D
AI Tool Profile

Docling

Open-source toolkit that parses PDFs, Office files, images and other formats into structured output for generative AI pipelines, for developers. Free under the MIT license and can run locally, including air-gapped.

Website
github.com
Pricing model
Open Source
Price start
Free

Description of Docling

Docling is an open-source document-processing toolkit whose repository tagline is get your documents ready for gen AI. It parses diverse formats, including advanced PDF understanding. The project was started by IBM Research Zurich's AI for knowledge team and is hosted as a project in the LF AI & Data Foundation. It is aimed at developers preparing documents for generative AI applications.

The README lists input formats including PDF, DOCX, PPTX, XLSX, HTML, EPUB, images such as PNG, TIFF and JPEG, audio, email, LaTeX and plain text. For PDFs it covers layout, reading order, table structure, code, formula and image classification, and it includes OCR for scanned PDFs and images. Documents are held in a unified DoclingDocument representation and can be exported to Markdown, HTML, WebVTT, DocLang, DocTags and lossless JSON. It supports vision-language models such as GraniteDocling.

Docling offers a command-line interface, an API server called docling-serve and an MCP server, with plug-and-play support for LangChain, LlamaIndex, CrewAI and Haystack. The README says local execution is supported for sensitive data and air-gapped environments, and that it works on macOS, Linux and Windows on x86_64 and arm64. Python 3.10 or higher is required, and installation is with pip install docling. The codebase is under the MIT license, while individual models may carry their own licenses.

Features of Docling

  1. Parses PDF, DOCX, PPTX, XLSX, HTML, images and other formats, with layout, reading order and table structure for PDFs.
  2. Includes OCR for scanned PDFs and images and exports to Markdown, HTML and lossless JSON.
  3. Offers a CLI, docling-serve API server and MCP server, with LangChain, LlamaIndex, CrewAI and Haystack support.

Frequently asked questions

Is Docling free?

Yes. The README states the Docling codebase is under the MIT license. Individual AI models may carry their own licenses, which the project says to check in the original packages.

Can Docling run locally?

Yes. The README says it supports local execution for sensitive data and air-gapped environments, and that it works on macOS, Linux and Windows on x86_64 and arm64.

Website: https://github.com/docling-project/docling

Key facts

Open-source parser that turns PDFs, Office files and images into structured text for AI pipelines, for developers. Biggest limit: needs Python 3.10 or higher and self-setup. Free under MIT.

Pricing model Open source
Free tier Yes · Free open-source software (MIT); individual models may have their own licenses · no credit card required
Starting price Not verified
Data residency On-premises — The README says local execution is supported for sensitive data and air-gapped environments.
Compliance (as stated by vendor) Not verified
Integrations LangChain, LlamaIndex, CrewAI, Haystack
Public API Yes
Self-hostable Yes
Official site Not verified
Can a general AI assistant replace it? For managed hosting, compare Mistral OCR, Google Document AI or Amazon Textract; for a single-purpose PDF text layer, OCRmyPDF.
Last verified 2026-11-17 by editor

Alternatives & Similar Tools

Vidsembly logo
Vidsembly Freemium

Vidsembly turns PowerPoint decks, PDFs and documents into narrated videos with AI voiceover or your own voice clone in 12 languages, then lets you host and share them with a link or embed.

A

Microsoft Azure service that extracts text, key-value pairs and tables from printed and handwritten forms, PDFs and images, for developers. Microsoft says free and standard pricing options exist; limits are on a page not readable today.

T
Tesseract OCR Open Source

Open-source OCR engine and command-line program that recognizes text in images, for developers building OCR into their own software. Free under the Apache License 2.0 and recognizes more than 100 languages out of the box.

M

Mistral AI's OCR API that extracts text and structured content from PDFs and images, for developers building document pipelines. Mistral lists OCR 4.1 at $4 per 1,000 pages; no free-tier terms were stated on the pages read.

N
Numerous.ai Freemium

Numerous.ai brings ChatGPT into Google Sheets and Microsoft Excel through an =AI function you can use in any cell, with no API key needed. Its site does not publish plan prices, so check the add-on before you rely on it.

S
Shortcut Freemium

Shortcut is an AI agent for building and editing Excel workbooks, aimed at finance work. It runs on the web, as a desktop app and as Excel and Google Sheets plugins; the free tier includes 20 credits a week.

Update history

  1. 2026-11-17 · ai alternative note updated (editor)
  2. 2026-11-17 · editor verdict updated (editor)
  3. 2026-11-17 · self hostable updated (editor)
  4. 2026-11-17 · api available updated (editor)
  5. 2026-11-17 · integrations updated (editor)
  6. 2026-11-17 · data residency updated (editor)
  7. 2026-11-17 · free tier updated (editor)
  8. 2026-11-17 · pricing model updated (editor)

Beyond the tool

Need the outcome rather than the software?