Framework
Docling
Docling is an open-source AI framework, launched in 2024, made for developers.
A library that parses PDFs, Office files and other documents into structured data for AI pipelines.
Main jobs: Document parsing, Text recognition (OCR). It is open source and free to use. You can use it on your own server, offline on your own machine, in the terminal and through an API.
Visit docling-project.github.io
Markdown version of https://godooo.ai/en/framework/docling. Every page on this site has one: add .md to its address.
At a glance
- Type
- Framework
- Launched
- 2024
- Galaxy
- Models & APIs
- Open source
- Yes · MIT
- Source code
- github.com/docling-project/docling
- GitHub stars
- 67,811
- How you run it
- Self-host · Runs offline · Terminal · API
- Made for
- Developers
- Protocols
- Model Context Protocol
- Website
- docling-project.github.io
What it can do
Document parsingmain jobunconfirmed
“Parsing of multiple document formats including PDF, DOCX, PPTX, XLSX, HTML, EPUB, Apple Pages, WAV, MP3, WebVTT, Box Notes, email formats”— docling-project.github.io, 2026-09-24
Text recognition (OCR)main jobunconfirmed
“Extensive OCR support for scanned PDFs and images”— docling-project.github.io, 2026-09-24
Knowledge base (RAG)supportedunconfirmed
“RAG with LangChain RAG with LlamaIndex”— docling-project.github.io, 2026-09-24
Speech to textsupportedunconfirmed
“Audio support with Automatic Speech Recognition (ASR) models”— docling-project.github.io, 2026-09-24
unconfirmedproposed by a machine, awaiting calibration
Alternatives
- MinerUOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- MarkerOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- UnstructuredOpen source, freeAlso does: Document parsing, Knowledge base (RAG), Text recognition (OCR)
- PaddleOCROpen source, freeAlso does: Document parsing, Text recognition (OCR)
- SuryaOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- MarkItDownOpen source, freeAlso does: Document parsing, Speech to text, Text recognition (OCR)
- LlamaIndexOpen source, freeAlso does: Knowledge base (RAG), Document parsing, Text recognition (OCR)
- RAGFlowOpen source, freeAlso does: Document parsing, Knowledge base (RAG)
- FastGPTOpen source, freeAlso does: Knowledge base (RAG), Document parsing; no code needed
- kotaemonOpen source, freeAlso does: Knowledge base (RAG), Document parsing; no code needed
- PDF SkillAlso does: Document parsing
- PrivateGPTOpen source, freeAlso does: Knowledge base (RAG), Document parsing
Questions
What is Docling?
Docling is an open-source AI framework, launched in 2024, made for developers. A library that parses PDFs, Office files and other documents into structured data for AI pipelines.
Is Docling free?
Yes. Docling is open source (MIT) and free to use.
Is Docling open source?
Yes, under the MIT license. The source code is at https://github.com/docling-project/docling.
Can Docling run locally?
Yes. Docling can run offline on your own machine. It can also be self-hosted on your own server.
What can Docling do?
Main jobs: Document parsing, Text recognition (OCR). It can also do: Knowledge base (RAG), Speech to text.
What are open-source alternatives to Docling?
Open-source ones: MinerU, Marker, Unstructured, PaddleOCR, Surya, MarkItDown, LlamaIndex and RAGFlow. Others: PDF Skill.
Sources
- docling-project.github.io/docling/checked 2026-09-24
- github.com/docling-project/docling