mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity
690 Commits 50 Branches 140 Tags
cce18b2ff7f14ab0643364055a1ec8a77479a211
Commit Graph

690 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Cesar Berrospi Ramis
cce18b2ff7 fix: deal with chartsheets in workbooks (#2433) 
* fix(xlsx): deal with chartsheets in workbooks

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* tests(xlsx): align test file names

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

---------

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
 2025-10-10 15:06:38 +02:00
Bruno Pio
f11f8c0a81 feat: Add Tesseract PSM options support (#2411) 
* feat: Add Tesseract PSM options support

Signed-off-by: Bruno Pio <913963+blap@users.noreply.github.com>

* apply formatting

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add tesseract_cli in checks

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Bruno Pio <913963+blap@users.noreply.github.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-10 14:44:30 +02:00
Victor Moreli
ee5501320e fix: skip temporary docx files (#2413) 
fix: CLI detects docx temporary files and breaks

Signed-off-by: Victor Moreli <victormoreli64@gmail.com>
 2025-10-10 09:39:26 +02:00
pixiake
b5f7fef29b fix: AsrPipeline to handle absolute paths and BytesIO streams correctly (#2407) 
Fix AsrPipeline to handle absolute paths and BytesIO streams correctly

Signed-off-by: pixiake <guofeng@spader-ai.com>
Co-authored-by: pixiake <guofeng@spader-ai.com>
 2025-10-10 09:37:15 +02:00
Utsav Talwar
f2854b2e1d docs: Add MongoDB + VoyageAI (#2382) 
Signed-off-by: Utsav Talwar <114057324+utsavMongoDB@users.noreply.github.com>
Co-authored-by: Utsav Talwar <114057324+utsavMongoDB@users.noreply.github.com>
 2025-10-07 14:36:19 -04:00
Michele Dolfi
0610d01afa fix: enrichment of documents without pages metadata (pptx and xlsx) (#2401) 
fix logic for pptx and xlsx

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-07 18:28:51 +02:00
Maxim Lysak
9705f4020c fix: Proper heading support in rich tables for HTML backend (#2394) 
* Fix for the proper headers support in rich tables in HTML

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* cleaning up

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Compatibility with older Python versions

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixing Furniture before the first heading rule

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added minimalistic test case

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* added html for the test

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
 2025-10-07 15:57:32 +02:00
Utsav Talwar
8a4b946a1a docs: add RAG example with MongoDB Atlas Vector Search and VoyageAI embeddings (#2341) 
* Add MongoDB RAG example

* Update MongoDB RAG Example

* Update MongoDB RAG Example

* Update MongoDB RAG Example

* DCO Remediation Commit for utsavMongoDB <utsav.talwar@mongodb.com>

I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: fbdbf53aa8
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 9b3065ba2b
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 1983f9db35
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 0522aa105d
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: f5a67e8012

Signed-off-by: utsavMongoDB <utsav.talwar@mongodb.com>

* DCO Remediation Commit for utsavMongoDB <utsav.talwar@mongodb.com>

I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: fbdbf53aa8
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 9b3065ba2b
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 1983f9db35
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 0522aa105d
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: f5a67e8012

Signed-off-by: utsavMongoDB <utsav.talwar@mongodb.com>

* docs: Add example with MongoDB

* DCO Remediation Commit for utsavMongoDB <utsav.talwar@mongodb.com>

I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: bb245a31ed
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 25436e543c

Signed-off-by: utsavMongoDB <utsav.talwar@mongodb.com>

* DCO Remediation Commit for utsavMongoDB <utsav.talwar@mongodb.com>

I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: bb245a31ed
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 25436e543c

Signed-off-by: utsavMongoDB <utsav.talwar@mongodb.com>

* DCO Remediation Commit for utsavMongoDB <utsav.talwar@mongodb.com>

I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: bb245a31ed
I, utsavMongoDB <utsav.talwar@mongodb.com>, hereby add my Signed-off-by to this commit: 25436e543c

Signed-off-by: utsavMongoDB <utsav.talwar@mongodb.com>

---------

Signed-off-by: utsavMongoDB <utsav.talwar@mongodb.com>
Signed-off-by: Utsav Talwar <114057324+utsavMongoDB@users.noreply.github.com>
 2025-10-03 13:29:43 +02:00
github-actions[bot]
22515b546a chore: bump version to 2.55.1 [skip ci] v2.55.1 2025-10-03 10:26:26 +00:00
Rui Dias Gomes
68230fe7e5 ci: split workflow to speedup CI runtime (#2313) 
* split workflow

Signed-off-by: rmdg88 <rmdg88@gmail.com>

* split workflow

Signed-off-by: rmdg88 <rmdg88@gmail.com>

* enable test_e2e_pdfs_conversions

Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Rui Dias Gomes <66125272+rmdg88@users.noreply.github.com>

* split workflow

Signed-off-by: rmdg88 <rmdg88@gmail.com>

* split workflow

Signed-off-by: rmdg88 <rmdg88@gmail.com>

* split workflow

Signed-off-by: rmdg88 <rmdg88@gmail.com>

* split workflow

Signed-off-by: rmdg88 <rmdg88@gmail.com>

* split workflow

Signed-off-by: rmdg88 <rmdg88@gmail.com>

* fix conflict files

Signed-off-by: rmdg88 <rmdg88@gmail.com>

---------

Signed-off-by: rmdg88 <rmdg88@gmail.com>
Signed-off-by: Rui Dias Gomes <66125272+rmdg88@users.noreply.github.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-03 11:16:38 +02:00
Matvei Smirnov
ee73ffae15 fix(markdown): Setext heading support (#2359) 
Signed-off-by: Matvei Smirnov <vdalekesmirnov@gmail.com>
Co-authored-by: Matvei Smirnov <matvei.smirnov@vkteam.ru>
 2025-10-03 10:32:53 +02:00
Hakeem Abbas
246de77d8c fix(docs): fixed the color scheme (#2371) 
* fix(docs): fixed the color scheme

Signed-off-by: Hakeem Abbas <hakeemsyd@gmail.com>

* fix(docs): colors background

Signed-off-by: Hakeem Abbas <hakeemsyd@gmail.com>

---------

Signed-off-by: Hakeem Abbas <hakeemsyd@gmail.com>
 2025-10-03 10:20:44 +02:00
Michele Dolfi
a975a790c9 docs: example using Hashicorp Vault PII transform (#2373) 
docs: add example using Hashicorp Vault PII transform

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-03 09:53:29 +02:00
Michele Dolfi
9505202e38 ci: update docling-parse and remove pages.json (#2372) 
* update docling-parse and remove pages.json

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* ocr gt

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-03 09:53:13 +02:00
Christoph Auer
ca2be7ff3a fix: Empty table handling (#2365) 
* add table raw cells when no table structure model was used

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Add RichTableCell instance for tables with missing structure.

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* update test results

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-02 19:35:16 +02:00
Lucas Morin
e6c3b05e63 docs: Jobkit and connectors (#2357) 
* feat: create documentation for docling-jobkit

Signed-off-by: Lucas Morin <lucas.morin222@gmail.com>

* small text fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Lucas Morin <lucas.morin222@gmail.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-10-02 13:46:56 +02:00
Michele Dolfi
4f295ed051 fix: add table raw content when no table structure model is used (#1815) 
* add table raw cells when no table structure model was used

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Add RichTableCell instance for tables with missing structure.

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
 2025-10-02 13:46:42 +02:00
github-actions[bot]
f0b630e24e chore: bump version to 2.55.0 [skip ci] v2.55.0 2025-09-30 14:50:42 +00:00
Christoph Auer
1e9dc43b72 feat: Repetition-based StoppingCriteria for GraniteDocling (#2323) 
* Experimental code for repetition detection, VLLM Streaming

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update VLLM Streaming

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update VLLM inference code, CLI and VLM specs

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix generation and decoder args for HF model

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix vllm device args

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Cleanup

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Bugfixes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Remove streaming VLLM for the moment

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add repetition StoppingCriteria for GraniteDocling/SmolDocling

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Make GenerationStopper base class and port for MLX

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add streaming support and custom GenerationStopper support for ApiVlmModel

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes for ApiVlmModel

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes for ApiVlmModel

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix api_image_request_streaming when GenerationStopper triggers.

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Move DocTagsRepetitionStopper to utility unit, update examples

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
 2025-09-30 15:26:09 +02:00
Michele Dolfi
68ae7ccf3c fix: pin wider range of typer (#2309) 
* pin larger range of typer

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update docling-core

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update deps

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update tests

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* lock docling-parse 4.5.0

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update results with docling-parse=4.4.0

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-09-30 08:42:23 +02:00
Christoph Auer
654c70f990 fix: Update Transformers & VLLM inference code, CLI and VLM specs (#2322) 
* Update VLLM inference code, CLI and VLM specs

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix generation and decoder args for HF model

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix vllm device args

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Cleanup

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Bugfixes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
 2025-09-29 21:06:54 +02:00
Maxim Lysak
c803abed9a feat: Rich tables support for HTML backend (#2324) 
* Rich tables support for HTML backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Decoupling JATS backend from HTML backend, ways of creating tables changed significantly

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* updated and added tests

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Refactored parse_table_data in html_backend into few smaller functions

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Changing scope of few functions in html_backend.py, making them static, when possible

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fix for HTML tables that have tbody and/or thead, now these tables are also properly supported

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
 2025-09-29 18:12:16 +02:00
Hakeem Abbas
325877aee9 docs(styling): update color scheme (#2154) 
* update the colors scheme

* update mkdocs.yml

* DCO Remediation Commit for Hakeem Abbas <hakeemsyd@gmail.com>

I, Hakeem Abbas <hakeemsyd@gmail.com>, hereby add my Signed-off-by to this commit: 861cb8ce6e
I, Hakeem Abbas <hakeemsyd@gmail.com>, hereby add my Signed-off-by to this commit: 72539fe5c0

Signed-off-by: Hakeem Abbas <hakeemsyd@gmail.com>

* update image

* DCO Remediation Commit for Hakeem Abbas <hakeemsyd@gmail.com>

I, Hakeem Abbas <hakeemsyd@gmail.com>, hereby add my Signed-off-by to this commit: 861cb8ce6e
I, Hakeem Abbas <hakeemsyd@gmail.com>, hereby add my Signed-off-by to this commit: 72539fe5c0
I, Hakeem Abbas <hakeemsyd@gmail.com>, hereby add my Signed-off-by to this commit: 1be2646643

Signed-off-by: Hakeem Abbas <hakeemsyd@gmail.com>

* undo image change

Signed-off-by: Hakeem Abbas <hakeemsyd@gmail.com>

---------

Signed-off-by: Hakeem Abbas <hakeemsyd@gmail.com>
 2025-09-29 11:44:40 +02:00
Luis
a873200c9d docs(vlm): Update SmolDocling to GraniteDocling references (#2315) 
Update minimal_vlm_pipeline.py

Signed-off-by: Luis <luis.rojas@ibm.com>
 2025-09-25 11:07:39 +02:00
Lucas Morin
9d67bb9ed6 fix: support escaped characters in markdown backend (#2304) 
fix: improve markdown backend to support input documents with escaped characters

Signed-off-by: Lucas Morin <lucas.morin222@gmail.com>
 2025-09-23 18:00:16 +02:00
github-actions[bot]
d599177547 chore: bump version to 2.54.0 [skip ci] v2.54.0 2025-09-22 15:28:30 +00:00
Maxim Lysak
e2482a2ada feat: Rich tables for MSWord backend (#2291) 
* Adding support of rich table cells to MSWord backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixes for properly accounting lists, pictures and headers in rich table cells

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Cleaned up msword backend, re-generated docx tests

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added detection of simple table cells in word backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Cleaned up

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
 2025-09-22 16:41:59 +02:00
Cesar Berrospi Ramis
46efaaefee feat: add a backend parser for WebVTT files (#2288) 
* feat: add a backend parser for WebVTT files

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* docs: update README with VTT support

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* docs: add description to supported formats

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* chore: upgrade docling-core to unescape WebVTT in markdown

Pin the new release of docling-core 2.48.2.
Do not escape HTML reserved characters when exporting WebVTT documents to markdown.

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* test: add missing copyright notice

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

---------

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
 2025-09-22 15:24:34 +02:00
manuflexor
b5628f1227 fix: correct y-axis scaling in draw_table_cells (#2287) 
* Fix y axis

* DCO Remediation Commit for manuflexor <imanuel@flexor.ai>

I, manuflexor <imanuel@flexor.ai>, hereby add my Signed-off-by to this commit: cd56622d4f

Signed-off-by: manuflexor <imanuel@flexor.ai>

---------

Signed-off-by: manuflexor <imanuel@flexor.ai>
 2025-09-19 13:42:29 +02:00
Christoph Auer
8b7e83a8c7 docs: Update API VLM example with granite-docling (#2294) 
chore: Update API VLM example with granite-docling

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
 2025-09-19 12:23:53 +02:00
Panos Vagenas
8322c2ea9b docs: fix examples rendering (#2281) 
fix examples rendering

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
 2025-09-17 20:50:50 -04:00
github-actions[bot]
f1687fb09b chore: bump version to 2.53.0 [skip ci] v2.53.0 2025-09-17 13:59:33 +00:00
Christoph Auer
17afb664d0 feat: Add granite-docling model (#2272) 
* 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>

* typo

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* use granite-docling and add to the model downloader

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update docs and README

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Update final repo_ids for GraniteDocling

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update final repo_ids for GraniteDocling

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix model name in CLI usage example

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

* Fix VLM model name in README.md

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Co-authored-by: Peter Staar <taa@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-09-17 15:15:49 +02:00
Mingxuan Zhao
ff351fd40c docs: Describe examples (#2262) 
* Update .py examples with clearer guidance,
update out of date imports and calls

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

* Fix minimal.py string error, fix ruff format error

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

* fix more CI issues

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

---------

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>
 2025-09-16 16:00:38 +02:00
dmorady1
0e95171dd6 feat(RapidOcr): Support generic extra arguments for RapidOcr (#2266) 
* feat: add support for additional parameters in RapidOcrOptions and fix RapidOcr font_path

* DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com>

I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060

Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com>

* fix: RapidOcr ensure backwards compatibility and add deprecation note

* add warning log for rec_font_path

* DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com>

I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f

Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com>

* add tests for code coverage for rapidocr

* DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com>

I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: af5df4bb30

Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com>

* add small comment for test

* DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com>

I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: af5df4bb30
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ab893b637f

Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com>

* fix test  comment

* DCO Remediation Commit for David Morady <29502285+dmorady1@users.noreply.github.com>

I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 133d989060
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 0a65eed28a
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ac96f1483f
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: af5df4bb30
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: ab893b637f
I, David Morady <29502285+dmorady1@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 028e332aa9

Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com>

---------

Signed-off-by: David Morady <29502285+dmorady1@users.noreply.github.com>
 2025-09-16 07:26:10 +02:00
Michele Dolfi
ad2f738231 chore: update lock (#2265) 
* update lock

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update changes from docling-core update

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-09-15 11:19:15 +02:00
Yuie.
609d902eef fix: handle empty result from RapidOCR to avoid crash (#2264) 
Signed-off-by: Junehyuk Park <yuie@evonit.net>
 2025-09-15 10:04:33 +02:00
github-actions[bot]
10bb0aee2d chore: bump version to 2.52.0 [skip ci] v2.52.0 2025-09-11 16:11:20 +00:00
Christoph Auer
0700af212c fix: Add missing features in ThreadedStandardPdfPipeline (#2252) 
Add missing features in ThreadedStandardPdfPipeline

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
 2025-09-11 16:26:02 +02:00
Michele Dolfi
2c9123419f feat: enrichment steps on all convert pipelines (incl docx, html, etc) (#2251) 
* allow enrichment on all convert pipelines

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* set options in CLI

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-09-11 15:09:00 +02:00
Michele Dolfi
c6965495a2 fix: address deprecation warnings of dependencies (#2237) 
* switch to dtype instead of torch_dtype

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* set __check_model__ to avoid deprecation warnings

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* remove dataloaders warnings in easyocr

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* suppress with option

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
 2025-09-10 14:38:34 +02:00
Cesar Berrospi Ramis
f8cc545bab docs: add an example of RAG with OpenSearch (#2238) 
* docs: add an example of RAG with OpeanSearch

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* chore: pin latest docling-core and update uv.lock

Pin latest version release of docling-core in pyproject.toml
Update the dependencies in uv.lock file
Run the notebook rag_opensearch.ipynb to pick up changes from docling-core

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

---------

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
 2025-09-10 14:37:22 +02:00
Roy Derks
e5cd7020bd docs: Add instructions for using Docling with MCP to README (#2219) 
* docs: Add instructions for using Docling with MCP to README

* DCO Remediation Commit for Roy Derks <10717410+royderks@users.noreply.github.com>

Signed-off-by: Roy Derks <roy.derks@ibm.com>

* DCO Remediation Commit for Roy Derks <10717410+royderks@users.noreply.github.com>

I, Roy Derks <10717410+royderks@users.noreply.github.com>, hereby add my Signed-off-by to this commit: 4b9ba1d0ef

Signed-off-by: Roy Derks <roy.derks@ibm.com>

* docs: reorganize documentation on MCP server

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* docs: align README with documentation index page

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

---------

Signed-off-by: Roy Derks <roy.derks@ibm.com>
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Co-authored-by: Roy Derks <roy.derks@ibm.com>
Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
 2025-09-10 10:02:28 +02:00
Tamás Bitai
55f5f3752f docs: Document VLM support requirement in extraction example (#2231) 
* docs: Document VLM support requirement in extraction example

* DCO Remediation Commit for Tamás Bitai <bitai.tamas@gmail.com>

I, Tamás Bitai <bitai.tamas@gmail.com>, hereby add my Signed-off-by to this commit: b90defdb77

Signed-off-by: Tamás Bitai <bitai.tamas@gmail.com>

---------

Signed-off-by: Tamás Bitai <bitai.tamas@gmail.com>
 2025-09-09 13:45:55 +02:00
github-actions[bot]
df60673992 chore: bump version to 2.51.0 [skip ci] v2.51.0 2025-09-05 13:01:33 +00:00
Peter W. J. Staar
b49d1ad4f1 feat: updating default parameters to get better performance with docling-parse (#2208) 
* updated the code

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the parameters

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-09-05 14:06:21 +02:00
Panos Vagenas
a9f41b088e docs: add information extraction example (#2199) 
* docs: add information exctraction example

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* update README

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* minor typo

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* update README

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

---------

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
 2025-09-05 11:27:09 +02:00
Peter W. J. Staar
b3d7542061 feat: updated the backend for new docling-parse (#2187) 
* updated the backend and pyproject.toml

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the version and test files

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the lock

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* forgot to add 1 updated test-file

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the lock

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
 2025-09-05 10:42:31 +02:00
Alina Ryan
2c3f6faf3d chore: update deprecation note for OcrEngine (#2200) 
This commit updates the deprecated note to correctly point to
get_ocr_factory().registered_kind.

Signed-off-by: Alina Ryan <aliryan@redhat.com>
 2025-09-05 08:24:14 +02:00
github-actions[bot]
3419c42f10 chore: bump version to 2.50.0 [skip ci] v2.50.0 2025-09-03 11:39:08 +00:00