Mineru
Converts PDF documents to HTML, including image resource organization and renaming, by encapsulating Mineru's official parsing capabilities as a FastMCP service callable by any MCP-compatible client.
Acerca de
This FastMCP service leverages Mineru's official PDF parsing capabilities to streamline the conversion of PDF documents into well-structured HTML, complete with organized and renamed image assets. Designed for seamless integration with any MCP-protocol-compatible client, including large language model agents, it makes batch PDF processing and content extraction efficient and automated. The service handles automatic scanning of PDF files, supports customizable parameters like language and table recognition, and intelligently processes Mineru's ZIP results to deliver clean, usable HTML outputs with properly managed image resources.
Características Principales
- Automated batch PDF upload and conversion using Mineru's official API.
- Customizable Mineru parsing parameters, including language, table recognition, and OCR.
- Intelligent organization and renaming of HTML and image assets from Mineru's ZIP output.
- Exposes `convert_pdfs_with_mineru` via FastMCP for direct integration with LLM agents.
- 1 GitHub stars
Casos de Uso
- Batch convert multiple PDF documents into clean, structured HTML.
- Extract content and images from PDFs for use in web applications or databases.
- Integrate PDF-to-HTML conversion capabilities directly into large language model workflows.
