lucky-verma/SaastIE

Document understanding system using Donut transformer architecture

7

stars

10

commits

Python

primary language

Jan 30, 2026

updated

document-classification
ocr
transformers
vqa

README

SaasTie

Getting Started

Run the fastapi unicorn server

cd backend
uvicorn main:app --reload --port 6969

Run the streamlit app

cd frontend
streamlit run home.py

TODO

  • Develop REST APIs
  • Create a streamlit app
  • Train a baseline model
  • Train on more data
  • Add more features
  • Define more models
  • Refine visualizations
  • Perform tests
  • Add more documentation
  • Add deployment options

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

License

MIT

Acknowledgements

Authors

Contributors

lucky-verma

10 commits

lucky-verma/SaastIE

Document understanding system using Donut transformer architecture

7

stars

10

commits

Python

primary language

Jan 30, 2026

updated

document-classification
ocr
transformers
vqa

README

SaasTie

Getting Started

Run the fastapi unicorn server

cd backend
uvicorn main:app --reload --port 6969

Run the streamlit app

cd frontend
streamlit run home.py

TODO

  • Develop REST APIs
  • Create a streamlit app
  • Train a baseline model
  • Train on more data
  • Add more features
  • Define more models
  • Refine visualizations
  • Perform tests
  • Add more documentation
  • Add deployment options

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

License

MIT

Acknowledgements

Authors

Contributors

lucky-verma

10 commits

Languages

Python

49.7%

Jupyter Notebook

46.7%

Shell

2.1%

Dockerfile

1.5%