MarkItDown: An all-in-one tool to convert files to Markdown
Microsoft introduced MarkItDown, a library for converting files to Markdown. The tool supports popular formats such as PDF, Word, Excel, PowerPoint, images, and audio.
MarkItDown is equipped with text analysis, OCR for image processing, and speech transcription. In addition, the library allows you to use large language models to describe content.
MarkItDown can be installed via pip or from source, and its simple API allows for easy integration into developers' projects.