cog.yaml

build:
  cuda: "12.1"
  gpu: true
  python_version: "3.11"
  system_packages:
    - git
    - tree
    - wget
    - build-essential
    - tesseract-ocr
    - libtesseract-dev
    - libmagic1
    - ocrmypdf
    - tesseract-ocr-eng
    - tesseract-ocr-deu
    - tesseract-ocr-por
    - tesseract-ocr-spa
    - tesseract-ocr-rus
    - tesseract-ocr-fra
  run:
    - "wget https://github.com/ArtifexSoftware/ghostpdl-downloads/releases/download/gs10012/ghostscript-10.01.2.tar.gz"
    - "tar -xvf ghostscript-10.01.2.tar.gz"
    - "cd ghostscript-10.01.2; ls && chmod +x configure && ./configure; make install"
    - "rm -rf ghostscript-10.01.2"
    - "rm ghostscript-10.01.2.tar.gz"
  python_packages:
    - scikit-learn==1.3.2
    - Pillow==10.1.0
    - pytesseract==0.3.10
    - PyMuPDF==1.23.5
    - pymupdf-fonts==1.0.5
    - pydantic==1.10.11
    - nougat-ocr==0.1.17
    - transformers==4.34.1
    - numpy==1.26.1
    - python-dotenv==1.0.0
    - torch==2.1.1
    - ray==2.7.1
    - tqdm==4.66.1
    - tabulate==0.9.0
    - thefuzz==0.20.0
    - python-magic==0.4.27
    - pyspellchecker==0.7.2
    - ftfy==6.1.1
    - nltk==3.8.1
    - ocrmypdf==15.4.0
    - bitsandbytes==0.41.2.post2
    - fastapi==0.103.1
predict: "predict.py:Predictor"