Framework
PaddleOCR
PaddleOCR is an open-source AI framework from Baidu 百度, launched in 2020, made for developers and businesses.
An OCR and document parsing toolkit that turns images and PDFs into text, tables and structure.
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.
Markdown version of https://godooo.ai/en/framework/paddleocr. Every page on this site has one: add .md to its address.
At a glance
- Type
- Framework
- Made by
- Baidu 百度
- Launched
- 2020
- Galaxy
- Models & APIs
- Open source
- Yes · Apache-2.0
- Source code
- github.com/PaddlePaddle/PaddleOCR
- GitHub stars
- 90,145
- How you run it
- Self-host · Runs offline · Terminal · API
- Made for
- Developers · Businesses
- Website
- paddleocr.com
What it can do
Document parsingmain jobunconfirmed
“PaddleOCR converts PDF documents and images into structured, LLM-ready data (JSON/Markdown) with industry-leading accuracy.”— github.com, 2026-09-24
Text recognition (OCR)main jobunconfirmed
“100+ Languages Supported : Native recognition for a vast global library.”— github.com, 2026-09-24
unconfirmedproposed by a machine, awaiting calibration
Alternatives
- MinerUOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- DoclingOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- MarkerOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- SuryaOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- MarkItDownOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- UnstructuredOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- LlamaIndexOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- RAGFlowOpen source, freeAlso does: Document parsing
- PDF SkillAlso does: Document parsing
- FirecrawlOpen source, freeAlso does: Document parsing
- MistralOpen source, freeAlso does: Text recognition (OCR)
- QwenOpen source, freeAlso does: Text recognition (OCR); no code needed
Connections
- Uses
- ERNIE 文心
Questions
What is PaddleOCR?
PaddleOCR is an open-source AI framework from Baidu 百度, launched in 2020, made for developers and businesses. An OCR and document parsing toolkit that turns images and PDFs into text, tables and structure.
Is PaddleOCR free?
Yes. PaddleOCR is open source (Apache-2.0) and free to use.
Is PaddleOCR open source?
Yes, under the Apache-2.0 license. The source code is at https://github.com/PaddlePaddle/PaddleOCR.
Can PaddleOCR run locally?
Yes. PaddleOCR can run offline on your own machine. It can also be self-hosted on your own server.
What can PaddleOCR do?
Main jobs: Document parsing, Text recognition (OCR).
Who makes PaddleOCR?
PaddleOCR is made by Baidu 百度.
What are open-source alternatives to PaddleOCR?
Open-source ones: MinerU, Docling, Marker, Surya, MarkItDown, Unstructured, LlamaIndex and RAGFlow. Others: PDF Skill.
Sources
- github.com/PaddlePaddle/PaddleOCRchecked 2026-09-24
- www.paddleocr.com