API_Request In-database Function Syntax Elements | OpenAI and Azure OpenAI - API_Request In-database Function Syntax Elements - Teradata Vantage

Teradata Vantage™ - API Integration Guide for Cloud Machine Learning
Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
1.4
Published
September 2023
ft:locale
en-US
ft:lastEdition
2023-09-28
dita:mapPath
mgu1643999543506.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
mgu1643999543506
Arguments Category Description Default Values Permitted Values Data Type Charset (Applicable for String) Case Sensitive
API_TYPE Required Specifies the API to be used. None
  • When connecting to OpenAI: open-ai-embedding
  • When connecting to Azure OpenAI: az-ai-embedding
 String Unicode  
AUTHORIZATION Required Specifies a JSON string representing key to access OpenAI or Azure OpenAI. None
JSON String of the following format:
  • For OpenAI: {"key": "openai-api-key"}
  • For Azure OpenAI:
    • {"Key":"az_ai_key", "Resource" : "azure_resource_name", "Deployment" : "azure_deployment_name"}
    • {"key": "az-ai-key"}
 String Unicode No, JSON keys are not case sensitive.MULTIDRAG
NUM_EMBEDDINGS Optional Number of embeddings to output 1536 Positive Integer      
MODEL_NAME Optional Name of OpenAI model to be used for computing embeddings “text-embedding-ada-002” Alphanumeric string with dashes String Unicode Yes, Value will be used as is for connecting to Azure.
TEXT_COLUMN Required Name of column of text to be used as input for computing embeddings None String name of Teradata column VARCHAR Unicode Argument is not case sensitive.