.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* feat(xml-jats): improve existing parser and extend features
Partially support lists, respect reading order, parse more sections, support equations, better text formatting.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* chore(xml-jats): rename PubMed objects to JATS
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* allow the artifacts_path to be defined as ENV
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add check if artifacts_path exists and is dir
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Filetype library may not identify some files as PDF. Leverage the file extension
as a simple solution.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* 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>
* added http header support for document converter and cli
Signed-off-by: Luke Harrison <Luke.Harrison1@ibm.com>
* fixed formatting and typing issues
Signed-off-by: Luke Harrison <Luke.Harrison1@ibm.com>
* use pydantic to parse dict
suggested by @dolfim-ibm
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Luke Harrison <luke.harrison1@ibm.com>
---------
Signed-off-by: Luke Harrison <Luke.Harrison1@ibm.com>
Signed-off-by: Luke Harrison <luke.harrison1@ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.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>
* 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>
* feat: add PATENT_USPTO as input format
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* feat: add USPTO backend parser
Add a backend implementation to parse patent applications and
grants from the United States Patent Office (USPTO).
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* refactor: change the name of the USPTO input format
Change the name of the patent USPTO input format to show the typical format (XML).
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* refactor: address several input formats with same mime type
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* refactor: group XML backend parsers in a subfolder
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* chore: add safe initialization of PatentUsptoDocumentBackend
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.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>
Signed-off-by: Abhishek Kumar <abhishekrocketeer@gmail.com>
Testing:
(.venv) mario@Abhisheks-MacBook-Air docling % docling https://arxiv.org/pdf/2206.01062 --document-timeout=10 --verbose
INFO:docling.document_converter:Going to convert document batch...
INFO:docling.pipeline.base_pipeline:Processing document 2206.01062v1.pdf
WARNING:docling.pipeline.base_pipeline:Document processing time (24.555 seconds) exceeded the specified timeout of 10.000 seconds
INFO:docling.document_converter:Finished converting document 2206.01062v1.pdf in 36.29 sec.
WARNING:docling.cli.main:Document /var/folders/d7/dsfkllxs0xs8x2t4fcjknj4c0000gn/T/tmpl6p08u5i/2206.01062v1.pdf failed to convert.
INFO:docling.cli.main:Processed 1 docs, of which 1 failed
INFO:docling.cli.main:All documents were converted in 36.29 seconds.
(.venv) mario@Abhisheks-MacBook-Air docling % docling https://arxiv.org/pdf/2206.01062 --document-timeout=100 --verbose
INFO:docling.document_converter:Going to convert document batch...
INFO:docling.pipeline.base_pipeline:Processing document 2206.01062v1.pdf
INFO:docling.document_converter:Finished converting document 2206.01062v1.pdf in 58.36 sec.
INFO:docling.cli.main:writing Markdown output to 2206.01062v1.md
INFO:docling.cli.main:Processed 1 docs, of which 0 failed
INFO:docling.cli.main:All documents were converted in 58.56 seconds.
(.venv) mario@Abhisheks-MacBook-Air docling % docling https://arxiv.org/pdf/2206.01062 --verbose
INFO:docling.document_converter:Going to convert document batch...
INFO:docling.pipeline.base_pipeline:Processing document 2206.01062v1.pdf
INFO:docling.document_converter:Finished converting document 2206.01062v1.pdf in 59.82 sec.
INFO:docling.cli.main:writing Markdown output to 2206.01062v1.md
INFO:docling.cli.main:Processed 1 docs, of which 0 failed
INFO:docling.cli.main:All documents were converted in 59.88 seconds.
(.venv) mario@Abhisheks-MacBook-Air docling % docling
Usage: docling [OPTIONS] source
╭─ Arguments ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ * input_sources source PDF files to convert. Can be local file / directory paths or URL. [default: None] [required] │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─ Options ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ --from [docx|pptx|html|image|pdf|asciido Specify input formats to convert │
│ c|md|xlsx] from. Defaults to all formats. │
│ [default: None] │
│ --to [md|json|html|text|doctags] Specify output formats. Defaults to │
│ Markdown. │
│ [default: None] │
│ --image-export-mode [placeholder|embedded|referenced] Image export mode for the document │
│ (only in case of JSON, Markdown or │
│ HTML). With `placeholder`, only the │
│ position of the image is marked in │
│ the output. In `embedded` mode, the │
│ image is embedded as base64 encoded │
│ string. In `referenced` mode, the │
│ image is exported in PNG format and │
│ referenced from the main exported │
│ document. │
│ [default: embedded] │
│ --ocr --no-ocr If enabled, the bitmap content will │
│ be processed using OCR. │
│ [default: ocr] │
│ --force-ocr --no-force-ocr Replace any existing text with OCR │
│ generated text over the full │
│ content. │
│ [default: no-force-ocr] │
│ --ocr-engine [easyocr|tesseract_cli|tesseract| The OCR engine to use. │
│ ocrmac|rapidocr] [default: easyocr] │
│ --ocr-lang TEXT Provide a comma-separated list of │
│ languages used by the OCR engine. │
│ Note that each OCR engine has │
│ different values for the language │
│ names. │
│ [default: None] │
│ --pdf-backend [pypdfium2|dlparse_v1|dlparse_v2] The PDF backend to use. │
│ [default: dlparse_v2] │
│ --table-mode [fast|accurate] The mode to use in the table │
│ structure model. │
│ [default: fast] │
│ --artifacts-path PATH If provided, the location of the │
│ model artifacts. │
│ [default: None] │
│ --abort-on-error --no-abort-on-error If enabled, the bitmap content will │
│ be processed using OCR. │
│ [default: no-abort-on-error] │
│ --output PATH Output directory where results are │
│ saved. │
│ [default: .] │
│ --verbose -v INTEGER Set the verbosity level. -v for │
│ info logging, -vv for debug │
│ logging. │
│ [default: 0] │
│ --debug-visualize-cells --no-debug-visualize-cells Enable debug output which │
│ visualizes the PDF cells │
│ [default: no-debug-visualize-cells] │
│ --debug-visualize-ocr --no-debug-visualize-ocr Enable debug output which │
│ visualizes the OCR cells │
│ [default: no-debug-visualize-ocr] │
│ --debug-visualize-layout --no-debug-visualize-layout Enable debug output which │
│ visualizes the layour clusters │
│ [default: │
│ no-debug-visualize-layout] │
│ --debug-visualize-tables --no-debug-visualize-tables Enable debug output which │
│ visualizes the table cells │
│ [default: │
│ no-debug-visualize-tables] │
│ --version Show version information. │
│ --document-timeout FLOAT The timeout for processing each │
│ document, in seconds. │
│ [default: None] │
│ --help Show this message and exit. │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
* fix: main: Introduce format options for Image with the same pdf pipeline_options.
Add RapidOcrOptions to the Union of ocr_options for PdfPipelineOptions
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Silence the tqdm messages during the downloading of model files
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Code styling
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Use the HF API to disable the tqdm progress bars
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---------
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
