Apple Vision Python Packages

autosxtract

Extracts text from PDFs using the fastest available method, falling back to OCR via PP-OCRv6 if needed. One pip install, no configuration.

d2md

Convert local documents to Markdown for AI agents, RAG, and automation. Lightweight by default, with optional OCR and Docling; macOS OCR uses Apple Vision with no API key or separate model download.

localcontextrouter

Preflight router that decides locally whether each document page reaches a multimodal model as text, on-device OCR, or an image. Cuts vision-token cost. macOS.