PREDICT-API Service
- Technische Redaktion
The service of the AI platform provides the API for the retrieval of typification predictions determined by the Machine Learning (ML) Pipeline.
Beta Version
The PREDICT-API service is a component of the Auto ML Platform. This platform is not included in yuuvis® Momentum installations and is available as a beta version only on request.
Characteristics
| Service Name | predict-api |
|---|---|
| Public API | PREDICT-API Endpoints |
Function
The Predcit-API service is responsible for calling the appropriate machine learning models, improving and validating results returned by the ML models, and finally creating responses for the calling party according to rules set in the inference schema.
The endpoints of the PREDICT-API service are provided in an own API that can be called by client applications.
>> PREDICT-API Endpoints
Requirements
The PREDICT-API service is a part of the Artificial Intelligence Platform and can run only in combination with the other included services.
If you want to use the PREDICT-API service for the AI integration in a client application based on our client libraries (e.g., yuuvis® client as a reference implementation), also the requirements of the involved services have to be considered.
Installation
The AI platform services including the PREDICT-API service are not yet included in yuuvis® Momentum installations but are only available on request.
Configuration
The PREDICT-API service is managed, configured, and maintained via the command line application Kairos CLI.
Especially, the Inference Schema needs to be defined according to your client application.