Papercast
A Python pipeline tool and plugin ecosystem for processing technical documents. Process papers from arXiv, SemanticScholar, PDF, with GROBID, LangChain, listen as podcast. Customize your own pipelines.
Install / Use
/learn @papercast-dev/PapercastREADME
Papercast

An extensible pipeline tool and plugin ecosystem for processing technical documents. Written in Python.
Features
|Feature|Examples|
|-|-|
| Add documents in multiple formats, from popular sources: | PDF <br /> LaTeX <br /> ArXiv <br /> SemanticScholar |
| Flexible Text Extraction | GROBID <br /> More coming soon! <br /> Write your own! |
| Flexible Text Narration | OSX say command <br /> More coming soon! <br /> Write your own! |
| Publish to multiple endpoints: | Self-hosted RSS podcast using GitHub Pages <br /> Any other endpoint you can think of |
| Run anywhere: | Local machine <br /> Remote server <br /> Cloud (AWS, GCP, Azure, etc.) |
