name: etl_chromadb_scanned_pdf
python_env: python_env.yml

entry_points:
  main:
    parameters:

      input_artifact:
        description: Fully-qualified name for the input artifact
        type: string

      output_artifact:
        description: Name for the output artifact
        type: string

      output_type:
        description: Type for the artifact output
        type: string

      output_description:
        description: Description for the artifact
        type: string

      embedding_model:
        description: Fully-qualified name for the embedding model
        type: string


    command: >-
        python run.py --input_artifact {input_artifact} \
                      --output_artifact {output_artifact} \
                      --output_type {output_type} \
                      --output_description {output_description} \
                      --embedding_model {embedding_model}