docling-project / docling-project/docling

Feature Request: Support for .docx and .pptx similar to pdfPipeline

Open
#1,504 1 comment 4 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

I tried using Docling for .pdf files and it worked great! However, when working with .docx and .pptx formats, I noticed there is no advanced pipeline support—only a simple pipeline is available.
Key missing features include:

No support for OCR, which is crucial for scanned documents.

No table extraction capabilities.

No intelligent handling of complex layouts (e.g., multi-column documents where content should be read top-to-bottom within a column, then left-to-right across columns).

I attempted to apply pdfPipeline features to .docx, but the system indicated that those features are only available for PDFs. I'd like to request similar advanced processing options for .docx and .pptx, including layout-aware parsing, OCR support, and table extraction.

Alternatives
Currently, I'm limited to basic extraction which misses critical structure and content in complex documents. Using external libraries for OCR or layout detection is an option, but it would be much more efficient and user-friendly if Docling offered this natively, just like for PDFs.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.