← Back to all projects

Docling

Converts PDFs, Office files and scans into one structured representation, without sending them anywhere

OfficialMIT
Stars
69.9k
Forks
5.2k
Open issues
922
Last commit
30 Oct 2026

What is Docling?

The difference from a text extractor is that structure survives: page layout, reading order, table cells, code blocks and formulas come through as parts of a single document representation rather than as a flattened string, which is what decides whether a table in a report is still a table by the time an agent reads it. Everything can run locally, including in air-gapped environments. The cost of that fidelity is compute — machine-learning models run over each page, so this is a pipeline to budget for, not a fast converter to call inline.

What can you do with Docling?

  • One representation for every input — Whatever went in, what comes out is a single document format, so downstream code does not branch on whether the source was a PDF, a spreadsheet or an email.
  • Keep the structure a text dump destroys — Page layout, reading order, table structure, code blocks, formulas and image classification are all recovered, and charts are converted into tables or code with a description attached.
  • Read the awkward formats too — Beyond PDF and Office there is HTML, EPUB, images, LaTeX, email, audio via speech recognition, and specialised schemas such as XBRL financial filings and USPTO patents.
  • Handle scans without an external service — OCR for scanned PDFs and images is included, along with support for vision-language models, so pages that are pictures of text are not simply skipped.
  • Hand the result straight to a RAG stack — Plug-in integrations exist for LangChain, LlamaIndex, CrewAI and Haystack, and an API server mode is available when conversion should be a service rather than a library call.

Before you choose Docling

  • Machine-learning models for layout and table structure run over each page, so conversion throughput is a capacity question — this is a pipeline to schedule, not a fast extractor to call in a request path.

Star history

21 Aug to 30 Oct · +4.5k

65.4k69.9k

Frequently asked questions

Is Docling free for commercial use?

Docling is released under the MIT licence — OSI-approved open source, which permits commercial use.

How can Docling be deployed?

Docling is available as Runs locally / Self-hosted.