A sleek, rapid-prototyped web tool built with Python, Streamlit, and Microsoft's MarkItDown library.
- Multi-format Support: Convert
.pdf,.docx, and.pptxfiles. - One-Click Conversion: Simple UI that handles the heavy lifting in the background.
- Instant Preview: Preview your Markdown content directly in the browser before downloading.
- Clean Output: Utilizes Microsoft’s
MarkItDownfor high-fidelity text extraction.
If you want to run this project locally, follow these steps:
-
Clone the repository:
git clone https://github.com/Denvermax19/Markdown-Converter.git cd markdown-converter -
Install dependencies: This project requires Python 3.9+. Install the necessary packages using the requirements file:
pip install -r requirements.txt
Note: Ensure your
requirements.txtincludesstreamlitandmarkitdown[pdf,docx,pptx]. -
Run the application:
streamlit run app.py
- Upload: Drag and drop your PDF, Word, or PowerPoint file into the uploader.
- Convert: Click the "Convert to Markdown" button. The tool will process the file using the MarkItDown engine.
- Download: Once the conversion is finished, a download button will appear. Click it to save your new
.mdfile.
- Images (OCR and llm based description)
- Audio (speech transcription)
The tool relies on the following major libraries:
- Streamlit: For the user interface.
- MarkItDown: Microsoft's library for converting various files to Markdown.
Check out the live tool here: Markdown Converter