Sentiment Analysis: JSON Input

This workflow showcases how the Container Input (JSON) and Container Output (JSON) nodes can be used to create a REST API for a workflow that can then be deployed as inference workflow to KNIME Edge. The workflow can be called via REST and classifies multiple reviews as positive or negative.

When deployed to KNIME Edge, a POST request with the following JSON body can be used for testing:

{
"content": [
"What a crappy flight, I hated it! It was the worst experience ever",
"What a lovely flight! I had the best time!!!"
]
}

The response will be:

[
{
"Prediction (Document class) (Confidence)": 0.7526856112217033,
"Prediction (Sentiment)": "Negative"
},
{
"Prediction (Document class) (Confidence)": 0.716930368994336,
"Prediction (Sentiment)": "Positive"
}
]