Workflow execution

The wf_client run command can be used to execute a project.

Use -p {PATH TO THE WORKFLOW PROJECT} to run a project from another directory (it defaults to current working directory)

Single task-group

• You can specify the analysed task group using the --task-group flag.

• You can pass entries using -e entry_name:entry_value

• You can pass metadata using -m metadata_name:metadata_value

• You can provide the path to your .env file if not previously sourced using the --env flag

To pass several entries/metadata, simply repeat the above syntax (multiple -e ...)

wf_client run  --task-group pm_ouvert_avant_travaux -e image_input:./pm-ouvert-avant-travaux.jpeg 

[INFO 16:54:13.961 client.py:37] engine initialization: 0.016 seconds
[INFO 16:54:13.968 client.py:37] workflow execution: 0.002 seconds
pm_ouvert_avant_travaux:
        [✓] pm-ouvert-avant-travaux-bool (bool): True
        [✓] pm-ouvert-avant-travaux-pres-etiquette-bool (bool): True
        [✓] pm-ouvert-avant-travaux-ocr-etiquette (str): 14222

Add the flag -d if you want the analysed image to be displayed with the drawn predicted regions

Multiple task-groups

You can run multiple task-groups with a shared environment (like a work-order) using an input file.

The format for the input file is:

[
    {
        "task_group": "pm_ouvert_avant_travaux",
        "entries": {
            "image_input": "./pm-ouvert-avant-travaux.jpeg"
        },
        "metadata": {
            "key": "value"
        }
    },
    {
        "task_group": "pm_ouvert_apres_travaux",
        "entries": {
            "image_input": "./pm-ouvert-apres-travaux.jpeg"
        }
    }
]

Then, running the workflow using

wf_client run -i inputs.json