Search

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.

🔥🔥🔥Java免费离线AI算法工具箱，支持人脸识别，活体检测，表情识别、目标检测、实例分割、行人检测、OCR文字识别、车牌识别、表格识别、ASR+TTS、机器翻译等功能，Maven引用即可使用。支持PyTorch、Tensorflow，已集成 Mtcnn、InsightFace、SeetaFace6、YOLOv8~v12、PaddleOCR(PPOCRv5)、Whisper等主流模型

AI workflow (base on gpt-image-2 and paddleocr vl1.6) for generating PPT decks from papers, PDFs, figures, screenshots, and prepared materials, then rebuilding editable PPTX files.

search every screenshot you've ever taken by the text inside it. native linux, offline, PaddleOCR + sqlite + gpui