Post: Predict Single

Endpoint: /pyspark_prediction/predict/single/

Executes a single-record prediction using distributed PySpark inference. Suitable for real-time, low-latency use cases.

Input Parameters:

• usecaseId (string, required): Unique identifier for the trained use case/model.
• usecaseVersion (integer, optional): Version of the use case (default:1).

• Request Body (application/json): JSON object representing the input feature values for a single prediction.

  Output:

  Returns a JSON object containing the prediction result(s) for the provided input.