Skip to content

v0.2.0

Latest

Choose a tag to compare

@atsyplenkov atsyplenkov released this 18 Mar 14:52
· 18 commits to main since this release

Initial release

What’s included

  • Convert a single PDF or an entire directory of PDFs to Markdown using Z.AI GLM-OCR
  • Download referenced figures locally during conversion
  • Run batch processing with configurable parallelism via --workers
  • Generate a consistent output per paper: index.md, figures/, and log.jsonl
  • Re-generate managed output artifacts safely with --overwrite

Notes

  • API key resolution is deterministic: --env-file first, then environment fallback
  • Optimized for academic papers in English
  • Focused on reliable table/formula extraction, fast local workflow, and low per-paper API cost