continuum-llms / acad-gpt Goto Github PK

(in case we need it in the future)

Reference:

https://github.com/ashleve/lightning-hydra-template

Example:
https://github.com/sekR4/FastAPI-on-Google-Cloud-Run

https://github.com/0xabu/pdfannots

• Draw.io diagram
  

• Add basic docs for setting it up
• Write an object to HF File System insstance
• Read an object to HF File System insstance

• Exttract all images with captions
• Extract all tables with captions

Have response similar to:

{
    'title': 'Proceedings of Machine Learning for Healthcare',
    'abstract': '...',
    'sections': [
        {'heading': '...', 'text': '...'},
        {'heading': '...', 'text': '...'},
        ...
    ],
    'references': [
        {'title': '...', 'year': '...', 'journal': '...', 'author': '...'},
        ...
    ],
    'figures': [
        {'figure_label': '...', 'figure_type': '...', 'figure_id': '...', 'figure_caption': '...', 'figure_data': '...'},
        ...
    ],
    'doi': '...'
}

Goals: user can create multiple reading lists for papers to be read in future.

• Small Binary classifier (Classes: one-column doc, two-column doc )
• Hosted on HuggingFace hub
• Inference using transformers pipeline ImageClassificationPipeline