PREDICT-API Endpoints
The PREDICT-API endpoints allow for the development of client applications with integrated AI functionality.
Beta Version
The PREDICT-API service is a component of the Artificial Intelligence Platform. This platform is not included in yuuvis® Momentum installations and is available as a beta version only on request.
| HTTP Method as of product version | Purpose | Response Format | Description |
|---|---|---|---|
Status Information | |||
| GET as of 2021 Autumn | Retrieve status of Model Serving for the tenant | JSON | Returns a JSON structure containing the status (activated or deactivated) of the processes provided by ML pipeline for the tenant. |
| GET as of 2021 Autumn | Retrieve status of Model Serving for specified app | JSON | Returns a JSON structure containing the status (activated or deactivated) of the processes provided by the ML pipeline for the app specified by |
Object Classification | |||
| GET as of 2021 Autumn | Retrieve classification prediction for a single object | JSON | Retrieves a classification prediction for a single object identified by its |
| POST as of 2021 Autumn | Retrieve classification prediction for multiple objects | JSON | Retrieves classification predictions for multiple objects identified by their |
| POST as of 2021 Autumn | Send classification feedback to Model Serving | HTTP status code | Sends a feedback to the ML Pipeline informing about the user decision for one of the object types suggested in a prediction. |
Metadata Extraction | |||
| GET as of 2021 Autumn | Retrieve extraction prediction for a single object | JSON | Retrieves a metadata extraction prediction for the binary content file of a single object identified by its |
| POST as of 2021 Autumn | Retrieve extraction prediction for multiple objects | JSON | Retrieves metadata extraction predictions for the binary content files of multiple objects identified by their |
| POST as of 2021 Autumn | Send extraction feedback to Model Serving | HTTP status code | Sends feedback to the ML Pipeline informing about the user decision for one of the property values suggested in a prediction. |