PREDICT-API Service

The service of the AI platform provides the API for the retrieval of typification predictions determined by the Machine Learning (ML) Pipeline.

Characteristics

Service Namepredict-api
Public APIPREDICT-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.

Configuration

The Inference Schema needs to be defined according to your client application and deployed via KAIROS-API Service service.

Read on

PREDICT-API Endpoints

The PREDICT-API endpoints allow for the development of client applications with integrated AI functionality. Keep reading

KAIROS-API Service

This service of the AI platform provides the API for the configuration of AI platform, such as the schema that binds the ML-extractors to fields in object schema. Keep reading

ML Training Pipeline

Responsible for preparing data for training, training of machine learning models, evaluation of trained models, and preparing for the deployment to the production. Keep reading