CfnPrompt
- class aws_cdk.aws_bedrock.CfnPrompt(scope, id, *, name, customer_encryption_key_arn=None, default_variant=None, description=None, tags=None, variants=None)
Bases:
CfnResource
Creates a prompt in your prompt library that you can add to a flow.
For more information, see Prompt management in Amazon Bedrock , Create a prompt using Prompt management and Prompt flows in Amazon Bedrock in the Amazon Bedrock User Guide.
- See:
http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-bedrock-prompt.html
- CloudformationResource:
AWS::Bedrock::Prompt
- 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 # any: Any # auto: Any # json: Any cfn_prompt = bedrock.CfnPrompt(self, "MyCfnPrompt", 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( text="text" )], role="role" )], # the properties below are optional input_variables=[bedrock.CfnPrompt.PromptInputVariableProperty( name="name" )], system=[bedrock.CfnPrompt.SystemContentBlockProperty( text="text" )], tool_configuration=bedrock.CfnPrompt.ToolConfigurationProperty( tools=[bedrock.CfnPrompt.ToolProperty( 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( 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 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 ) ), model_id="modelId" )] )
- Parameters:
scope (
Construct
) – Scope in which this resource is defined.id (
str
) – Construct identifier for this resource (unique in its scope).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.
Methods
- add_deletion_override(path)
Syntactic sugar for
addOverride(path, undefined)
.- Parameters:
path (
str
) – The path of the value to delete.- Return type:
None
- add_dependency(target)
Indicates that this resource depends on another resource and cannot be provisioned unless the other resource has been successfully provisioned.
This can be used for resources across stacks (or nested stack) boundaries and the dependency will automatically be transferred to the relevant scope.
- Parameters:
target (
CfnResource
) –- Return type:
None
- add_depends_on(target)
(deprecated) Indicates that this resource depends on another resource and cannot be provisioned unless the other resource has been successfully provisioned.
- Parameters:
target (
CfnResource
) –- Deprecated:
use addDependency
- Stability:
deprecated
- Return type:
None
- add_metadata(key, value)
Add a value to the CloudFormation Resource Metadata.
- Parameters:
key (
str
) –value (
Any
) –
- See:
- Return type:
None
https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/metadata-section-structure.html
Note that this is a different set of metadata from CDK node metadata; this metadata ends up in the stack template under the resource, whereas CDK node metadata ends up in the Cloud Assembly.
- add_override(path, value)
Adds an override to the synthesized CloudFormation resource.
To add a property override, either use
addPropertyOverride
or prefixpath
with “Properties.” (i.e.Properties.TopicName
).If the override is nested, separate each nested level using a dot (.) in the path parameter. If there is an array as part of the nesting, specify the index in the path.
To include a literal
.
in the property name, prefix with a\
. In most programming languages you will need to write this as"\\."
because the\
itself will need to be escaped.For example:
cfn_resource.add_override("Properties.GlobalSecondaryIndexes.0.Projection.NonKeyAttributes", ["myattribute"]) cfn_resource.add_override("Properties.GlobalSecondaryIndexes.1.ProjectionType", "INCLUDE")
would add the overrides Example:
"Properties": { "GlobalSecondaryIndexes": [ { "Projection": { "NonKeyAttributes": [ "myattribute" ] ... } ... }, { "ProjectionType": "INCLUDE" ... }, ] ... }
The
value
argument toaddOverride
will not be processed or translated in any way. Pass raw JSON values in here with the correct capitalization for CloudFormation. If you pass CDK classes or structs, they will be rendered with lowercased key names, and CloudFormation will reject the template.- Parameters:
path (
str
) –The path of the property, you can use dot notation to override values in complex types. Any intermediate keys will be created as needed.
value (
Any
) –The value. Could be primitive or complex.
- Return type:
None
- add_property_deletion_override(property_path)
Adds an override that deletes the value of a property from the resource definition.
- Parameters:
property_path (
str
) – The path to the property.- Return type:
None
- add_property_override(property_path, value)
Adds an override to a resource property.
Syntactic sugar for
addOverride("Properties.<...>", value)
.- Parameters:
property_path (
str
) – The path of the property.value (
Any
) – The value.
- Return type:
None
- apply_removal_policy(policy=None, *, apply_to_update_replace_policy=None, default=None)
Sets the deletion policy of the resource based on the removal policy specified.
The Removal Policy controls what happens to this resource when it stops being managed by CloudFormation, either because you’ve removed it from the CDK application or because you’ve made a change that requires the resource to be replaced.
The resource can be deleted (
RemovalPolicy.DESTROY
), or left in your AWS account for data recovery and cleanup later (RemovalPolicy.RETAIN
). In some cases, a snapshot can be taken of the resource prior to deletion (RemovalPolicy.SNAPSHOT
). A list of resources that support this policy can be found in the following link:- Parameters:
policy (
Optional
[RemovalPolicy
]) –apply_to_update_replace_policy (
Optional
[bool
]) – Apply the same deletion policy to the resource’s “UpdateReplacePolicy”. Default: truedefault (
Optional
[RemovalPolicy
]) – The default policy to apply in case the removal policy is not defined. Default: - Default value is resource specific. To determine the default value for a resource, please consult that specific resource’s documentation.
- See:
- Return type:
None
- get_att(attribute_name, type_hint=None)
Returns a token for an runtime attribute of this resource.
Ideally, use generated attribute accessors (e.g.
resource.arn
), but this can be used for future compatibility in case there is no generated attribute.- Parameters:
attribute_name (
str
) – The name of the attribute.type_hint (
Optional
[ResolutionTypeHint
]) –
- Return type:
- get_metadata(key)
Retrieve a value value from the CloudFormation Resource Metadata.
- Parameters:
key (
str
) –- See:
- Return type:
Any
https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/metadata-section-structure.html
Note that this is a different set of metadata from CDK node metadata; this metadata ends up in the stack template under the resource, whereas CDK node metadata ends up in the Cloud Assembly.
- inspect(inspector)
Examines the CloudFormation resource and discloses attributes.
- Parameters:
inspector (
TreeInspector
) – tree inspector to collect and process attributes.- Return type:
None
- obtain_dependencies()
Retrieves an array of resources this resource depends on.
This assembles dependencies on resources across stacks (including nested stacks) automatically.
- Return type:
List
[Union
[Stack
,CfnResource
]]
- obtain_resource_dependencies()
Get a shallow copy of dependencies between this resource and other resources in the same stack.
- Return type:
List
[CfnResource
]
- override_logical_id(new_logical_id)
Overrides the auto-generated logical ID with a specific ID.
- Parameters:
new_logical_id (
str
) – The new logical ID to use for this stack element.- Return type:
None
- remove_dependency(target)
Indicates that this resource no longer depends on another resource.
This can be used for resources across stacks (including nested stacks) and the dependency will automatically be removed from the relevant scope.
- Parameters:
target (
CfnResource
) –- Return type:
None
- replace_dependency(target, new_target)
Replaces one dependency with another.
- Parameters:
target (
CfnResource
) – The dependency to replace.new_target (
CfnResource
) – The new dependency to add.
- Return type:
None
- to_string()
Returns a string representation of this construct.
- Return type:
str
- Returns:
a string representation of this resource
Attributes
- CFN_RESOURCE_TYPE_NAME = 'AWS::Bedrock::Prompt'
- attr_arn
The Amazon Resource Name (ARN) of the prompt or the prompt version (if you specified a version in the request).
- CloudformationAttribute:
Arn
- attr_created_at
The time at which the prompt was created.
- CloudformationAttribute:
CreatedAt
- attr_id
The unique identifier of the prompt.
- CloudformationAttribute:
Id
- attr_updated_at
The time at which the prompt was last updated.
- CloudformationAttribute:
UpdatedAt
- attr_version
The version of the prompt that this summary applies to.
- CloudformationAttribute:
Version
- cdk_tag_manager
Tag Manager which manages the tags for this resource.
- cfn_options
Options for this resource, such as condition, update policy etc.
- cfn_resource_type
AWS resource type.
- creation_stack
return:
the stack trace of the point where this Resource was created from, sourced from the +metadata+ entry typed +aws:cdk:logicalId+, and with the bottom-most node +internal+ entries filtered.
- 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.
- description
The description of the prompt.
- logical_id
The logical ID for this CloudFormation stack element.
The logical ID of the element is calculated from the path of the resource node in the construct tree.
To override this value, use
overrideLogicalId(newLogicalId)
.- Returns:
the logical ID as a stringified token. This value will only get resolved during synthesis.
- name
The name of the prompt.
- node
The tree node.
- ref
Return a string that will be resolved to a CloudFormation
{ Ref }
for this element.If, by any chance, the intrinsic reference of a resource is not a string, you could coerce it to an IResolvable through
Lazy.any({ produce: resource.ref })
.
- stack
The stack in which this element is defined.
CfnElements must be defined within a stack scope (directly or indirectly).
- tags
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.
Static Methods
- classmethod is_cfn_element(x)
Returns
true
if a construct is a stack element (i.e. part of the synthesized cloudformation template).Uses duck-typing instead of
instanceof
to allow stack elements from different versions of this library to be included in the same stack.- Parameters:
x (
Any
) –- Return type:
bool
- Returns:
The construct as a stack element or undefined if it is not a stack element.
- classmethod is_cfn_resource(x)
Check whether the given object is a CfnResource.
- Parameters:
x (
Any
) –- Return type:
bool
- classmethod is_construct(x)
Checks if
x
is a construct.Use this method instead of
instanceof
to properly detectConstruct
instances, even when the construct library is symlinked.Explanation: in JavaScript, multiple copies of the
constructs
library on disk are seen as independent, completely different libraries. As a consequence, the classConstruct
in each copy of theconstructs
library is seen as a different class, and an instance of one class will not test asinstanceof
the other class.npm install
will not create installations like this, but users may manually symlink construct libraries together or use a monorepo tool: in those cases, multiple copies of theconstructs
library can be accidentally installed, andinstanceof
will behave unpredictably. It is safest to avoid usinginstanceof
, and using this type-testing method instead.- Parameters:
x (
Any
) – Any object.- Return type:
bool
- Returns:
true if
x
is an object created from a class which extendsConstruct
.
ChatPromptTemplateConfigurationProperty
- class CfnPrompt.ChatPromptTemplateConfigurationProperty(*, messages, input_variables=None, system=None, tool_configuration=None)
Bases:
object
Contains configurations to use a prompt in a conversational format.
For more information, see Create a prompt using Prompt management .
- Parameters:
messages (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,MessageProperty
,Dict
[str
,Any
]]]]) – Contains messages in the chat for the prompt.input_variables (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,PromptInputVariableProperty
,Dict
[str
,Any
]]],None
]) – An array of the variables in the prompt template.system (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,SystemContentBlockProperty
,Dict
[str
,Any
]]],None
]) – Contains system prompts to provide context to the model or to describe how it should behave.tool_configuration (
Union
[IResolvable
,ToolConfigurationProperty
,Dict
[str
,Any
],None
]) – Configuration information for the tools that the model can use when generating a response.
- See:
- 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 # any: Any # auto: Any # json: Any chat_prompt_template_configuration_property = bedrock.CfnPrompt.ChatPromptTemplateConfigurationProperty( messages=[bedrock.CfnPrompt.MessageProperty( content=[bedrock.CfnPrompt.ContentBlockProperty( text="text" )], role="role" )], # the properties below are optional input_variables=[bedrock.CfnPrompt.PromptInputVariableProperty( name="name" )], system=[bedrock.CfnPrompt.SystemContentBlockProperty( text="text" )], tool_configuration=bedrock.CfnPrompt.ToolConfigurationProperty( tools=[bedrock.CfnPrompt.ToolProperty( 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" ) ) ) )
Attributes
- input_variables
An array of the variables in the prompt template.
- messages
Contains messages in the chat for the prompt.
- system
Contains system prompts to provide context to the model or to describe how it should behave.
- tool_configuration
Configuration information for the tools that the model can use when generating a response.
ContentBlockProperty
- class CfnPrompt.ContentBlockProperty(*, text)
Bases:
object
A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.
- Parameters:
text (
str
) – Text to include in the message.- See:
- 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 content_block_property = bedrock.CfnPrompt.ContentBlockProperty( text="text" )
Attributes
- text
Text to include in the message.
MessageProperty
- class CfnPrompt.MessageProperty(*, content, role)
Bases:
object
A message input, or returned from, a call to Converse or ConverseStream .
- Parameters:
content (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,ContentBlockProperty
,Dict
[str
,Any
]]]]) – The message content. Note the following restrictions:. - You can include up to 20 images. Each image’s size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively. - You can include up to five documents. Each document’s size must be no more than 4.5 MB. - If you include aContentBlock
with adocument
field in the array, you must also include aContentBlock
with atext
field. - You can only include images and documents if therole
isuser
.role (
str
) – The role that the message plays in the message.
- See:
- 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 message_property = bedrock.CfnPrompt.MessageProperty( content=[bedrock.CfnPrompt.ContentBlockProperty( text="text" )], role="role" )
Attributes
- content
.
You can include up to 20 images. Each image’s size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively.
You can include up to five documents. Each document’s size must be no more than 4.5 MB.
If you include a
ContentBlock
with adocument
field in the array, you must also include aContentBlock
with atext
field.You can only include images and documents if the
role
isuser
.
- See:
- Type:
The message content. Note the following restrictions
- role
The role that the message plays in the message.
PromptAgentResourceProperty
- class CfnPrompt.PromptAgentResourceProperty(*, agent_identifier)
Bases:
object
Contains specifications for an Amazon Bedrock agent with which to use the prompt.
For more information, see Create a prompt using Prompt management and Automate tasks in your application using conversational agents .
- Parameters:
agent_identifier (
str
) – The ARN of the agent with which to use the prompt.- See:
- 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 prompt_agent_resource_property = bedrock.CfnPrompt.PromptAgentResourceProperty( agent_identifier="agentIdentifier" )
Attributes
- agent_identifier
The ARN of the agent with which to use the prompt.
PromptGenAiResourceProperty
- class CfnPrompt.PromptGenAiResourceProperty(*, agent)
Bases:
object
Contains specifications for a generative AI resource with which to use the prompt.
For more information, see Create a prompt using Prompt management .
- Parameters:
agent (
Union
[IResolvable
,PromptAgentResourceProperty
,Dict
[str
,Any
]]) – Specifies an Amazon Bedrock agent with which to use the prompt.- See:
- 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 prompt_gen_ai_resource_property = bedrock.CfnPrompt.PromptGenAiResourceProperty( agent=bedrock.CfnPrompt.PromptAgentResourceProperty( agent_identifier="agentIdentifier" ) )
Attributes
- agent
Specifies an Amazon Bedrock agent with which to use the prompt.
PromptInferenceConfigurationProperty
- class CfnPrompt.PromptInferenceConfigurationProperty(*, text)
Bases:
object
Contains inference configurations for the prompt.
- Parameters:
text (
Union
[IResolvable
,PromptModelInferenceConfigurationProperty
,Dict
[str
,Any
]]) – Contains inference configurations for a text prompt.- See:
- 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 prompt_inference_configuration_property = bedrock.CfnPrompt.PromptInferenceConfigurationProperty( text=bedrock.CfnPrompt.PromptModelInferenceConfigurationProperty( max_tokens=123, stop_sequences=["stopSequences"], temperature=123, top_p=123 ) )
Attributes
- text
Contains inference configurations for a text prompt.
PromptInputVariableProperty
- class CfnPrompt.PromptInputVariableProperty(*, name=None)
Bases:
object
Contains information about a variable in the prompt.
- Parameters:
name (
Optional
[str
]) – The name of the variable.- See:
- 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 prompt_input_variable_property = bedrock.CfnPrompt.PromptInputVariableProperty( name="name" )
Attributes
PromptModelInferenceConfigurationProperty
- class CfnPrompt.PromptModelInferenceConfigurationProperty(*, max_tokens=None, stop_sequences=None, temperature=None, top_p=None)
Bases:
object
Contains inference configurations related to model inference for a prompt.
For more information, see Inference parameters .
- Parameters:
max_tokens (
Union
[int
,float
,None
]) – The maximum number of tokens to return in the response.stop_sequences (
Optional
[Sequence
[str
]]) – A list of strings that define sequences after which the model will stop generating.temperature (
Union
[int
,float
,None
]) – Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.top_p (
Union
[int
,float
,None
]) – The percentage of most-likely candidates that the model considers for the next token.
- See:
- 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 prompt_model_inference_configuration_property = bedrock.CfnPrompt.PromptModelInferenceConfigurationProperty( max_tokens=123, stop_sequences=["stopSequences"], temperature=123, top_p=123 )
Attributes
- max_tokens
The maximum number of tokens to return in the response.
- stop_sequences
A list of strings that define sequences after which the model will stop generating.
- temperature
Controls the randomness of the response.
Choose a lower value for more predictable outputs and a higher value for more surprising outputs.
- top_p
The percentage of most-likely candidates that the model considers for the next token.
PromptTemplateConfigurationProperty
- class CfnPrompt.PromptTemplateConfigurationProperty(*, chat=None, text=None)
Bases:
object
Contains the message for a prompt.
For more information, see Construct and store reusable prompts with Prompt management in Amazon Bedrock .
- Parameters:
chat (
Union
[IResolvable
,ChatPromptTemplateConfigurationProperty
,Dict
[str
,Any
],None
]) – Contains configurations to use the prompt in a conversational format.text (
Union
[IResolvable
,TextPromptTemplateConfigurationProperty
,Dict
[str
,Any
],None
]) – Contains configurations for the text in a message for a prompt.
- See:
- 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 # any: Any # auto: Any # json: Any prompt_template_configuration_property = bedrock.CfnPrompt.PromptTemplateConfigurationProperty( chat=bedrock.CfnPrompt.ChatPromptTemplateConfigurationProperty( messages=[bedrock.CfnPrompt.MessageProperty( content=[bedrock.CfnPrompt.ContentBlockProperty( text="text" )], role="role" )], # the properties below are optional input_variables=[bedrock.CfnPrompt.PromptInputVariableProperty( name="name" )], system=[bedrock.CfnPrompt.SystemContentBlockProperty( text="text" )], tool_configuration=bedrock.CfnPrompt.ToolConfigurationProperty( tools=[bedrock.CfnPrompt.ToolProperty( 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( 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" ) ) )
Attributes
- chat
Contains configurations to use the prompt in a conversational format.
- text
Contains configurations for the text in a message for a prompt.
PromptVariantProperty
- class CfnPrompt.PromptVariantProperty(*, name, template_configuration, template_type, gen_ai_resource=None, inference_configuration=None, model_id=None)
Bases:
object
Contains details about a variant of the prompt.
- Parameters:
name (
str
) – The name of the prompt variant.template_configuration (
Union
[IResolvable
,PromptTemplateConfigurationProperty
,Dict
[str
,Any
]]) – Contains configurations for the prompt template.template_type (
str
) – The type of prompt template to use.gen_ai_resource (
Union
[IResolvable
,PromptGenAiResourceProperty
,Dict
[str
,Any
],None
]) – Specifies a generative AI resource with which to use the prompt.inference_configuration (
Union
[IResolvable
,PromptInferenceConfigurationProperty
,Dict
[str
,Any
],None
]) – Contains inference configurations for the prompt variant.model_id (
Optional
[str
]) – The unique identifier of the model or inference profile with which to run inference on the prompt.
- See:
- 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 # any: Any # auto: Any # json: Any prompt_variant_property = bedrock.CfnPrompt.PromptVariantProperty( name="name", template_configuration=bedrock.CfnPrompt.PromptTemplateConfigurationProperty( chat=bedrock.CfnPrompt.ChatPromptTemplateConfigurationProperty( messages=[bedrock.CfnPrompt.MessageProperty( content=[bedrock.CfnPrompt.ContentBlockProperty( text="text" )], role="role" )], # the properties below are optional input_variables=[bedrock.CfnPrompt.PromptInputVariableProperty( name="name" )], system=[bedrock.CfnPrompt.SystemContentBlockProperty( text="text" )], tool_configuration=bedrock.CfnPrompt.ToolConfigurationProperty( tools=[bedrock.CfnPrompt.ToolProperty( 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( 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 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 ) ), model_id="modelId" )
Attributes
- gen_ai_resource
Specifies a generative AI resource with which to use the prompt.
- inference_configuration
Contains inference configurations for the prompt variant.
- model_id
//docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html>`_ with which to run inference on the prompt.
- See:
- Type:
The unique identifier of the model or `inference profile <https
- name
The name of the prompt variant.
- template_configuration
Contains configurations for the prompt template.
- template_type
The type of prompt template to use.
SpecificToolChoiceProperty
- class CfnPrompt.SpecificToolChoiceProperty(*, name)
Bases:
object
The model must request a specific tool.
For example,
{"tool" : {"name" : "Your tool name"}}
. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide .. epigraph:This field is only supported by Anthropic Claude 3 models.
- Parameters:
name (
str
) – The name of the tool that the model must request.- See:
- 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 specific_tool_choice_property = bedrock.CfnPrompt.SpecificToolChoiceProperty( name="name" )
Attributes
- name
The name of the tool that the model must request.
SystemContentBlockProperty
- class CfnPrompt.SystemContentBlockProperty(*, text)
Bases:
object
Contains configurations for instructions to provide the model for how to handle input.
To learn more, see Using the Converse API .
- Parameters:
text (
str
) – A system prompt for the model.- See:
- 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 system_content_block_property = bedrock.CfnPrompt.SystemContentBlockProperty( text="text" )
Attributes
- text
A system prompt for the model.
TextPromptTemplateConfigurationProperty
- class CfnPrompt.TextPromptTemplateConfigurationProperty(*, input_variables=None, text=None, text_s3_location=None)
Bases:
object
Contains configurations for a text prompt template.
To include a variable, enclose a word in double curly braces as in
{{variable}}
.- Parameters:
input_variables (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,PromptInputVariableProperty
,Dict
[str
,Any
]]],None
]) – An array of the variables in the prompt template.text (
Optional
[str
]) – The message for the prompt.text_s3_location (
Union
[IResolvable
,TextS3LocationProperty
,Dict
[str
,Any
],None
]) – The Amazon S3 location of the prompt text.
- See:
- 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 text_prompt_template_configuration_property = bedrock.CfnPrompt.TextPromptTemplateConfigurationProperty( 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" ) )
Attributes
- input_variables
An array of the variables in the prompt template.
- text
The message for the prompt.
- text_s3_location
The Amazon S3 location of the prompt text.
TextS3LocationProperty
- class CfnPrompt.TextS3LocationProperty(*, bucket, key, version=None)
Bases:
object
The Amazon S3 location of the prompt text.
- Parameters:
bucket (
str
) – The Amazon S3 bucket containing the prompt text.key (
str
) – The object key for the Amazon S3 location.version (
Optional
[str
]) – The version of the Amazon S3 location to use.
- See:
- 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 text_s3_location_property = bedrock.CfnPrompt.TextS3LocationProperty( bucket="bucket", key="key", # the properties below are optional version="version" )
Attributes
- bucket
The Amazon S3 bucket containing the prompt text.
- key
The object key for the Amazon S3 location.
- version
The version of the Amazon S3 location to use.
ToolChoiceProperty
- class CfnPrompt.ToolChoiceProperty(*, any=None, auto=None, tool=None)
Bases:
object
Determines which tools the model should request in a call to
Converse
orConverseStream
.ToolChoice
is only supported by Anthropic Claude 3 models and by Mistral AI Mistral Large. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.- Parameters:
any (
Any
) – The model must request at least one tool (no text is generated).auto (
Any
) – (Default). The Model automatically decides if a tool should be called or whether to generate text instead.tool (
Union
[IResolvable
,SpecificToolChoiceProperty
,Dict
[str
,Any
],None
]) – The Model must request the specified tool. Only supported by Anthropic Claude 3 models.
- See:
- 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 # any: Any # auto: Any tool_choice_property = bedrock.CfnPrompt.ToolChoiceProperty( any=any, auto=auto, tool=bedrock.CfnPrompt.SpecificToolChoiceProperty( name="name" ) )
Attributes
- any
The model must request at least one tool (no text is generated).
- auto
(Default).
The Model automatically decides if a tool should be called or whether to generate text instead.
- tool
The Model must request the specified tool.
Only supported by Anthropic Claude 3 models.
ToolConfigurationProperty
- class CfnPrompt.ToolConfigurationProperty(*, tools, tool_choice=None)
Bases:
object
Configuration information for the tools that you pass to a model.
For more information, see Tool use (function calling) in the Amazon Bedrock User Guide.
- Parameters:
tools (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,ToolProperty
,Dict
[str
,Any
]]]]) – An array of tools that you want to pass to a model.tool_choice (
Union
[IResolvable
,ToolChoiceProperty
,Dict
[str
,Any
],None
]) – If supported by model, forces the model to request a tool.
- See:
- 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 # any: Any # auto: Any # json: Any tool_configuration_property = bedrock.CfnPrompt.ToolConfigurationProperty( tools=[bedrock.CfnPrompt.ToolProperty( 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" ) ) )
Attributes
- tool_choice
If supported by model, forces the model to request a tool.
- tools
An array of tools that you want to pass to a model.
ToolInputSchemaProperty
- class CfnPrompt.ToolInputSchemaProperty(*, json)
Bases:
object
The schema for the tool.
The top level schema type must be
object
. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.- Parameters:
json (
Any
) – The JSON schema for the tool. For more information, see JSON Schema Reference .- See:
- 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 # json: Any tool_input_schema_property = bedrock.CfnPrompt.ToolInputSchemaProperty( json=json )
Attributes
- json
The JSON schema for the tool.
For more information, see JSON Schema Reference .
ToolProperty
- class CfnPrompt.ToolProperty(*, tool_spec)
Bases:
object
Information about a tool that you can use with the Converse API.
For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
- Parameters:
tool_spec (
Union
[IResolvable
,ToolSpecificationProperty
,Dict
[str
,Any
]]) – The specfication for the tool.- See:
- 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 # json: Any tool_property = bedrock.CfnPrompt.ToolProperty( tool_spec=bedrock.CfnPrompt.ToolSpecificationProperty( input_schema=bedrock.CfnPrompt.ToolInputSchemaProperty( json=json ), name="name", # the properties below are optional description="description" ) )
Attributes
- tool_spec
The specfication for the tool.
ToolSpecificationProperty
- class CfnPrompt.ToolSpecificationProperty(*, input_schema, name, description=None)
Bases:
object
The specification for the tool.
For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
- Parameters:
input_schema (
Union
[IResolvable
,ToolInputSchemaProperty
,Dict
[str
,Any
]]) – The input schema for the tool in JSON format.name (
str
) – The name for the tool.description (
Optional
[str
]) – The description for the tool.
- See:
- 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 # json: Any tool_specification_property = bedrock.CfnPrompt.ToolSpecificationProperty( input_schema=bedrock.CfnPrompt.ToolInputSchemaProperty( json=json ), name="name", # the properties below are optional description="description" )
Attributes
- description
The description for the tool.
- input_schema
The input schema for the tool in JSON format.