DocDot

DocDot provides a unified, local interface for robust PDF parsing on macOS, ensuring data privacy and high-quality output. Key features include: • One-line installation for macOS (M-chip) • Multiple parser engines (NanoDoc, PaddleOCR, MinerU) • Local processing with zero cloud upload • Outputs clean Markdown and JSON • Select the best parser for each document type This tool is designed for users who require precise document extraction without compromising data security by uploading sensitive PDFs to cloud services. It allows you to transform complex PDF structures into usable, structured formats like Markdown and JSON, making content ready for further processing or integration into other systems. The ability to choose between various parsing engines means DocDot can handle a wide range of document layouts and content types, from scanned images to rich text documents, providing optimal results for diverse needs. It's an essential utility for developers, researchers, and data professionals working with documents containing sensitive information. Ideal for creating structured data from reports, research papers, or legal documents, ensuring all processing remains on your local machine. Windows and Linux support is planned for future releases.