Docling
MIT local document parser that feeds PDFs and Office files into gen-AI pipelines
Python / Document AI · OSS/MIT · 69.1k
Reviewed 2026-09-20 · last push 2026-10-18 · repo checked 2026-10-19
What's Good
MIT (docling-project/docling). Strong PDF understanding (layout, reading order, tables, code, formulas), wide format coverage, local/air-gapped execution, and gen-AI ecosystem integrations. It is the practical document-ingestion primitive when agents must read real enterprise files, not only clean Markdown.
The Catch
Vs MinerU and plain OCR pipelines: Docling is the broader multi-format DoclingDocument stack with gen-AI export paths — still expect GPU/CPU cost on heavy PDF batches and imperfect table recovery on ugly scans. Local models and extras increase install weight versus a thin Markdown converter.
Verdict
MIT document AI for agent/RAG ingest. Default when PDFs and Office files must become structured context locally.
Embed
Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.
Markdown
[](https://stackgems.com/gems/docling)
HTML
<a href="https://stackgems.com/gems/docling"><img src="https://stackgems.com/badge/docling.svg" alt="Docling reviewed on Stack Gems" height="20"></a>