PaddlePaddle/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.

语言：Python · GitHub 星标：92,075 · Fork：11,604

话题：ai4science · chineseocr · document-parsing · document-translation · kie · ocr · paddleocr-vl · pdf-extractor-rag

在 GitHub 上查看原仓库