* chore: Update .gitignore with local dirs of AI agents
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* feat: Extend KserveV2OcrModel and kserve_v2_grpc.py to support the new version of Triton-RapidOCR
model where the language is the first input parameter:
- The gRPC client has been extended to encode BYTE input, needed for String types.
- An additional test ensures to have proper BYTE encoding/decoding.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* feat: Add test for the KServe-Triton integration: WIP
- The test currently supports only the gRPC KServe client
- Extend the ground-truth test data.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Simplify code in kserve test
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* chore: Rename test file
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* feat: Extend the kserve_v2 implementation to support binary data in the HTTP interface.
- Decouple functions for binary encoding/decoding inside the kserve_v2_utils.py and share for both HTTP and gRPC.
- Introduce use_binary_data init parameter in KserveV2OptionsMixin
- Improve tests
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Put back the field grpc_use_binary_data of KserveV2OptionsMixin as a deprecated alias to use_binary_data
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---------
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Use model_copy() instead of mutating code_formula_options in-place
during StandardPdfPipeline._init_models(). The in-place mutation
changed the hash of pipeline_options, causing initialize_pipeline()
to cache under one key while convert() computed a different key,
resulting in unnecessary pipeline re-initialization.
Fixes#3109
Signed-off-by: majiayu000 <1835304752@qq.com>
* feat: simplifying towards docling-parse v5
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* working on integrating docling-parse v5
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added the test_backend_docling_parse
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* Updated the docling-parse to 5.3.0
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* ran the pre-commit
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fixed the backend_docling_parse
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* ran pre-commit
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updated the groundtruth to deal with rounding errors
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updated comments for later docling-parse integrations
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* ran pre-commit
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* Make DoclingParseV2 and DoclingParseV4 backend stubs that route to new backend, emit warning.
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* lock docling-parse
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* updated to 3.5.2
Signed-off-by: Peter Staar <taa@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 <dol@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
* fix: Respect document_timeout in new threaded StandardPdfPipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* add test case to test_options
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Make sure unprocessed pages are not getting into assemble_document
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>
fix: Support for RTL programmatic documents
fix(parser): detect and handle rotated pages
fix(parser): fix bug causing duplicated text
fix(formula): improve stopping criteria
chore: update lock file
fix: temporary constrain beautifulsoup
* switch to code formula model v1.0.1 and new test pdf
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* switch to code formula model v1.0.1 and new test pdf
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* cleaned up the data folder in the tests
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* switch to code formula model v1.0.1 and new test pdf
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* added three test-files for right-to-left
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fix black
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* added new gt for test_e2e_conversion
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* added new gt for test_e2e_conversion
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* Add code to expose text direction of cell
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* new test file
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* update lock
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* fix mypy reports
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* fix example filepaths
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add test data results
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* pin wheel of latest docling-parse release
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* use latest docling-core
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* remove debugging code
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* fix path to files in example
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* Revert unwanted RTL additions
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix test data paths in examples
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@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 <dol@zurich.ibm.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Peter Staar <taa@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.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>
Nikos Livathinos
Hemanth Battu
lif
Peter W. J. Staar
jspast
Christoph Auer
Michele Dolfi