🔬 ScholarForge — Research toolkit
Python script for academic workflows.
Features:
📚 Harvest — Search 20+ academic sources (arXiv, PubMed, bioRxiv). Auto-download PDFs & EPUBs.
⚙️ Forge — Convert documents into AI-ready datasets with semantic chunking.
1/2
🔗 Pipeline — Search → download → process.
Why:
- Free sources, no paywalls
- Multilingual (Greek, Cyrillic)
- Cross-platform
- Zero dependencies
Perfect for researchers tired of manual data prep.
github.com/AnastasiosPapalias/Python/tree/main/scholarforge
Tasos Papalias