TeradataAI Parameters | Teradata Package for Generative AI - TeradataAI Parameters - Teradata VantageCloud Lake

Lake - Analyze Your Data with ClearScape Analytics™

Deployment
VantageCloud
Edition
Lake
Product
Teradata VantageCloud Lake
Release Number
Published
February 2025
ft:locale
en-US
ft:lastEdition
2026-02-20
dita:mapPath
tcl1683670667798.ditamap
dita:ditavalPath
pny1626732985837.ditaval
dita:id
tcl1683670667798
Parameter Category Description Permitted Values Type Default Value ENV Variable Case Sensitivity
api_type Required Specifies the LLM platform. aws, azure, gcp, hugging_face, nim string N/A N/A Permitted values are not case sensitive.
authorization Required
authorization is mutually exclusive with access_key, secret_key, or session_key.
Specifies the existing authorization object name containing the credentials. Authorization object string N/A N/A No
region Required Specifies the name of your AWS Bedrock service region. Authorization object string N/A AWS_DEFAULT_REGION N/A
access_key Required
access_key is mutually exclusive with authorization.
Specifies the AWS Bedrock service access key. N/A string N/A AWS_ACCESS_KEY_ID Yes
secret_key Required
secret_key is mutually exclusive with authorization.
Specifies the AWS Bedrock service secret key. N/A string N/A AWS_SECRET_ACCESS_KEY Yes
model_name Required Specifies the name of the AWS Bedrock LLM to be used for text analytics tasks. Alphanumeric string with dashes. string N/A N/A Yes, value will be used as is for connecting to AWS.
session_key Optional Specifies the AWS Bedrock service session key. N/A string N/A AWS_SESSION_TOKEN Yes
model_args Optional Specifies the JSON string representing the inference parameters for the selected LLM model. N/A string N/A N/A No
model_operation Optional Specifies the model operation for AWS Bedrock. invoke,converse string invoke N/A No
Parameter Category Description Permitted Values Type Default Value ENV Variable Case Sensitivity
api_type Required Specifies the LLM platform. aws, azure, gcp, hugging_face, nim string N/A N/A Permitted values are not case sensitive.
authorization Required
authorization is mutually exclusive with api_key, api_version and api_base.
Specifies the existing authorization object name containing the credentials. Authorization object string N/A N/A No
api_base Required
api_base is mutually exclusive with authorization.
Specifies the LLM API base URL. URL string string N/A AZURE_OPENAI_ENDPOINT Yes
api_key Required
api_key is mutually exclusive with authorization.
Specifies the LLM API key. N/A string N/A AZURE_OPENAI_API_KEY Yes
api_version Required
api_version is mutually exclusive with authorization.
Specifies the LLM API version. N/A string N/A AZURE_OPENAI_API_VERSION Yes
deployment_id Required Specifies the deployment id of the LLM. It takes the engine id for Azure AI. N/A string N/A AZURE_OPENAI_DEPLOYMENT_ID Yes, value will be used as is for connecting to Azure.
model_name Optional Specifies the name of the Azure AI LLM to be used for text analytics tasks. Alphanumeric string with dashes string N/A N/A Yes, value will be used as is for connecting to Azure.
model_args Optional Specifies the JSON string representing the inference parameters for the selected LLM model. N/A string N/A N/A No
Parameter Category Description Permitted Values Type Default Value ENV Variable Case Sensitivity
api_type Required Specifies the LLM platform. aws, azure, gcp, hugging_face, nim string N/A N/A Permitted values are not case sensitive.
authorization Required
authorization is mutually exclusive with region, access_token, or project.
Specifies the existing authorization object name containing the credentials. Authorization object string N/A N/A No
region Required
region is mutually exclusive with authorization.
Specifies the name of your Google Cloud service region. N/A string N/A GOOGLE_CLOUD_REGION N/A
access_token Required
access_token is mutually exclusive with authorization.
Specifies the session token for Google Cloud. N/A string N/A GOOGLE_APPLICATION_CREDENTIALS Yes
project Required
project is mutually exclusive with authorization.
Specifies the name of the gcp project. N/A string N/A GOOGLE_CLOUD_PROJECT Yes
model_name Required Specifies the name of the Google Cloud LLM to be used for text analytics tasks. Alphanumeric string with dashes string N/A N/A Yes, value will be used as is for connecting to Google Cloud.
enable_safety Optional Specifies if the safety feature needs to be enabled. True,False boolean True N/A No
model_args Optional Specifies the JSON string representing the inference parameters for the selected LLM model. N/A string N/A N/A No
Parameter Category Description Permitted Values Type Default Value ENV Variable Case Sensitivity
api_type Required Specifies the LLM platform. aws, azure, gcp, hugging_face, nim string N/A N/A No
model_name Required Specifies the LLM model name. N/A string N/A N/A Yes
model_args Required Specifies the arguments for downloading and inferencing the LLM.
  • 'transformer_class': Sets the class specific to the model to allow easy loading of models.
  • 'task': Sets the task defining which pipeline will be returned.
dict N/A N/A N/A
ues_args Optional Specifies the parameters for the user environment service. 'env_name': Specifies the remote user environment. It can be the name of environment or the UserEnv object. If not specified, the model is installed in the default environment ('td_gen_ai_env'). dict N/A N/A N/A
asynchronous Optional Specifies if the model installation should be asynchronous. True, False boolean False N/A N/A
NVIDIA NIM
Parameter Category Description Permitted Values Type Default Value ENV Variable Case Sensitivity
api_type Required Specifies the LLM platform. aws, azure, gcp, hugging_face, nim string N/A N/A Permitted values are not case sensitive.
authorization Required
authorization is mutually exclusive with api_key and api_base.
Specifies the existing authorization object name containing the credentials. Authorization object string N/A N/A No
api_base Required
api_base is mutually exclusive with authorization.
Specifies the LLM API endpoint URL. URL string string N/A   Yes
api_key Required
api_key is mutually exclusive with authorization.
Specifies the LLM API key. N/A string N/A NIM_API_KEY Yes
model_name Optional Specifies the name of the NIM LLM to be used for text analytics tasks. Alphanumeric string with dashes string N/A N/A Yes
model_args Optional Specifies the JSON string representing the inference parameters for the selected LLM model. N/A string N/A N/A No