Does it support extracting data from .doc files?

[morozover]

I need extract data from .doc (MS Office) files

[dosubot[bot]]

Hi @morozover! I'm Dosu and I’m helping the docling team.

Docling doesn't support extracting data from .doc (MS Office binary) files. It only works with .docx and related formats, because its backend relies on the python-docx library, which can't open .doc files (source). If you need to process .doc files, you'll need to convert them to .docx first—tools like Microsoft Word, LibreOffice, or unoconv can do this. Once converted, you can extract data using Docling as usual.

To reply, just mention @dosu.

---

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}