markitdown and markdrop
These are competitors in the core markdown conversion space, though markdrop differentiates by adding LLM-powered extraction of semantic content (tables, images, descriptions) versus markitdown's broader file format support without AI enhancement.
About markitdown
microsoft/markitdown
Python tool for converting files and office documents to Markdown.
MarkItDown helps data scientists, researchers, and AI developers prepare various document types for Large Language Models (LLMs). It takes common formats like PDFs, Word documents, PowerPoint presentations, or even YouTube URLs, and converts them into structured Markdown text. The output preserves key structural elements like headings and tables, making it ideal for text analysis pipelines and LLM ingestion.
About markdrop
shoryasethia/markdrop
A Python package for converting PDFs to markdown while extracting images and tables, generate descriptive text descriptions for extracted tables/images using several LLM clients. And many more functionalities. Markdrop is available on PyPI.
This tool helps you convert complex PDF documents, including research papers, reports, or manuals, into organized Markdown and interactive HTML files. It takes your PDF and extracts text, images, and tables, then generates descriptive summaries for the visuals using various AI models. Anyone who needs to extract and understand content from PDFs, like researchers, analysts, or content creators, would find this useful for streamlining their workflow.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work