Optional
applicationOptional
awsOptional
awsOptional
awsOptional
credentialsAWS Credentials.
If no credentials are provided, the default credentials from @aws-sdk/credential-provider-node
will be used.
Optional
endpointOverride the default endpoint hostname.
Optional
endpointOptional
fetchA custom fetch function for low-level access to AWS API. Defaults to fetch().
Optional
init: RequestInitOptional
init: RequestInitOptional
guardrailRequired when Guardrail is in use.
Optional
guardrailIdentifier for the guardrail configuration.
Optional
guardrailVersion for the guardrail configuration.
Optional
maxMax tokens.
Optional
modelModel to use. For example, "amazon.titan-tg1-large", this is equivalent to the modelId property in the list-foundation-models api.
Optional
modelAdditional kwargs to pass to the model.
Optional
regionThe AWS region e.g. us-west-2
.
Fallback to AWS_DEFAULT_REGION env variable or region specified in ~/.aws/config in case it is not provided here.
Optional
stopOptional additional stop sequences to pass to the model. Currently only supported for Anthropic and AI21.
Optional
streamingWhether or not to stream responses
Optional
temperatureTemperature.
Optional
traceTrace settings for the Bedrock Guardrails.
Optional URL Encoded overide for URL model parameter in fetch. Necessary for invoking an Application Inference Profile. For example, "arn%3Aaws%3Abedrock%3Aus-east-1%3A1234567890%3Aapplication-inference-profile%2Fabcdefghi", will override this.model in final /invoke URL call. Must still provide
model
as normal modelId to benefit from all the metadata.