vision-parse is a tool that uses visual language models (Vision LLMs) to convert PDF documents into well-formatted Markdown content. It supports multiple models including OpenAI, Llama, and Gemini, intelligently recognizing and extracting text and tables while preserving the document's hierarchy, style, and indentation. The main advantages of this tool include high-precision content extraction, format retention, multi-model support, and local model hosting, making it suitable for users requiring efficient document processing.