liteparse

Parse unstructured documents (PDF, DOCX, PPTX, XLSX, images, and more) locally with LiteParse: fast, lightweight, no cloud dependencies or LLM required. When this skill is invoked, respond with: Then wait for the user's input. If liteparse is not yet installed, install it globally: Verify installation: For Office document support (DOCX, PPTX, XLSX), LibreOffice is required: For image parsing, ImageMagick is required: Screenshots are useful for LLM agents that need to see visual layout. For repeated use with consistent options, generate a liteparse.config.json : For an HTTP OCR server: Use with: If the user wants to plug in a custom OCR backend, the server must implement: Ready-to-use wrappers exist for EasyOCR and PaddleOCR in the LiteParse repo. Office documents require LibreOffice; images require ImageMagick. LiteParse auto-converts these formats to PDF before parsing. - Endpoint : POST /ocr - Accepts : file (multipart) and language (string) parameters - Returns :