Back to directory

MarkItDown

A Python utility that converts PDFs, Office documents, images, audio, HTML and other file types into Markdown for use with LLMs and text analysis pipelines.

MarkItDown

MarkItDown is a lightweight Python utility for converting a range of file formats into Markdown so the content can be fed into LLMs and other text analysis tools. It supports PDF, PowerPoint, Word, Excel, images (using EXIF metadata and OCR), audio (using EXIF metadata and speech transcription), HTML, text-based formats such as CSV, JSON and XML, ZIP archives, YouTube URLs and EPubs.

The project favors Markdown as an output format because it stays close to plain text while still representing headings, lists, tables and links, and because mainstream LLMs are trained on large amounts of Markdown and handle it well; Markdown is also comparatively token-efficient.

MarkItDown requires Python 3.10 through 3.14, and the project documents installing it inside a virtual environment created with venv, uv or Anaconda.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.