今夜无眠 on Nostr: 这是好东西 ...

quoting
nevent1q…6n4k

Microsoft released an opensource tool to convert anything, even pdf, PowerPoint, and excel files into Markdown. MarkItDown prioritizes preserving essential document structures like headings, lists, tables, and links, making the output highly suitable for text analysis pipelines and LLM ingestion.
https://github.com/microsoft/markitdown