Nikos Livathinos c6b3763ecb

feat(OCR): Introduce the OcrOptions.force_full_page_ocr parameter that forces a full page OCR scanning (#290) ...

- When the OCR is forced, any existing PDF cells are rejected.
- Introduce the force-ocr cmd parameter in docling CLI.
- Update unit tests.
- Add the full_page_ocr.py example in mkdocs.

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

2024-11-12 09:46:14 +01:00

..

batch_convert.py

chore: make tests lighter (#228)

2024-11-04 14:02:28 +01:00

custom_convert.py

fix: allow mps usage for easyocr (#286)

2024-11-10 14:26:17 +01:00

develop_picture_enrichment.py

feat!: Docling v2 (#117)

2024-10-16 21:02:03 +02:00

export_figures.py

docs: add export with embedded images (#175)

2024-10-24 20:19:41 +02:00

export_multimodal.py

feat!: Docling v2 (#117)

2024-10-16 21:02:03 +02:00

export_tables.py

feat!: Docling v2 (#117)

2024-10-16 21:02:03 +02:00

full_page_ocr.py

feat(OCR): Introduce the OcrOptions.force_full_page_ocr parameter that forces a full page OCR scanning (#290)

2024-11-12 09:46:14 +01:00

index.md

docs: add navigation indices (#305)

2024-11-11 14:49:06 +01:00

minimal.py

chore: various minor docs fixes (#169)

2024-10-22 15:29:36 +02:00

rag_langchain.ipynb

feat!: Docling v2 (#117)

2024-10-16 21:02:03 +02:00

rag_llamaindex.ipynb

docs: update LlamaIndex docs for Docling v2 (#182)

2024-10-28 14:28:26 +01:00

run_md.py

feat: Support AsciiDoc and Markdown input format (#168)

2024-10-23 16:14:26 +02:00

run_with_formats.py

fix: fix duplicate title and heading + add e2e tests for html and docx (#186)

2024-10-30 13:14:56 +01:00