Launch a async Batch job, given a job name that will be used as its id.

Each request should have the same parameters as you would normally pass to a feature.

You can also pass an optional paramater name to help better identify each requests you send.

Example with text/sentiment_analysis:

"requests": [
    {
        "text": "It's -25 outside and I am so hot.",
        "language": "en",
        "providers": "google,amazon"
    },
    {
        "name": "mixed",
        "text": "Overall I am satisfied with my experience at Amazon, but two areas of major improvement needed.",
        "language": "en",
        "providers": "google"
    },
    ...
]

Limitations:

You can have up to 5 concurrent running Jobs & input up to 500 requests per Batch