Docling
An open-source toolkit that converts PDFs, Office files, HTML, images, audio and more into structured data for AI, started at IBM Research.
About Docling
RAG and agents struggle with complex documents such as PDFs with tables and multi-column layouts.
Who it’s for
- Developers building RAG pipelines
- Teams processing large document collections
When to consider it
Consider Docling when you need accurate document parsing, including tables and layout, that runs locally.
Tradeoffs & limitations
- MIT licensed and hosted by the LF AI & Data Foundation; it runs on your own hardware.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Docling.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 3, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Docling official website
An open-source toolkit that converts PDFs, Office files, HTML, images, audio and more into structured data for AI, started at IBM Research.
Based on official pages and announcements checked on 2026-10-03. No hands-on test, performance benchmark or popularity ranking is claimed.