* add example processing parquet file of images
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* vlm using vllm api
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* use openvino and add more docs
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* add default input file
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* change default to standard for running in CI
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* use simple rapidocr without openvino in the CI example
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* feat: add the Image backend
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fixed the pre-commit
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* Fixed single- versus multi-frame image formats
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fix: Proper usage of ImageDocumentBackend in the pipeline, deprecate old code.
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Adapt tests
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: correct mets_gbs backend test
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Make ImagePageBackend.get_bitmap_rects() yield
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>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
* adding granite-docling preview
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updated the model specs
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* Add Layout+VLM pipeline with prompt injection, ApiVlmModel updates
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update layout injection, move to experimental
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Adjust defaults
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Map Layout+VLM pipeline to GraniteDoclign
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Remove base_prompt from layout injection prompt
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Reinstate custom prompt
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* add demo_layout file that produces with vs without layout injection
Signed-off-by: Peter El Hachem <peter.el.hachem@ibm.com>
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* feat: wrap vlm_inference around process_images
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* feat: carry input prompt + number of input tokens
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* fix: adapt example to run on local test file
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* fix: example now expects single document
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* feat: add layout example to EXAMPLES_TO_SKIP
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* feat: address comments on git
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* feat: add inference wrapper for hf_transformers + carry input prompt
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* Feat: add track_input_prompt to ApiVlmOptions, and track input prompt as part of api vlm
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* fix: Ensure backward-compatible build_prompt by adding _internal_page ag
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Ensure backward-compatible build_prompt by adding _internal_page ag
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fixes for demo
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Typing fixes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Restoring lost changes in vllm_model
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Restoring vlm_pipeline_api_model example
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: Peter El Hachem <peter.el.hachem@ibm.com>
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
Co-authored-by: Peter Staar <taa@zurich.ibm.com>
Co-authored-by: ElHachem02 <peterelhachem02@gmail.com>
* fix(docx): parse page headers and footers
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): rename _add_header with _add_heading
To avoid confusion, rename _add_header function name with _add_heading
since the function is about adding section headings.
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): extend the page header and footer parsing to any content type
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): fix _add_header_footer function
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
---------
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): remove unnecessary import
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(docx): simplify parsing of simple tables
Simplify the parsing of tables with just text (no rich cells).
Move nested function group_cell_elements out of _handle_tables for readability.
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): reuse method for finding inline pictures
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): format strikethrough text
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* tests(docx): use fixtures to avoid converting same file multiple times
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(docx): remove unnecessary argument docx_obj in functions
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* tests(docx): add test for rich table cells
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): small improvements in backend and its unit tests
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(docx): parse superscript and subscript formatted text
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
---------
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(html): simplify parsing of simple table cells
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* tests(html): add test for rich table cells
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(html): ensure table cells with formatted text are parsed as RichTableCell
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* refactor(html): simplify process_rich_table_cells since only rich cells are processed
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(html): formatted cell runs should be parsed as text items respecting the order
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore: pin latest docling-core and update uv.lock
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore: upgrade dependencies on uv.lock
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
---------
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* feat: add enum StopReason and use it in VlmPrediction
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* add vlm_inference time for api calls and track stop reason
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* fix: rename enum to VlmStopReason
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* Propagate partial success status if page reaches max tokens
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
* feat: page with generation stopped by loop detector create partial success status
Signed-off-by: Peter El Hachem <peter.el.hachem@ibm.com>
* Add hint for future improvement
Signed-off-by: Peter El Hachem <peter.el.hachem@ibm.com>
* fix: remove vlm_stop_reason from extracted page data, add UNSPECIFIED state as VlmStopReason to avoid null value
Signed-off-by: Peter El Hachem <peter.el.hachem@ibm.com>
---------
Signed-off-by: ElHachem02 <peterelhachem02@gmail.com>
Signed-off-by: Peter El Hachem <peter.el.hachem@ibm.com>
Co-authored-by: Peter El Hachem <peter.el.hachem@ibm.com>
* fix(ocr): use PSM integer values directly instead of constructor
- Use integer psm value directly instead of calling tesserocr.PSM()
- Fixed in both main_psm and script_readers initialization
- tesserocr.PSM is a class with integer constants, not an enum
Fixes#2576
* DCO Remediation Commit for mulgyeol <mulgyeoljung@gmail.com>
I, mulgyeol <mulgyeoljung@gmail.com>, hereby add my Signed-off-by to this commit: da63a17a3c
Signed-off-by: mulgyeol <mulgyeoljung@gmail.com>
---------
Signed-off-by: mulgyeol <mulgyeoljung@gmail.com>
* fix: xlsx doc parsing, now returning values instead of formulas
Signed-off-by: glypt <8trash-can8@protonmail.ch>
* fix: add test for better coverage of xlsx backend
Signed-off-by: glypt <8trash-can8@protonmail.ch>
* fix: add the total of ducks as a formula in the tests/data
This also adds the test that the value 310 is contained in the table.
Without the fix from the previous commit, it would return "B7+C7"
Signed-off-by: glypt <8trash-can8@protonmail.ch>
---------
Signed-off-by: glypt <8trash-can8@protonmail.ch>
* docs(opensearch): update the example notebook RAG with OpenSearch
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* docs(uspto): remove direct usage of the backend class for conversion
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* docs: remove direct usage of backends from documentation
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
---------
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* feat: add backend options support to document backends
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* feat: enhance document backends with generic backend options and improve HTML image handling
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* Refactor tests for declarativebackend
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(HTML): improve image caption handling and ensure backend options are set correctly
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix: enhance HTML backend image handling and add support for local file paths
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore: Add ground truth data for test data
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(HTML): skip loading SVG files in image data handling
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* refactor(html): simplify backend options and address gaps
Backend options for DeclarativeDocumentBackend classes and only when necessary.
Refactor caption parsing in 'img' elements and remove dummy text.
Replace deprecated annotations from Typing library with native types.
Replace typing annotations according to pydantic guidelines.
Some documentation with pydantic annotations.
Fix diff issue with test files.
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* tests(html): add tests and fix bugs
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* refactor(html): refactor backend options
Move backend option classes to its own module within datamodel package.
Rename 'source_location' with 'source_uri' in HTMLBackendOptions.
Rename 'image_fetch' with 'fetch_images' in HTMLBackendOptions.
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* refactor(markdown): create a class for the markdown backend options
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
---------
Signed-off-by: Leg0shii <dragonsaremyfavourite@gmail.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* add mlx-whisper support
* added mlx-whisper example and test. update docling cli to use MLX automatically if present.
* fix pre-commit checks and added proper type safety
* fixed linter issue
* DCO Remediation Commit for Ken Steele <ksteele@gmail.com>
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: a979a680e1dc2fee8461401335cfb5dda8cfdd98
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: 9827068382ca946fe1387ed83f747ae509fcf229
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: ebbeb45c7dc266260e1fad6bdb54a7041f8aeed4
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: 2f6fd3cf46c8ca0bb98810191578278f1df87aa3
Signed-off-by: Ken Steele <ksteele@gmail.com>
* fix unit tests and code coverage for CI
* DCO Remediation Commit for Ken Steele <ksteele@gmail.com>
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: 5e61bf11139a2133978db2c8d306be6289aed732
Signed-off-by: Ken Steele <ksteele@gmail.com>
* fix CI example test - mlx_whisper_example.py defaults to tests/data/audio/sample_10s.mp3 if no args specified.
Signed-off-by: Ken Steele <ksteele@gmail.com>
* refactor: centralize audio file extensions and MIME types in base_models.py
- Move audio file extensions from CLI hardcoded set to FormatToExtensions[InputFormat.AUDIO]
- Add support for additional audio formats: m4a, aac, ogg, flac, mp4, avi, mov
- Update FormatToMimeType mapping to include MIME types for all audio formats
- Update CLI auto-detection to use centralized FormatToExtensions mapping
- Add comprehensive tests for audio file auto-detection and pipeline selection
- Ensure explicit pipeline choices are not overridden by auto-detection
Fixes issue where only .mp3 and .wav files were processed as audio despite
CLI auto-detection working for all formats. The document converter now
properly recognizes all audio formats through MIME type detection.
Addresses review comments:
- Centralizes audio extensions in base_models.py as suggested
- Maintains existing auto-detection behavior while using centralized data
- Adds proper test coverage for the audio detection functionality
All examples and tests pass with the new centralized approach.
All audio formats (mp3, wav, m4a, aac, ogg, flac, mp4, avi, mov) now work correctly.
Signed-off-by: Ken Steele <ksteele@gmail.com>
* feat: address reviewer feedback - improve CLI auto-detection and add explicit model options
Review feedback addressed:
1. Fix CLI auto-detection to only switch to ASR pipeline when ALL files are audio
- Previously switched if ANY file was audio, now requires ALL files to be audio
- Added warning for mixed file types with guidance to use --pipeline asr
2. Add explicit WHISPER_X_MLX and WHISPER_X_NATIVE model options
- Users can now force specific implementations if desired
- Auto-selecting models (WHISPER_BASE, etc.) still choose best for hardware
- Added 12 new explicit model options: _MLX and _NATIVE variants for each size
CLI now supports:
- Auto-selecting: whisper_tiny, whisper_base, etc. (choose best for hardware)
- Explicit MLX: whisper_tiny_mlx, whisper_base_mlx, etc. (force MLX)
- Explicit Native: whisper_tiny_native, whisper_base_native, etc. (force native)
Addresses reviewer comments from @dolfim-ibm
Signed-off-by: Ken Steele <ksteele@gmail.com>
* DCO Remediation Commit for Ken Steele <ksteele@gmail.com>
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: c60e72d2b5
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: 94803317a3
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: 21905e8ace
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: 96c669d155
I, Ken Steele <ksteele@gmail.com>, hereby add my Signed-off-by to this commit: 8371c060ea
Signed-off-by: Ken Steele <ksteele@gmail.com>
* test(asr): add coverage for MLX options, pipeline helpers, and VLM prompts
- tests/test_asr_mlx_whisper.py: verify explicit MLX options (framework, repo ids)
- tests/test_asr_pipeline.py: cover _has_text/_determine_status and backend support with proper InputDocument/NoOpBackend wiring
- tests/test_interfaces.py: add BaseVlmPageModel.formulate_prompt tests (RAW/NONE/CHAT, invalid style), with minimal InlineVlmOptions scaffold
Improves reliability of ASR and VLM components by validating configuration paths and helper logic.
Signed-off-by: Ken Steele <ksteele@gmail.com>
* test(asr): broaden coverage for model selection, pipeline flows, and VLM prompts
- tests/test_asr_mlx_whisper.py
- Add MLX/native selector coverage across all Whisper sizes
- Validate repo_id choices under MLX and Native paths
- Cover fallback path when MPS unavailable and mlx_whisper missing
- tests/test_asr_pipeline.py
- Relax silent-audio assertion to accept PARTIAL_SUCCESS or SUCCESS
- Force CPU native path in helper tests to avoid torch in device selection
- Add language handling tests for native/MLX transcribe
- Cover native run success (BytesIO) and failure (exception) branches
- Cover MLX run success/failure branches with mocked transcribe
- Add init path coverage with artifacts_path
- tests/test_interfaces.py
- Add focused VLM prompt tests (NONE/CHAT variants)
Result: all tests passing with significantly improved coverage for ASR model selectors, pipeline execution paths, and VLM prompt formulation.
Signed-off-by: Ken Steele <ksteele@gmail.com>
* simplify ASR model settings (no pipeline detection needed)
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* clean up disk space in runners
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Ken Steele <ksteele@gmail.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
