* 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>
Update data_prep_kit.md
The links were broken, since the repository was renamed. I also noticed that PDF2Parquet is now referred to as Docling2Parquet.
Signed-off-by: Oleg Lavrovsky <31819+loleg@users.noreply.github.com>
* feat: add milvus rag with docling tutorial
Signed-off-by: Ryan Lin <linjinhong@yandex.com>
* chore: run pre-commit
Signed-off-by: Ryan Lin <linjinhong@yandex.com>
* feat: add RAG with Milvus example to mkdocs
Signed-off-by: Ryan Lin <linjinhong@yandex.com>
---------
Signed-off-by: Ryan Lin <linjinhong@yandex.com>
Fixed the [Usage] link in architecture.md
Changed the usage link in the tip box from "../usage.md#adjust-pipeline-features" to "../usage/index.md#adjust-pipeline-features" as the previous link is not valid.
Signed-off-by: Leandro Rosas <36343022+leandrosas101@users.noreply.github.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>
* point the auxiliary files to the community repo and add lfai in README
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* update docs index
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-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>
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>
* docs: Introduce example with custom models for RapidOCR
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* chore: Exclude the example with custom RapidOCR models from the examples to run in github actions
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---------
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
