API_Request In-database Function Input | Amazon SageMaker | Vantage - API_Request In-database Function Input - Teradata Vantage

Teradata Vantageā„¢ - API Integration Guide for Cloud Machine Learning

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
1.4
Published
September 2023
Language
English (United States)
Last Update
2023-09-28
dita:mapPath
mgu1643999543506.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
mgu1643999543506

When API_Request in-database function is running with Amazon SageMaker, it has the following input requirements.

Input table columns are used to form the model input for SageMaker deployed models.

START_KEY_INDEX can be used to make few columns pass through without going to SageMaker models.

Along with the input table, ENDPOINT, AUTHORIZATION are required arguments. If endpoint is multi-model endpoint, TARGET_MODEL is also required.

Supported Input Data Types

API_Request supports following data types.

In CSV and JSON content types, all columns are serialized into string and then a csv/json structure is formed.

Data Type Category Teradata Data Type
Numeric
  • BYTEINT
  • SMALLINT
  • INTEGER
  • BIGINT
  • DECIMAL/NUMERIC
  • FLOAT/REAL/DOUBLE PRECISION
Character
  • CHAR
  • VARCHAR
DateTime
  • DATE
  • TIME
  • TIMESTAMP
  • TIME WITH TIME ZONE
  • TIMESTAMP WITH TIME ZONE