#3 · Primary category： Computer Vision
PaddleOCR
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.
Project last updated：07/22/26
GitHub Stars
88.5K
Forks
11.3K
Contributors
295
License
Apache-2.0
Why we included this project
PaddleOCR is a solid choice when your application has to pull text and structure out of scanned pages, photos, or PDFs. It recognizes text in more than 100 languages and can turn complex layouts into Markdown or JSON, which is exactly what an LLM needs for RAG ingestion or form and table extraction. There's also a lightweight vision-language model for document parsing, so you can stick with fast classical OCR or trade some speed for the VLM's accuracy depending on your hardware. It runs on CPU and GPU, and it plugs into common agent and RAG frameworks, so teams can move from a working demo to production without rebuilding the pipeline.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)
ultralytics
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking