Peter W. J. Staar fd834204fa feat: Support for GraniteVision v4 (#3217) ...

* feat: add GV4

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

* got everything to work with granite-vision-4

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

* robustifying the output of granite-vision-v4

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

* refactored the code to reduce duplications:

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

* refactored the code to align with pipeline options

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

* ran pre-commit

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

* fixed the circular import

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

* added the chart_extraction_options file

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

---------

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

2026-04-10 08:55:40 +02:00

..

data

docs: add granite vision for charts (#2946)

2026-02-03 12:31:27 +01:00

experimental

docs(example): fix update sample image path to be relative (#2864)

2026-01-09 12:46:48 +01:00

legacy

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

advanced_chunking_and_serialization.ipynb

feat: Enrichment annotations in the new meta format (#2859)

2026-01-08 18:28:52 +01:00

asr_pipeline_performance_comparison.py

feat(ASR): MLX Whisper Support for Apple Silicon (#2366)

2025-10-21 08:05:59 +02:00

backend_csv.ipynb

feat: Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945)

2025-02-14 08:55:09 +01:00

backend_xml_rag.ipynb

docs: update opensearch notebook and backend documentation (#2519)

2025-10-27 10:02:50 +01:00

batch_convert.py

feat: Introduce docling-parse v5 and deprecate old docling-parse backends (#2872)

2026-02-17 20:27:56 +01:00

chart_extraction.py

feat: Support for GraniteVision v4 (#3217)

2026-04-10 08:55:40 +02:00

code_formula_granite_docling.py

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

compare_vlm_models.py

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

custom_convert.py

fix: correct type hint for table_structure_options usage (#2823)

2026-01-06 08:59:43 +01:00

demo_layout_vlm.py

fix: Ensure proper image_scale for generated page images in VLM pipelines (#2728)

2025-12-05 13:16:11 +01:00

develop_formula_understanding.py

docs: Describe examples (#2262)

2025-09-16 16:00:38 +02:00

develop_picture_enrichment.py

feat: Enrichment annotations in the new meta format (#2859)

2026-01-08 18:28:52 +01:00

dpk-ingest-chunk-tokenize.ipynb

docs: add information extraction example (#2199)

2025-09-05 11:27:09 +02:00

enrich_doclingdocument.py

feat: Unified model-family inference engines (including image-classification) and KServe v2 API support (#2979)

2026-02-18 10:49:19 +01:00

enrich_simple_pipeline.py

feat: enrichment steps on all convert pipelines (incl docx, html, etc) (#2251)

2025-09-11 15:09:00 +02:00

export_figures.py

docs: Describe examples (#2262)

2025-09-16 16:00:38 +02:00

export_multimodal.py

docs: Describe examples (#2262)

2025-09-16 16:00:38 +02:00

export_tables.py

docs(examples): remove deprecation warnings with export_to_dataframe (#2638)

2025-11-17 12:48:41 +01:00

extraction.ipynb

feat: remove the deprecation of extraction (#3220)

2026-04-01 09:39:34 +02:00

full_page_ocr.py

fix: correct type hint for table_structure_options usage (#2823)

2026-01-06 08:59:43 +01:00

gpu_standard_pipeline.py

docs: More GPU results and improvements in the example docs (#2674)

2025-11-24 15:26:08 +01:00

gpu_vlm_pipeline.py

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

granitedocling_repetition_stopping.py

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

hybrid_chunking.ipynb

docs: add line-based chunker documentation and examples (#3210)

2026-03-30 10:55:31 +02:00

index.md

docs: add XBRL conversion example notebook and update feature listings (#3039)

2026-02-27 16:09:19 +01:00

inspect_picture_content.py

docs: Describe examples (#2262)

2025-09-16 16:00:38 +02:00

line_based_chunking.ipynb

docs: add line-based chunker documentation and examples (#3210)

2026-03-30 10:55:31 +02:00

minimal_asr_pipeline.py

feat(ASR): MLX Whisper Support for Apple Silicon (#2366)

2025-10-21 08:05:59 +02:00

minimal_vlm_pipeline.py

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

minimal.py

docs: fix examples rendering (#2281)

2025-09-17 20:50:50 -04:00

mlx_whisper_example.py

feat(ASR): MLX Whisper Support for Apple Silicon (#2366)

2025-10-21 08:05:59 +02:00

model_family_engines_example.py

feat: Unified model-family inference engines (including image-classification) and KServe v2 API support (#2979)

2026-02-18 10:49:19 +01:00

parquet_images.py

feat: add preset for using granite-docling via vllm and other apis (#2792)

2025-12-16 17:22:35 +01:00

picture_description_inline.py

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

pictures_description_api.py

feat: Introduce pluggable VLM runtime system with preset-based configuration (#2919)

2026-02-04 17:29:17 +01:00

pictures_description.ipynb

feat: Enrichment annotations in the new meta format (#2859)

2026-01-08 18:28:52 +01:00

pii_obfuscate.py

docs: Example on PII obfuscation (#2459)

2025-10-14 15:39:16 +02:00

post_process_ocr_with_vlm.py

feat: Drop support for Python 3.9 (#2905)

2026-01-23 10:15:58 +01:00

rag_azuresearch.ipynb

ci: add coverage and ruff (#1383)

2025-04-14 18:01:26 +02:00

rag_haystack.ipynb

chore: update Milvus on examples and references to deprecated method (#2664)

2025-11-20 13:22:45 +01:00

rag_langchain.ipynb

docs: fix code in rag langchain chunker tokenizer (#2993)

2026-03-10 06:50:24 +01:00

rag_llamaindex.ipynb

chore: move to docling-project org (#1160)

2025-03-14 12:35:29 +01:00

rag_milvus.ipynb

chore: update Milvus on examples and references to deprecated method (#2664)

2025-11-20 13:22:45 +01:00

rag_mongodb.ipynb

docs: Add MongoDB + VoyageAI (#2382)

2025-10-07 14:36:19 -04:00

rag_opensearch.ipynb

docs: update opensearch notebook and backend documentation (#2519)

2025-10-27 10:02:50 +01:00

rag_weaviate.ipynb

docs: fix Colab badge links and Weaviate typo in docs examples (#2871)

2026-01-12 08:50:41 +01:00

rapidocr_with_custom_models.py

docs: Describe examples (#2262)

2025-09-16 16:00:38 +02:00

retrieval_qdrant.ipynb

docs: fix Colab badge links and Weaviate typo in docs examples (#2871)

2026-01-12 08:50:41 +01:00

run_md.py

ci: add coverage and ruff (#1383)

2025-04-14 18:01:26 +02:00

run_with_accelerator.py

fix: correct type hint for table_structure_options usage (#2823)

2026-01-06 08:59:43 +01:00

run_with_formats_html_rendered_mp.py

feat: Implementation of HTML backend with headless browser (#2969)

2026-03-24 14:28:57 +01:00

run_with_formats_html_rendered.py

feat: Implementation of HTML backend with headless browser (#2969)

2026-03-24 14:28:57 +01:00

run_with_formats.py

docs: Describe examples (#2262)

2025-09-16 16:00:38 +02:00

serialization.ipynb

feat: Enrichment annotations in the new meta format (#2859)

2026-01-08 18:28:52 +01:00

suryaocr_with_custom_models.py

docs: Added documentation to use SuryaOCR via plugin docling-surya (#2533)

2025-11-19 15:27:24 +01:00

tesseract_lang_detection.py

docs: Describe examples (#2262)

2025-09-16 16:00:38 +02:00

translate.py

docs: fix Colab badge links and Weaviate typo in docs examples (#2871)

2026-01-12 08:50:41 +01:00

visual_grounding.ipynb

docs: set HuggingFaceEndpoint task for Mixtral examples (#2945)

2026-03-08 10:38:06 +01:00

vlm_pipeline_api_model.py

docs: Fix Erroneous vLLM VLM pipeline engine option params causing empty/bad responses (#3167)

2026-03-23 10:44:37 +01:00

xbrl_conversion.ipynb

docs: add XBRL conversion example notebook and update feature listings (#3039)

2026-02-27 16:09:19 +01:00