PaddleOCR is an open-source RAG and search tool written in Python, released under the Apache-2.0 license. It has 91k GitHub stars and 12k forks, and was last updated in September 2026. Topics include ai4science, chineseocr and document-parsing.
“Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.”
— PaddlePaddle, project description on GitHub
Details
| Category | RAG & Search |
|---|---|
| GitHub stars | 91,323 |
| Forks | 11,518 |
| Language | Python |
| License | Apache-2.0 |
| Last updated | |
| Owner | PaddlePaddle |
| Website | www.paddleocr.com |
| Repository | PaddlePaddle/PaddleOCR |
Tags
ai4sciencechineseocrdocument-parsingdocument-translationkieocrpaddleocr-vlpdf-extractor-rag
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.