Exported Model Prediction API
Generates predictions by executing an exported machine learning model on the provided input data.
Endpoint:
/utilities/exported_model_prediction
Input Parameters:
- Provide Use case ID
- Provide Use case version
- Select Response format (view or download).
- Provide Data File.
- Provide Model File. (onnx/pkl)
Output:
Status message - Prediction results that can be viewed directly or downloaded based on the selected response format, along with a status message indicating success or failure.