Update docling-core dependency to version 2.23.3.
Fix regression test of HTML backend after docling-core dependency update.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Fixing function return
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Add message
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.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>
* fix: Improve OCR results, stricten criteria before dropping bitmap areas (#719)
fix: Properly care for all bitmap elements in OCR
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Adam Kliment <adam@netmilk.net>
* chore: bump version to 2.15.1 [skip ci]
* Actor: Initial implementation
Signed-off-by: Václav Vančura <commit@vancura.dev>
Signed-off-by: Adam Kliment <adam@netmilk.net>
* Actor: .dockerignore update
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Adding the Actor badge
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Moving the badge where it belongs
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Documentation update
Signed-off-by: Václav Vančura <commit@vancura.dev>
Signed-off-by: Adam Kliment <adam@netmilk.net>
* Actor: Switching Docker to python:3.11-slim-bookworm
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Enhance Docker security with proper user permissions
- Set proper ownership and permissions for runtime directory.
- Switch to non-root user for enhanced security.
- Use `--chown` flag in COPY commands to maintain correct file ownership.
- Ensure all files and directories are owned by `appuser`.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Optimize Dockerfile with security and size improvements
- Combine RUN commands to reduce image layers and overall size.
- Add non-root user `appuser` for improved security.
- Use `--no-install-recommends` flag to minimize installed packages.
- Install only necessary dependencies in a single RUN command.
- Maintain proper cleanup of package lists and caches.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Add Docker image metadata labels
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Update dependencies with fixed versions
Upgrade pip and npm to latest versions, pin docling to 2.15.1 and apify-cli to 2.7.1 for better stability and reproducibility. This change helps prevent unexpected behavior from dependency updates and ensures consistent builds across environments.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Fix apify-cli version problem
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Create Apify user home directory in Docker setup
Add and configure `/home/appuser/.apify` directory with proper permissions for the appuser in the Docker container. This ensures the Apify SDK has a writable home directory for storing its configuration and temporary files.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Update Docker configuration for improved security
- Add `ACTOR_PATH_IN_DOCKER_CONTEXT` argument to ignore the Apify-tooling related warning.
- Improve readability with consistent formatting and spacing in RUN commands.
- Enhance security by properly setting up appuser home directory and permissions.
- Streamline directory structure and ownership for runtime operations.
- Remove redundant `.apify` directory creation as it's handled by the CLI.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Improve shell script robustness and error handling
The shell script has been enhanced with better error handling, input validation, and cleanup procedures. Key improvements include:
- Added proper quoting around variables to prevent word splitting.
- Improved error messages and logging functionality.
- Implemented a cleanup trap to ensure temporary files are removed.
- Enhanced validation of input parameters and output formats.
- Added better handling of the log file and its storage.
- Improved command execution with proper evaluation.
- Added comments for better code readability and maintenance.
- Fixed potential security issues with proper variable expansion.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Improve script logging and error handling
- Initialize log file at `/tmp/docling.log` and redirect all output to it
- Remove exit on error trap, now only logs error line numbers
- Use temporary directory for timestamp file
- Capture Docling exit code and handle errors more gracefully
- Update log file references to use `LOG_FILE` variable
- Remove local log file during cleanup
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Updating Docling to 2.17.0
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Adding README
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: README update
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Enhance Dockerfile with additional utilities and env vars
- Add installation of `time` and `procps` packages for better resource monitoring.
- Set environment variables `PYTHONUNBUFFERED`, `MALLOC_ARENA_MAX`, and `EASYOCR_DOWNLOAD_CACHE` for improved performance.
- Create a cache directory for EasyOCR to optimize storage usage.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: README update
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Adding the Apify FirstPromoter integration
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Adding the "Run on Apify" button
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Fixing example PDF document URLs
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Documentation update
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Adding input document URL validation
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Fix quoting in `DOC_CONVERT_CMD` variable
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Documentation update
Removing the dollar signs due to what we discovered at https://cirosantilli.com/markdown-style-guide/#dollar-signs-in-shell-code
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Add specific error codes for better error handling
- `ERR_INVALID_INPUT` for missing document URL
- `ERR_URL_INACCESSIBLE` for inaccessible URLs
- `ERR_DOCLING_FAILED` for Docling command failures
- `ERR_OUTPUT_MISSING` for missing or empty output files
- `ERR_STORAGE_FAILED` for failures in storing the output document
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Enhance error handling and data logging
- Add `apify pushData` calls to log errors when the document URL is missing or inaccessible.
- Introduce dataset record creation with processing results, including a success status and output file URL.
- Modify completion message to indicate successful processing and provide a link to the results.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Normalize key-value store terminology
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Enhance `README.md` with output details
Added detailed information about the Actor's output storage to the `README.md`. This includes specifying where processed documents, processing logs, and dataset records are stored.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Adding CHANGELOG.md
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Adding dataset schema
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Update README with output URL details
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Fix the Apify call syntax and final result URL message
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Add section on Actors to README
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Replace Docling CLI with docling-serve API
This commit transitions the Actor from using the full Docling CLI package to the more lightweight docling-serve API. Key changes include:
- Redesign Dockerfile to use docling-serve as base image
- Update actor.sh to communicate with API instead of running CLI commands
- Improve content type handling for various output formats
- Update input schema to align with API parameters
- Reduce Docker image size from ~6GB to ~600MB
- Update documentation and changelog to reflect architectural changes
The image size reduction will make the Actor more cost-effective for users while maintaining all existing functionality including OCR capabilities.
Issue: No official docling-serve Docker image is currently available, which will be addressed in a future commit.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Overhaul the implementation using official docling-serve image
This commit completely revamps the Actor implementation with two major improvements:
1) CRITICAL CHANGE: Switch to official docling-serve image
* Now using quay.io/ds4sd/docling-serve-cpu:latest as base image
* Eliminates need for custom docling installation
* Ensures compatibility with latest docling-serve features
* Provides more reliable and consistent document processing
2) Fix Apify Actor KVS storage issues:
* Standardize key names to follow Apify conventions:
- Change "OUTPUT_RESULT" to "OUTPUT"
- Change "DOCLING_LOG" to "LOG"
* Add proper multi-stage Docker build:
- First stage builds dependencies including apify-cli
- Second stage uses official image and adds only necessary tools
* Fix permission issues in Docker container:
- Set up proper user and directory permissions
- Create writable directories for temporary files and models
- Configure environment variables for proper execution
3) Solve EACCES permission errors during CLI version checks:
* Create temporary HOME directory with proper write permissions
* Set APIFY_DISABLE_VERSION_CHECK=1 environment variable
* Add NODE_OPTIONS="--no-warnings" to suppress update checks
* Support --no-update-notifier CLI flag when available
4) Improve code organization and reliability:
* Create reusable upload_to_kvs() function for all KVS operations
* Ensure log files are uploaded before tools directory is removed
* Set proper MIME types based on output format
* Add detailed error reporting and proper cleanup
* Display final output URLs for easy verification
This major refactoring significantly improves reliability and maintainability by leveraging the official docling-serve image while solving persistent permission and storage issues. The Actor now properly follows Apify standards while providing a more robust document processing pipeline.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Refactor `actor.sh` and add `docling_processor.py`
Refactor the `actor.sh` script to modularize functions for finding the Apify CLI, setting up a temporary environment, and cleaning it up. Introduce a new function, `get_actor_input()`, to handle input detection more robustly. Replace inline Python conversion logic with an external script, `docling_processor.py`, for processing documents via the docling-serve API.
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Update CHANGELOG and README for Docker and API changes
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Removing obsolete actor.json keys
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Fixed input getter
Signed-off-by: Adam Kliment <adam@netmilk.net>
* Actor: Always output a zip
Signed-off-by: Adam Kliment <adam@netmilk.net>
* Actor: Resolving conflicts with main
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Resolving conflicts with main (pass 2)
Signed-off-by: Václav Vančura <commit@vancura.dev>
* Actor: Updated main Readme and Actor Readme
Signed-off-by: Adam Kliment <adam@netmilk.net>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Adam Kliment <adam@netmilk.net>
Signed-off-by: Václav Vančura <commit@vancura.dev>
Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Adam Kliment <adam@netmilk.net>
* Equation groups
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix: Proper handling of orphan IDs in layout postprocessing (#1118)
* Fix the handling of orphan IDs in layout postprocessing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test cases
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* chore: bump version to 2.25.2 [skip ci]
* docs: add description of DOCLING_ARTIFACTS_PATH env var (#1124)
add env var in docs
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* fix(CLI): fix help message for abort options (#1130)
fix help message
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* perf: New revision code formula model and document picture classifier (#1140)
* new version code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new version document picture classifier
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* restored original code formula test pdf
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
---------
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* feat: Use new TableFormer model weights and default to accurate model version (#1100)
* 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>
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* chore: bump version to 2.26.0 [skip ci]
* fix: Pass tests, update docling-core to 2.22.0 (#1150)
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>
* Updating content hash
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Matteo <43417658+Matteo-Omenetti@users.noreply.github.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.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>
* 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>
* new version code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new version document picture classifier
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* new code formula model
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* restored original code formula test pdf
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
---------
Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
* Fix the handling of orphan IDs in layout postprocessing
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test cases
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* added the contentlayer to html-backend
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updated the handle_image function
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* reformatted code of html backend
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* test(html): add more info if a test case fails
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* refactor(html): put parsed item in body if doc has no header
In case an HTML does not have any header tag, all parsed items are placed in
DoclingDocument's body content layer.
HTML paragraphs ('p' tags) are parsed as text items with paragraph label.
Update test ground truth accoring to the changes above.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* chore: set TextItem label to 'text' instead of 'paragraph'
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Peter Staar <taa@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(html): use 'start' attribute in ordered lists
When parsing ordered lists in HTML, take into account the 'start' attribute if it exists.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* chore(html): reduce verbosity in HTML backend
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.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>
* test: avoid testing exact JSON
Avoid testing exact JSON output in html and xml backends.
Reuse the JSON verify helper function among backend test files.
Improve type annotations in html backend.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Update tests/test_backend_patent_uspto.py
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
* refactor: upgrade BeautifulSoup4 with type hints
Upgrade dependency library BeautifulSoup4 to 4.13.3 (with type hints).
Refactor backends using BeautifulSoup4 to comply with type hints.
Apply style simplifications and improvements for consistency.
Remove variables and functions that are never used.
Remove code duplication between backends for parsing HTML tables.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* build: allow beautifulsoup4 version 4.12.3
Allow older version of beautifulsoup4 and ensure compatibility.
Update library dependencies.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* Testing fix for docling-core dt
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
* fix: Fix code_formula test unit, update test-cases
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Fix code-formula model for new docling-core
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* fix: Update fixes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test cases for office formats
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update deps and lockfile
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Clean up imports
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@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>
