marker
https://github.com/datalab-to/marker
Python
Convert PDF to markdown + JSON quickly with high accuracy
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported0 Subscribers
Add a CodeTriage badge to marker
Help out
- Issues
- chore: improve marker maintenance path
- Enhancement: Streamlit UI improvements (Loading screen & Downloads) + import fix
- fix: clear highres images and reset surya KV cache to prevent memory leak in PdfConverter
- Fix misspellings of 'compatible'/'compatibility' in OpenAIService
- fix: respect Gemini API RetryInfo delay on 429 responses
- Memory seems to grow unbounded when reusing PdfConverter across multiple PDFs
- [FEAT]Best practice for running Marker alongside a local LLM on a single GPU to avoid VRAM conflict?
- feat: page_batch_size
- Add --llm_image_context for context-aware image descriptions
- [BUG: Breaking]torch.AcceleratorError: index 8192 is out of bounds: 2, range 0 to 4756
- Docs
- Python not yet supported