2025-04-21 07:13:19 +00:00
|
|
|
# MarkItUp
|
2024-11-13 19:56:46 +00:00
|
|
|
|
2025-04-21 07:13:19 +00:00
|
|
|
This is a fork of [MarkItDown](https://github.com/microsoft/markitdown).
|
2024-12-18 22:26:36 +00:00
|
|
|
|
2025-04-23 07:18:23 +00:00
|
|
|
While markitdown is a useful tool, its returned content is too text-focused, which is not updated to the current rise of multi-modal LLMs.
|
2025-03-25 22:00:04 +00:00
|
|
|
|
2025-04-21 07:13:19 +00:00
|
|
|
## Features
|
2024-12-18 22:26:36 +00:00
|
|
|
|
2025-04-23 07:18:23 +00:00
|
|
|
- Converts various file formats to markdown-oriented OpenAI compatible responses
|
|
|
|
|
- Supports multiple file types including:
|
|
|
|
|
- Documents: DOCX (not DOC)
|
|
|
|
|
- Presentations: PPTX (not PPT)
|
|
|
|
|
- Spreadsheets: XLSX, XLS, CSV
|
|
|
|
|
- Media: Audio files (MP3, M4A)
|
|
|
|
|
- Web content: HTML
|
|
|
|
|
- PDF files
|
|
|
|
|
- Plain text files
|
|
|
|
|
- Returns OpenAI compatible response, which can be used by most LLM clients
|
|
|
|
|
- Supports command line usage
|
