TL;DR
An open-source tool that transforms complex documents into LLM-ready markdown or JSON for agentic workflows.
Key features
Converts various document formats like PDFs and Office files into markdown or JSON.
Optimized for structured data extraction for agentic workflows.
Python-based and easily installable via PyPI.
When to use it
When you need to inject external document knowledge into an LLM agent.
When document preprocessing is required for a RAG (Retrieval-Augmented Generation) pipeline.
When you need to extract content from complex documents into structured data.