tesseract_test.yaml

# The directory containing the pdfs to convert
pdf_dir: /lus/eagle/projects/argonne_tpc/siebenschuh/aurora_gpt/small-pdf-dataset/

# The directory to place the converted pdfs in
out_dir: /eagle/projects/argonne_tpc/siebenschuh/aurora_gpt/output/tesseract/

# The settings for the pdf parser
parser_settings:
  # The name of the parser to use
  name: tesseract
  # Image resolution (DPI)
  dpi: 50
  # Language
  lang: eng

# The compute settings for the workflow
compute_settings:
  # The name of the compute platform to use
  name: polaris
  # The number of compute nodes to use
  num_nodes: 2
  # Make sure to update the path to your conda environment and HF cache
  worker_init: "module use /soft/modulefiles; module load conda/2024-04-29; conda activate adaparse"
  # The scheduler options to use when submitting jobs
  scheduler_options: "#PBS -l filesystems=home:eagle"
  # Make sure to change the account to the account you want to charge
  account: argonne_tpc
  # The HPC queue to submit to
  queue: debug
  # The amount of time to request for your job
  walltime: 00:30:00