docling good first issues (Python)

PY-09-docling-core: `validate_misplaced_list_items` drops the children of multi-run list items, so `export_to_markdown()` / `export_to_html()` lose their text and mutate the document about 1 hour ago

bug docling-document good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

PY-07-docling: `docx`: paragraphs inside a body-level `mc:AlternateContent` are dropped 5 days ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

PY-08-docling: `docx`: even-page headers and footers (`evenAndOddHeaders`) are never extracted 7 days ago

enhancement docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Improve parsing of JATS documents 14 days ago

enhancement xml good first issue triage/close-fixed

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Wrong markdown serialization of pivot tables about 1 month ago

bug docling-document good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Docling on n8n nodes about 1 month ago

enhancement help wanted triage/close-stale

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Add image_dir parameter to export_to_markdown for automatic image saving about 2 months ago

enhancement docling-document good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

VLM pipeline MD/HTML conversion 2 months ago

bug good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Markdown serialization of headings in rich table cells 3 months ago

bug markdown good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

tables in json format inside md or txt file 3 months ago

enhancement docling-document good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Option to set the default ContentLayer in the Body for html_backend 4 months ago

enhancement good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Support page range conversion in xlsx documents 4 months ago

bug xlsx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

When converting a docx document, inexplicable blank images appear, and a line of text disappears. 4 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Docling cannot obtain the images inserted into the text box of docx file 5 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Document /tmp/tmpqpqmezip/R1-2602795.docx failed to convert 6 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Extracting user comments from office documents like (.docx, .pptx, .xlsx) and embedding them into output format (.md, .html). 6 months ago

enhancement pptx xlsx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

DOCX chunkers return 0 chunks when document contains tables (TableItem serialization is empty but consumes `visited`) 6 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Docling cannot convert user-defined numbering formats that include English words. 6 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Multi-level outline numbering incorrectly rendered as single-level in DOCX 6 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Improved Footnote Serialization in `MarkdownDocSerializer` 6 months ago

enhancement docling-document good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

CLI: directory input crashes with PermissionError on Windows 7 months ago

bug windows good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

image/figure count in md an txt 7 months ago

enhancement docling-document good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Section after table being incorrectly added as child of table header 7 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Investigate how to remove dependency of OpenCV 7 months ago

help wanted

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Docling fails to convert docx document 8 months ago

bug good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Incorrect image placement and layout distortion in Excel conversion 8 months ago

bug xlsx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Bug: page_footer/page_header elements retain content_layer=body when processed inside container groups 8 months ago

bug good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Add_node_items doesn't update caption reference 8 months ago

bug docling-document good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

PPTX parsing: bullet points not grouped correctly under subheadings 9 months ago

bug pptx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

page_no is sometimes 0 indexed and sometimes 1 indexed 9 months ago

bug good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Support for capturing Word document comments (e.g., reviewer comments or annotations added in Microsoft Word) 9 months ago

enhancement help wanted

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Single table incorrectly detected as two separate tables 10 months ago

bug xlsx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

RapidOCR ignores custom rec_keys.txt due to wrong parameter name in Docling 10 months ago

bug ocr good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

implement retry strategy for remote calls 11 months ago

enhancement good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

IndexError: list index out of range in msword_backend.py when processing DOCX files with empty paragraph runs 11 months ago

bug docx good first issue

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

Standardized Access to Common Email and Calendar Formats 11 months ago

enhancement help wanted icebox

docling-project/docling

63.1K

Get your documents ready for gen AI

Python

#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables#xlsx

docling-project/docling

Open Issues Need Help