Google Gemini LLM Syntax | Text AI Analytic Functions - Google Gemini LLM Syntax - Teradata VantageCloud Lake

Google_Gemini_LLM_arguments
(
    ApiType('gcp') 
    [AUTHORIZATION([DatabaseName.]AuthorizationObjectName] 
    |{
    AccessToken('<gcp_vertex_access token>')
    REGION('<gcp_region>')
    Project('<gcp_project_name>')
    }
    ModelName('<gemini-model-name>')
    [ModelArgs('{"Temperature": "temp", "top_p" : "top_p"}')]
    [EnableSafety('TRUE')]
)

Required Syntax Elements

ApiType

Identification of the cloud platform.

Permitted values (not case-sensitive): aws, azure, gcp, nim, litellm

AUTHORIZATION

Mutually exclusive with region, AccessToken, and Project.

Authorization object containing the credentials.

region

Mutually exclusive with AUTHORIZATION.

Specifies the name of your Google Cloud service region.

AccessToken

Mutually exclusive with AUTHORIZATION.

Specifies the session token for the session token for Google Cloud.

Project

Mutually exclusive with AUTHORIZATION.

Specifies the name of the gcp project.

ModelName

Name of AI LLM to be used for text analytics tasks.

Permitted values: Case-sensitive alphanumeric string with dashes. The value is used as is for connection to Google Cloud.

Optional Syntax Elements

EnableSafety

Specifies if the safety feature needs to be enabled.

Default value: True

ModelArgs

JSON string representing the inference parameters for the selected LLM model.