Parse PDF documents with MinerU MCP to extract text, tables, and formulas. Supports multiple backends including MLX-accelerated inference on Apple Silicon.
Initial release of mineru-pdf, a PDF parser supporting text, tables, and formulas with Apple Silicon optimization. - Parse PDF documents using MinerU MCP to extract structured content (text, tables, formulas) - Supports multiple backends including MLX for Apple Silicon and a general pipeline - Provides both a direct parsing tool (persistent output) and MinerU MCP integration (temporary output) - Handles advanced options: specific page ranges, backend selection, table/formula toggles - Returns structured Markdown output with metadata, Markdown tables, and LaTeX for formulas - Supports PDF and various image formats; built-in OCR for scanned documents