CfnPromptProps
- class aws_cdk.aws_bedrock.CfnPromptProps(*, name, customer_encryption_key_arn=None, default_variant=None, description=None, tags=None, variants=None)
Bases:
object
Properties for defining a
CfnPrompt
.- Parameters:
name (
str
) – The name of the prompt.customer_encryption_key_arn (
Optional
[str
]) – The Amazon Resource Name (ARN) of the KMS key that the prompt is encrypted with.default_variant (
Optional
[str
]) – The name of the default variant for the prompt. This value must match thename
field in the relevant PromptVariant object.description (
Optional
[str
]) – The description of the prompt.tags (
Optional
[Mapping
[str
,str
]]) – Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:. - Tag naming limits and requirements - Tagging best practicesvariants (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,PromptVariantProperty
,Dict
[str
,Any
]]],None
]) – A list of objects, each containing details about a variant of the prompt.
- See:
http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-bedrock-prompt.html
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_bedrock as bedrock # additional_model_request_fields: Any # any: Any # auto: Any # json: Any cfn_prompt_props = bedrock.CfnPromptProps( name="name", # the properties below are optional customer_encryption_key_arn="customerEncryptionKeyArn", default_variant="defaultVariant", description="description", tags={ "tags_key": "tags" }, variants=[bedrock.CfnPrompt.PromptVariantProperty( name="name", template_configuration=bedrock.CfnPrompt.PromptTemplateConfigurationProperty( chat=bedrock.CfnPrompt.ChatPromptTemplateConfigurationProperty( messages=[bedrock.CfnPrompt.MessageProperty( content=[bedrock.CfnPrompt.ContentBlockProperty( cache_point=bedrock.CfnPrompt.CachePointBlockProperty( type="type" ), text="text" )], role="role" )], # the properties below are optional input_variables=[bedrock.CfnPrompt.PromptInputVariableProperty( name="name" )], system=[bedrock.CfnPrompt.SystemContentBlockProperty( cache_point=bedrock.CfnPrompt.CachePointBlockProperty( type="type" ), text="text" )], tool_configuration=bedrock.CfnPrompt.ToolConfigurationProperty( tools=[bedrock.CfnPrompt.ToolProperty( cache_point=bedrock.CfnPrompt.CachePointBlockProperty( type="type" ), tool_spec=bedrock.CfnPrompt.ToolSpecificationProperty( input_schema=bedrock.CfnPrompt.ToolInputSchemaProperty( json=json ), name="name", # the properties below are optional description="description" ) )], # the properties below are optional tool_choice=bedrock.CfnPrompt.ToolChoiceProperty( any=any, auto=auto, tool=bedrock.CfnPrompt.SpecificToolChoiceProperty( name="name" ) ) ) ), text=bedrock.CfnPrompt.TextPromptTemplateConfigurationProperty( cache_point=bedrock.CfnPrompt.CachePointBlockProperty( type="type" ), input_variables=[bedrock.CfnPrompt.PromptInputVariableProperty( name="name" )], text="text", text_s3_location=bedrock.CfnPrompt.TextS3LocationProperty( bucket="bucket", key="key", # the properties below are optional version="version" ) ) ), template_type="templateType", # the properties below are optional additional_model_request_fields=additional_model_request_fields, gen_ai_resource=bedrock.CfnPrompt.PromptGenAiResourceProperty( agent=bedrock.CfnPrompt.PromptAgentResourceProperty( agent_identifier="agentIdentifier" ) ), inference_configuration=bedrock.CfnPrompt.PromptInferenceConfigurationProperty( text=bedrock.CfnPrompt.PromptModelInferenceConfigurationProperty( max_tokens=123, stop_sequences=["stopSequences"], temperature=123, top_p=123 ) ), metadata=[bedrock.CfnPrompt.PromptMetadataEntryProperty( key="key", value="value" )], model_id="modelId" )] )
Attributes
- customer_encryption_key_arn
The Amazon Resource Name (ARN) of the KMS key that the prompt is encrypted with.
- default_variant
The name of the default variant for the prompt.
This value must match the
name
field in the relevant PromptVariant object.
- description
The description of the prompt.
- name
The name of the prompt.
- tags
.
- See:
- Type:
Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources
- variants
A list of objects, each containing details about a variant of the prompt.