* feat: Switch default layout model to DOCLING_LAYOUT_HERON. Update the unit test data.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* Use default layout model in model_downloader default args
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Use default layout model in model_downloader default args
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update docling-models tag for TableFormer
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test GT
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update test GT (from linux CPU)
Signed-off-by: Ubuntu <ubuntu@ip-172-31-30-253.eu-central-1.compute.internal>
* fix: Ensure that the visualisations happen on copies of the page image
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* chore: Pinpoint docling-ibm-models to the fix branch for the ReadingOrderPredictor
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* chore: Update uv.lock
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* chore: Update tests GT to match the Heron layout model and the improved reading order model in Linux
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* fix: Introduce the verify_doctags optional parameter in conversion tests to control if a doctags
comparison should take place. Skip doctags comparisons for certain tests.
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* chore: Generate tests GT on Mac
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
* chore: Remove the pinning of the docling-ibm-models and use the release 3.9.1
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---------
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Ubuntu <ubuntu@ip-172-31-30-253.eu-central-1.compute.internal>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-30-253.eu-central-1.compute.internal>
* Fix OCR bounding box misalignment caused by rotation metadata
Signed-off-by: AndrewTsai0406 <tsai247365@gmail.com>
* Add rotation-mismatch scanned pdf test case
Signed-off-by: AndrewTsai0406 <tsai247365@gmail.com>
* add ground truth for ocr_test_rotation_mismatch.pdf
Signed-off-by: AndrewTsai0406 <tsai247365@gmail.com>
* add ground truth for ocr_test_rotation_mismatch.pdf
Signed-off-by: AndrewTsai0406 <tsai247365@gmail.com>
* Updated test GT and merged from main
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix OCR test by excluding mismatched rotation example
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: AndrewTsai0406 <tsai247365@gmail.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
* Add DocumentConverter.extract and full extraction pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add DocumentConverter.extract template arg
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add NuExtract model
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add Extraction pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add proper test, support pydantic class types
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add qr bill example
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add base_extraction_pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add types
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update typing of ExtractionResult and inner fields
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Factor out extract to DocumentExtractor
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Address mypy issues
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add DocumentExtractor
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Resolve circular import issue
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Clean up imports, remove Optional for template arg
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Move new type definitions into datamodel
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Update comments
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Respect page-range, disable test_extraction for CI
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* chore(html): refactor parser to leverage context managers
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(html): parse inline code snippets, also from list items
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* chore(html): remove hidden tags
Remove tags that are not meant to be displayed.
Add regression tests for code blocks, inline code, and hidden tags.
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
---------
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* feat: exploring new version
* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 5815c8f81b0e5ce400332597b6795e5a97ecf775
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
* chore: autoformat
DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 5815c8f81b0e5ce400332597b6795e5a97ecf775
* feat: enable configurable runtime for rapidocr and handle new result better;
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
* chore: fix linter
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
* chore: use new server model
* chore: change default engine type to onnx
* chore: tests update for new rapidocr
* fix: rebase from main and fix clashes
* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 5815c8f81b0e5ce400332597b6795e5a97ecf775
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 02f9db85f562e5cdfda40c52fee55cfd4030d70a
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: a7bcb205faedb881f94a89b3bbd29cb31ccd54f0
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: a39482a98cbcff7a825c8321134732af0c65930a
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 63e9d717fa26951566b02761f3fdfc752c31f805
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: ef12a6ec1ea2846a8a8e2e776eeaa59c2a0c4dfe
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 2222d2340387f8d9d66f3ca9d8e21a0945a44e7a
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: bc6a1dc507d7f146ec4797a2d3840414f46ac64d
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 56e0d67da7c57d4b5caf8eaef8dff7056c3efd32
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 871ca21271412006c76acf3c19426140efed3d50
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 7b1b77159da729d483a581a86c7309acba1712a7
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: a792a714a43e19a91b2b782f54621c1c5efda632
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: d1fed26323ff829b716bc667fe69532839363e45
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 346ec1cad943765f886e5d17fb0a54221124689c
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 4d0bbe5bd6e9f7261b97362ff8823af244267089
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 34a5ad53892a7064a6bf35f890d344d464c78b2f
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 9151959db3ad53535011d1cfdcf9181fdf936bb1
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 8ef5536f2c098826c6c0a05190f8a80614c3f3cb
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 7e18637a35
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 63fb8ff599
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 0cb9444fb8
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 38940d9978
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: b6d461ac42
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: ee55eb3408
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
---------
Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
* Show converted page count in PaginatedPipeline debug statement
* DCO Remediation Commit for Raphael Norman-Tenazas <tenazasr@gmail.com>
I, Raphael Norman-Tenazas <tenazasr@gmail.com>, hereby add my Signed-off-by to this commit: b7930bf56d
Signed-off-by: Raphael Norman-Tenazas <tenazasr@gmail.com>
* Show total progress instead of batch size
Signed-off-by: Raphael Norman-Tenazas <tenazasr@gmail.com>
---------
Signed-off-by: Raphael Norman-Tenazas <tenazasr@gmail.com>
* Added option to docling-tools to download arbitrary HuggingFace model
Signed-off-by: Viktor Kuropiatnyk <vku@zurich.ibm.com>
* Added note in documentation
Signed-off-by: Viktor Kuropiatnyk <vku@zurich.ibm.com>
* Removed note on custom artifact path usage from HF download option
Signed-off-by: Viktor Kuropiatnyk <vku@zurich.ibm.com>
* Fixed typo
Signed-off-by: Viktor Kuropiatnyk <vku@zurich.ibm.com>
---------
Signed-off-by: Viktor Kuropiatnyk <vku@zurich.ibm.com>
* Prepare existing codes for use with new multi-stage VLM pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add multithreaded VLM pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add VLM task interpreters
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add VLM task interpreters
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Remove prints
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Fix KeyboardInterrupt behaviour
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add VLLM backend support, optimize process_images
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Tweak defaults
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Implement proper batch inference for HuggingFaceTransformersVlmModel
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Small fixes
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Cleanup hf_transformers_model batching impl
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Adjust example instatiation of multi-stage VLM pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add GoT OCR 2.0
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Factor out changes without multi-stage pipeline
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Reset defaults for generation
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Cleanup
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add torch.compile, fix temperature setting in gen_kwargs
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Expose page_batch_size on CLI
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Add torch_dtype bfloat16 to SMOLDOCLING and SMOLVLM model spec
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Clip off pad_token
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
* Notebook showing example on how to use docling transforms in DPK
Signed-off-by: Maroun Touma <touma@us.ibm.com>
* fix HF Token name
Signed-off-by: Maroun Touma <touma@us.ibm.com>
* use %pip instead of pip install jupyter lab
Signed-off-by: Maroun Touma <touma@us.ibm.com>
* run formatter
Signed-off-by: Maroun Touma <touma@us.ibm.com>
* add example to mkdocs and fix typo
Signed-off-by: Maroun Touma <touma@us.ibm.com>
---------
Signed-off-by: Maroun Touma <touma@us.ibm.com>
* fix(HTML): parse footer tag as a section in furniture
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* fix(HTML): add test for body vs furniture in HTML parser.
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
---------
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
* ⚡️ Speed up function `_parse_orientation` by 242%
Here’s how you should rewrite the code for **maximum speed** based on your profiler.
- The _bottleneck_ is the line
```python
orientations = df_osd.loc[df_osd["key"] == "Orientation in degrees"].value.tolist()
```
This does a dataframe filtering (`loc`) and then materializes a list for every call, which is slow.
- We can **vectorize** this search (avoid repeated boolean masking and conversion).
- Instead of `.loc[df_osd["key"] == ...].value.tolist()`, use `.at[idx, 'value']` where `idx` is the first index where key matches, or better, `.values[0]` after a fast boolean mask.
- Since you only use the *first* matching value, you don’t need the full filtered column.
- You can optimize `parse_tesseract_orientation` by.
- Storing `CLIPPED_ORIENTATIONS` as a set for O(1) lookup if it isn't already (can't change the global so just memoize locally).
- Remove unnecessary steps.
**Here is your optimized code:**
**Why is this faster?**
- `_fast_get_orientation_value`:
- Avoids all index alignment overhead of `df.loc`.
- Uses numpy arrays under the hood (thanks to `.values`) for direct boolean masking and fast nonzero lookup.
- Fetches just the first match directly, skipping conversion to lists.
- Only fetches and processes the single cell you actually want.
**If you’re sure there’s always exactly one match:**
You can simplify `_fast_get_orientation_value` to.
Or, if always sorted and single.
---
- **No semantics changed.**
- **Comments unchanged unless part modified.**
This approach should reduce the time spent in `_parse_orientation()` by almost two orders of magnitude, especially as the DataFrame grows.
Let me know if you want further micro-optimizations (e.g., Cython, pre-fetched numpy conversions, etc.)!
* fix: pandas vet error
* DCO Remediation Commit for mohammed <mohammed18200118@gmail.com>
I, mohammed <mohammed18200118@gmail.com>, hereby add my Signed-off-by to this commit: d9824749bb
Signed-off-by: mohammed <mohammed18200118@gmail.com>
* Dummy commit to trigger CI
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: mohammed <mohammed18200118@gmail.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
* re-implement links for html backend.
Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch>
* fix inline groups in list items. write specific test for find_parent_annotation of _extract_text_and_hyperlink_recursively.
Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch>
* implement hack for images.
Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch>
---------
Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch>
* Add ability to preprocess VLM response
Signed-off-by: Shkarupa Alex <shkarupa.alex@gmail.com>
* Move response decoding to vlm options (requires inheritance to override). Per-page prompt formulation also moved to vlm options to keep api consistent.
Signed-off-by: Shkarupa Alex <shkarupa.alex@gmail.com>
---------
Signed-off-by: Shkarupa Alex <shkarupa.alex@gmail.com>
* feat: add convert_string to document-converter
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* fix unsupported operand type(s) for |: type and NoneType
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* added tests for convert_string
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
---------
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* use re to stop at first non-digit
Signed-off-by: Maroun Touma <touma@us.ibm.com>
* Allow digit in first place followed by non numerical values
Signed-off-by: Maroun Touma <touma@us.ibm.com>
* refactor to match type checker
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---------
Signed-off-by: Maroun Touma <touma@us.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
