eimenhmdt / autoresearcher

⚡ Automating scientific workflows with AI ⚡
MIT License
374 stars 38 forks source link

Add paper analysis workflow & pdf loader #19

Open eimenhmdt opened 1 year ago

eimenhmdt commented 1 year ago

This PR adds a workflow that analyzes a given paper. The workflow extracts the main findings, methodology and limitations of the paper. The paper can be loaded as a PDF. For this, I added a new module "file_loaders" and a PDF loader that loads and splits PDFs by page. The PDF can load local and also remote PDFs if passed a URL (e.g. "https://arxiv.org/pdf/2302.03803.pdf").

Looking forward to your feedback!

janzheng commented 1 year ago

Could you please add the common sections of a paper? (Abstract, Introduction, Materials, Methods (sometimes they're in a single section called Materials & Methods), Results, Discussion, Supplemental Materials, References)

I think a method to just extract the text from those sections would be SO useful on its own.

eimenhmdt commented 1 year ago

Could you please add the common sections of a paper? (Abstract, Introduction, Materials, Methods (sometimes they're in a single section called Materials & Methods), Results, Discussion, Supplemental Materials, References)

I think a method to just extract the text from those sections would be SO useful on its own.

Great idea!