CfnPromptVersionPropsMixin

class aws_cdk.mixins_preview.aws_bedrock.mixins.CfnPromptVersionPropsMixin(props, *, strategy=None)

Bases: Mixin

Creates a static snapshot of your prompt that can be deployed to production.

For more information, see Deploy prompts using Prompt management by creating versions in the Amazon Bedrock User Guide.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-bedrock-promptversion.html
CloudformationResource:: AWS::Bedrock::PromptVersion
Mixin:: true
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.mixins_preview import mixins
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

cfn_prompt_version_props_mixin = bedrock_mixins.CfnPromptVersionPropsMixin(bedrock_mixins.CfnPromptVersionMixinProps(
    description="description",
    prompt_arn="promptArn",
    tags={
        "tags_key": "tags"
    }
),
    strategy=mixins.PropertyMergeStrategy.OVERRIDE
)

Create a mixin to apply properties to AWS::Bedrock::PromptVersion.

Parameters:

props (Union[CfnPromptVersionMixinProps, Dict[str, Any]]) – L1 properties to apply.
strategy (Optional[PropertyMergeStrategy]) – (experimental) Strategy for merging nested properties. Default: - PropertyMergeStrategy.MERGE

Methods

apply_to(construct)

Apply the mixin properties to the construct.

Parameters:: construct (IConstruct)
Return type:: IConstruct

supports(construct)

Check if this mixin supports the given construct.

Parameters:: construct (IConstruct)
Return type:: bool

Attributes

CFN_PROPERTY_KEYS = ['description', 'promptArn', 'tags']

Static Methods

classmethod is_mixin(x)

(experimental) Checks if x is a Mixin.

Parameters:: x (Any) – Any object.
Return type:: bool
Returns:: true if x is an object created from a class which extends Mixin.
Stability:: experimental

CachePointBlockProperty

class CfnPromptVersionPropsMixin.CachePointBlockProperty(*, type=None)

Bases: object

Defines a section of content to be cached for reuse in subsequent API calls.

Parameters:: type (Optional[str]) – Specifies the type of cache point within the CachePointBlock.
See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-cachepointblock.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

cache_point_block_property = bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
    type="type"
)

Attributes

type

Specifies the type of cache point within the CachePointBlock.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-cachepointblock.html#cfn-bedrock-promptversion-cachepointblock-type

ChatPromptTemplateConfigurationProperty

class CfnPromptVersionPropsMixin.ChatPromptTemplateConfigurationProperty(*, input_variables=None, messages=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:

input_variables (Union[IResolvable, Sequence[Union[IResolvable, PromptInputVariableProperty, Dict[str, Any]]], None]) – An array of the variables in the prompt template.
messages (Union[IResolvable, Sequence[Union[IResolvable, MessageProperty, Dict[str, Any]]], None]) – Contains messages in the chat for the prompt.
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:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-chatprompttemplateconfiguration.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# any: Any
# auto: Any
# json: Any

chat_prompt_template_configuration_property = bedrock_mixins.CfnPromptVersionPropsMixin.ChatPromptTemplateConfigurationProperty(
    input_variables=[bedrock_mixins.CfnPromptVersionPropsMixin.PromptInputVariableProperty(
        name="name"
    )],
    messages=[bedrock_mixins.CfnPromptVersionPropsMixin.MessageProperty(
        content=[bedrock_mixins.CfnPromptVersionPropsMixin.ContentBlockProperty(
            cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                type="type"
            ),
            text="text"
        )],
        role="role"
    )],
    system=[bedrock_mixins.CfnPromptVersionPropsMixin.SystemContentBlockProperty(
        cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
            type="type"
        ),
        text="text"
    )],
    tool_configuration=bedrock_mixins.CfnPromptVersionPropsMixin.ToolConfigurationProperty(
        tool_choice=bedrock_mixins.CfnPromptVersionPropsMixin.ToolChoiceProperty(
            any=any,
            auto=auto,
            tool=bedrock_mixins.CfnPromptVersionPropsMixin.SpecificToolChoiceProperty(
                name="name"
            )
        ),
        tools=[bedrock_mixins.CfnPromptVersionPropsMixin.ToolProperty(
            cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                type="type"
            ),
            tool_spec=bedrock_mixins.CfnPromptVersionPropsMixin.ToolSpecificationProperty(
                description="description",
                input_schema=bedrock_mixins.CfnPromptVersionPropsMixin.ToolInputSchemaProperty(
                    json=json
                ),
                name="name"
            )
        )]
    )
)

Attributes

input_variables

An array of the variables in the prompt template.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-chatprompttemplateconfiguration.html#cfn-bedrock-promptversion-chatprompttemplateconfiguration-inputvariables

messages

Contains messages in the chat for the prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-chatprompttemplateconfiguration.html#cfn-bedrock-promptversion-chatprompttemplateconfiguration-messages

system

Contains system prompts to provide context to the model or to describe how it should behave.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-chatprompttemplateconfiguration.html#cfn-bedrock-promptversion-chatprompttemplateconfiguration-system

tool_configuration

Configuration information for the tools that the model can use when generating a response.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-chatprompttemplateconfiguration.html#cfn-bedrock-promptversion-chatprompttemplateconfiguration-toolconfiguration

ContentBlockProperty

class CfnPromptVersionPropsMixin.ContentBlockProperty(*, cache_point=None, text=None)

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:

cache_point (Union[IResolvable, CachePointBlockProperty, Dict[str, Any], None]) – CachePoint to include in the message.
text (Optional[str]) – Text to include in the message.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-contentblock.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

content_block_property = bedrock_mixins.CfnPromptVersionPropsMixin.ContentBlockProperty(
    cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
        type="type"
    ),
    text="text"
)

Attributes

cache_point

CachePoint to include in the message.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-contentblock.html#cfn-bedrock-promptversion-contentblock-cachepoint

text

Text to include in the message.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-contentblock.html#cfn-bedrock-promptversion-contentblock-text

MessageProperty

class CfnPromptVersionPropsMixin.MessageProperty(*, content=None, role=None)

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]]], None]) – 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 a ContentBlock with a document field in the array, you must also include a ContentBlock with a text field. - You can only include images and documents if the role is user .
role (Optional[str]) – The role that the message plays in the message.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-message.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

message_property = bedrock_mixins.CfnPromptVersionPropsMixin.MessageProperty(
    content=[bedrock_mixins.CfnPromptVersionPropsMixin.ContentBlockProperty(
        cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
            type="type"
        ),
        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 a document field in the array, you must also include a ContentBlock with a text field.
You can only include images and documents if the role is user .

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-message.html#cfn-bedrock-promptversion-message-content
Type:: The message content. Note the following restrictions

role

The role that the message plays in the message.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-message.html#cfn-bedrock-promptversion-message-role

PromptAgentResourceProperty

class CfnPromptVersionPropsMixin.PromptAgentResourceProperty(*, agent_identifier=None)

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 (Optional[str]) – The ARN of the agent with which to use the prompt.
See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptagentresource.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

prompt_agent_resource_property = bedrock_mixins.CfnPromptVersionPropsMixin.PromptAgentResourceProperty(
    agent_identifier="agentIdentifier"
)

Attributes

agent_identifier

The ARN of the agent with which to use the prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptagentresource.html#cfn-bedrock-promptversion-promptagentresource-agentidentifier

PromptGenAiResourceProperty

class CfnPromptVersionPropsMixin.PromptGenAiResourceProperty(*, agent=None)

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], None]) – Specifies an Amazon Bedrock agent with which to use the prompt.
See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptgenairesource.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

prompt_gen_ai_resource_property = bedrock_mixins.CfnPromptVersionPropsMixin.PromptGenAiResourceProperty(
    agent=bedrock_mixins.CfnPromptVersionPropsMixin.PromptAgentResourceProperty(
        agent_identifier="agentIdentifier"
    )
)

Attributes

agent

Specifies an Amazon Bedrock agent with which to use the prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptgenairesource.html#cfn-bedrock-promptversion-promptgenairesource-agent

PromptInferenceConfigurationProperty

class CfnPromptVersionPropsMixin.PromptInferenceConfigurationProperty(*, text=None)

Bases: object

Contains inference configurations for the prompt.

Parameters:: text (Union[IResolvable, PromptModelInferenceConfigurationProperty, Dict[str, Any], None]) – Contains inference configurations for a text prompt.
See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptinferenceconfiguration.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

prompt_inference_configuration_property = bedrock_mixins.CfnPromptVersionPropsMixin.PromptInferenceConfigurationProperty(
    text=bedrock_mixins.CfnPromptVersionPropsMixin.PromptModelInferenceConfigurationProperty(
        max_tokens=123,
        stop_sequences=["stopSequences"],
        temperature=123,
        top_p=123
    )
)

Attributes

text

Contains inference configurations for a text prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptinferenceconfiguration.html#cfn-bedrock-promptversion-promptinferenceconfiguration-text

PromptInputVariableProperty

class CfnPromptVersionPropsMixin.PromptInputVariableProperty(*, name=None)

Bases: object

Contains information about a variable in the prompt.

Parameters:: name (Optional[str]) – The name of the variable.
See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptinputvariable.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

prompt_input_variable_property = bedrock_mixins.CfnPromptVersionPropsMixin.PromptInputVariableProperty(
    name="name"
)

Attributes

name

The name of the variable.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptinputvariable.html#cfn-bedrock-promptversion-promptinputvariable-name

PromptMetadataEntryProperty

class CfnPromptVersionPropsMixin.PromptMetadataEntryProperty(*, key=None, value=None)

Bases: object

Contains a key-value pair that defines a metadata tag and value to attach to a prompt variant.

For more information, see Create a prompt using Prompt management .

Parameters:

key (Optional[str]) – The key of a metadata tag for a prompt variant.
value (Optional[str]) – The value of a metadata tag for a prompt variant.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmetadataentry.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

prompt_metadata_entry_property = bedrock_mixins.CfnPromptVersionPropsMixin.PromptMetadataEntryProperty(
    key="key",
    value="value"
)

Attributes

key

The key of a metadata tag for a prompt variant.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmetadataentry.html#cfn-bedrock-promptversion-promptmetadataentry-key

value

The value of a metadata tag for a prompt variant.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmetadataentry.html#cfn-bedrock-promptversion-promptmetadataentry-value

PromptModelInferenceConfigurationProperty

class CfnPromptVersionPropsMixin.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:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmodelinferenceconfiguration.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

prompt_model_inference_configuration_property = bedrock_mixins.CfnPromptVersionPropsMixin.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.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmodelinferenceconfiguration.html#cfn-bedrock-promptversion-promptmodelinferenceconfiguration-maxtokens

stop_sequences

A list of strings that define sequences after which the model will stop generating.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmodelinferenceconfiguration.html#cfn-bedrock-promptversion-promptmodelinferenceconfiguration-stopsequences

temperature

Controls the randomness of the response.

Choose a lower value for more predictable outputs and a higher value for more surprising outputs.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmodelinferenceconfiguration.html#cfn-bedrock-promptversion-promptmodelinferenceconfiguration-temperature

top_p

The percentage of most-likely candidates that the model considers for the next token.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptmodelinferenceconfiguration.html#cfn-bedrock-promptversion-promptmodelinferenceconfiguration-topp

PromptTemplateConfigurationProperty

class CfnPromptVersionPropsMixin.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:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-prompttemplateconfiguration.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# any: Any
# auto: Any
# json: Any

prompt_template_configuration_property = bedrock_mixins.CfnPromptVersionPropsMixin.PromptTemplateConfigurationProperty(
    chat=bedrock_mixins.CfnPromptVersionPropsMixin.ChatPromptTemplateConfigurationProperty(
        input_variables=[bedrock_mixins.CfnPromptVersionPropsMixin.PromptInputVariableProperty(
            name="name"
        )],
        messages=[bedrock_mixins.CfnPromptVersionPropsMixin.MessageProperty(
            content=[bedrock_mixins.CfnPromptVersionPropsMixin.ContentBlockProperty(
                cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                    type="type"
                ),
                text="text"
            )],
            role="role"
        )],
        system=[bedrock_mixins.CfnPromptVersionPropsMixin.SystemContentBlockProperty(
            cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                type="type"
            ),
            text="text"
        )],
        tool_configuration=bedrock_mixins.CfnPromptVersionPropsMixin.ToolConfigurationProperty(
            tool_choice=bedrock_mixins.CfnPromptVersionPropsMixin.ToolChoiceProperty(
                any=any,
                auto=auto,
                tool=bedrock_mixins.CfnPromptVersionPropsMixin.SpecificToolChoiceProperty(
                    name="name"
                )
            ),
            tools=[bedrock_mixins.CfnPromptVersionPropsMixin.ToolProperty(
                cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                    type="type"
                ),
                tool_spec=bedrock_mixins.CfnPromptVersionPropsMixin.ToolSpecificationProperty(
                    description="description",
                    input_schema=bedrock_mixins.CfnPromptVersionPropsMixin.ToolInputSchemaProperty(
                        json=json
                    ),
                    name="name"
                )
            )]
        )
    ),
    text=bedrock_mixins.CfnPromptVersionPropsMixin.TextPromptTemplateConfigurationProperty(
        cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
            type="type"
        ),
        input_variables=[bedrock_mixins.CfnPromptVersionPropsMixin.PromptInputVariableProperty(
            name="name"
        )],
        text="text"
    )
)

Attributes

chat

Contains configurations to use the prompt in a conversational format.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-prompttemplateconfiguration.html#cfn-bedrock-promptversion-prompttemplateconfiguration-chat

text

Contains configurations for the text in a message for a prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-prompttemplateconfiguration.html#cfn-bedrock-promptversion-prompttemplateconfiguration-text

PromptVariantProperty

class CfnPromptVersionPropsMixin.PromptVariantProperty(*, additional_model_request_fields=None, gen_ai_resource=None, inference_configuration=None, metadata=None, model_id=None, name=None, template_configuration=None, template_type=None)

Bases: object

Contains details about a variant of the prompt.

Parameters:

additional_model_request_fields (Any) – Contains model-specific inference configurations that aren’t in the inferenceConfiguration field. To see model-specific inference parameters, see Inference request parameters and response fields for foundation models .
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.
metadata (Union[IResolvable, Sequence[Union[IResolvable, PromptMetadataEntryProperty, Dict[str, Any]]], None]) – An array of objects, each containing a key-value pair that defines a metadata tag and value to attach to a prompt variant.
model_id (Optional[str]) – The unique identifier of the model or inference profile with which to run inference on the prompt.
name (Optional[str]) – The name of the prompt variant.
template_configuration (Union[IResolvable, PromptTemplateConfigurationProperty, Dict[str, Any], None]) – Contains configurations for the prompt template.
template_type (Optional[str]) – The type of prompt template to use.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# additional_model_request_fields: Any
# any: Any
# auto: Any
# json: Any

prompt_variant_property = bedrock_mixins.CfnPromptVersionPropsMixin.PromptVariantProperty(
    additional_model_request_fields=additional_model_request_fields,
    gen_ai_resource=bedrock_mixins.CfnPromptVersionPropsMixin.PromptGenAiResourceProperty(
        agent=bedrock_mixins.CfnPromptVersionPropsMixin.PromptAgentResourceProperty(
            agent_identifier="agentIdentifier"
        )
    ),
    inference_configuration=bedrock_mixins.CfnPromptVersionPropsMixin.PromptInferenceConfigurationProperty(
        text=bedrock_mixins.CfnPromptVersionPropsMixin.PromptModelInferenceConfigurationProperty(
            max_tokens=123,
            stop_sequences=["stopSequences"],
            temperature=123,
            top_p=123
        )
    ),
    metadata=[bedrock_mixins.CfnPromptVersionPropsMixin.PromptMetadataEntryProperty(
        key="key",
        value="value"
    )],
    model_id="modelId",
    name="name",
    template_configuration=bedrock_mixins.CfnPromptVersionPropsMixin.PromptTemplateConfigurationProperty(
        chat=bedrock_mixins.CfnPromptVersionPropsMixin.ChatPromptTemplateConfigurationProperty(
            input_variables=[bedrock_mixins.CfnPromptVersionPropsMixin.PromptInputVariableProperty(
                name="name"
            )],
            messages=[bedrock_mixins.CfnPromptVersionPropsMixin.MessageProperty(
                content=[bedrock_mixins.CfnPromptVersionPropsMixin.ContentBlockProperty(
                    cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                        type="type"
                    ),
                    text="text"
                )],
                role="role"
            )],
            system=[bedrock_mixins.CfnPromptVersionPropsMixin.SystemContentBlockProperty(
                cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                    type="type"
                ),
                text="text"
            )],
            tool_configuration=bedrock_mixins.CfnPromptVersionPropsMixin.ToolConfigurationProperty(
                tool_choice=bedrock_mixins.CfnPromptVersionPropsMixin.ToolChoiceProperty(
                    any=any,
                    auto=auto,
                    tool=bedrock_mixins.CfnPromptVersionPropsMixin.SpecificToolChoiceProperty(
                        name="name"
                    )
                ),
                tools=[bedrock_mixins.CfnPromptVersionPropsMixin.ToolProperty(
                    cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                        type="type"
                    ),
                    tool_spec=bedrock_mixins.CfnPromptVersionPropsMixin.ToolSpecificationProperty(
                        description="description",
                        input_schema=bedrock_mixins.CfnPromptVersionPropsMixin.ToolInputSchemaProperty(
                            json=json
                        ),
                        name="name"
                    )
                )]
            )
        ),
        text=bedrock_mixins.CfnPromptVersionPropsMixin.TextPromptTemplateConfigurationProperty(
            cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
                type="type"
            ),
            input_variables=[bedrock_mixins.CfnPromptVersionPropsMixin.PromptInputVariableProperty(
                name="name"
            )],
            text="text"
        )
    ),
    template_type="templateType"
)

Attributes

additional_model_request_fields

Contains model-specific inference configurations that aren’t in the inferenceConfiguration field.

To see model-specific inference parameters, see Inference request parameters and response fields for foundation models .

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-additionalmodelrequestfields

gen_ai_resource

Specifies a generative AI resource with which to use the prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-genairesource

inference_configuration

Contains inference configurations for the prompt variant.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-inferenceconfiguration

metadata

An array of objects, each containing a key-value pair that defines a metadata tag and value to attach to a prompt variant.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-metadata

model_id

The unique identifier of the model or inference profile with which to run inference on the prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-modelid

name

The name of the prompt variant.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-name

template_configuration

Contains configurations for the prompt template.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-templateconfiguration

template_type

The type of prompt template to use.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-promptvariant.html#cfn-bedrock-promptversion-promptvariant-templatetype

SpecificToolChoiceProperty

class CfnPromptVersionPropsMixin.SpecificToolChoiceProperty(*, name=None)

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 (Optional[str]) – The name of the tool that the model must request.
See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-specifictoolchoice.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

specific_tool_choice_property = bedrock_mixins.CfnPromptVersionPropsMixin.SpecificToolChoiceProperty(
    name="name"
)

Attributes

name

The name of the tool that the model must request.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-specifictoolchoice.html#cfn-bedrock-promptversion-specifictoolchoice-name

SystemContentBlockProperty

class CfnPromptVersionPropsMixin.SystemContentBlockProperty(*, cache_point=None, text=None)

Bases: object

Contains configurations for instructions to provide the model for how to handle input.

To learn more, see Using the Converse API .

Parameters:

cache_point (Union[IResolvable, CachePointBlockProperty, Dict[str, Any], None]) – CachePoint to include in the system prompt.
text (Optional[str]) – A system prompt for the model.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-systemcontentblock.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

system_content_block_property = bedrock_mixins.CfnPromptVersionPropsMixin.SystemContentBlockProperty(
    cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
        type="type"
    ),
    text="text"
)

Attributes

cache_point

CachePoint to include in the system prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-systemcontentblock.html#cfn-bedrock-promptversion-systemcontentblock-cachepoint

text

A system prompt for the model.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-systemcontentblock.html#cfn-bedrock-promptversion-systemcontentblock-text

TextPromptTemplateConfigurationProperty

class CfnPromptVersionPropsMixin.TextPromptTemplateConfigurationProperty(*, cache_point=None, input_variables=None, text=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:

cache_point (Union[IResolvable, CachePointBlockProperty, Dict[str, Any], None]) – A cache checkpoint within a template configuration.
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.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-textprompttemplateconfiguration.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

text_prompt_template_configuration_property = bedrock_mixins.CfnPromptVersionPropsMixin.TextPromptTemplateConfigurationProperty(
    cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
        type="type"
    ),
    input_variables=[bedrock_mixins.CfnPromptVersionPropsMixin.PromptInputVariableProperty(
        name="name"
    )],
    text="text"
)

Attributes

cache_point

A cache checkpoint within a template configuration.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-textprompttemplateconfiguration.html#cfn-bedrock-promptversion-textprompttemplateconfiguration-cachepoint

input_variables

An array of the variables in the prompt template.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-textprompttemplateconfiguration.html#cfn-bedrock-promptversion-textprompttemplateconfiguration-inputvariables

text

The message for the prompt.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-textprompttemplateconfiguration.html#cfn-bedrock-promptversion-textprompttemplateconfiguration-text

ToolChoiceProperty

class CfnPromptVersionPropsMixin.ToolChoiceProperty(*, any=None, auto=None, tool=None)

Bases: object

Determines which tools the model should request in a call to Converse or ConverseStream .

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 and Amazon Nova models.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolchoice.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# any: Any
# auto: Any

tool_choice_property = bedrock_mixins.CfnPromptVersionPropsMixin.ToolChoiceProperty(
    any=any,
    auto=auto,
    tool=bedrock_mixins.CfnPromptVersionPropsMixin.SpecificToolChoiceProperty(
        name="name"
    )
)

Attributes

any

The model must request at least one tool (no text is generated).

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolchoice.html#cfn-bedrock-promptversion-toolchoice-any

auto

(Default).

The Model automatically decides if a tool should be called or whether to generate text instead.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolchoice.html#cfn-bedrock-promptversion-toolchoice-auto

tool

The Model must request the specified tool.

Only supported by Anthropic Claude 3 and Amazon Nova models.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolchoice.html#cfn-bedrock-promptversion-toolchoice-tool

ToolConfigurationProperty

class CfnPromptVersionPropsMixin.ToolConfigurationProperty(*, tool_choice=None, tools=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:

tool_choice (Union[IResolvable, ToolChoiceProperty, Dict[str, Any], None]) – If supported by model, forces the model to request a tool.
tools (Union[IResolvable, Sequence[Union[IResolvable, ToolProperty, Dict[str, Any]]], None]) – An array of tools that you want to pass to a model.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolconfiguration.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# any: Any
# auto: Any
# json: Any

tool_configuration_property = bedrock_mixins.CfnPromptVersionPropsMixin.ToolConfigurationProperty(
    tool_choice=bedrock_mixins.CfnPromptVersionPropsMixin.ToolChoiceProperty(
        any=any,
        auto=auto,
        tool=bedrock_mixins.CfnPromptVersionPropsMixin.SpecificToolChoiceProperty(
            name="name"
        )
    ),
    tools=[bedrock_mixins.CfnPromptVersionPropsMixin.ToolProperty(
        cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
            type="type"
        ),
        tool_spec=bedrock_mixins.CfnPromptVersionPropsMixin.ToolSpecificationProperty(
            description="description",
            input_schema=bedrock_mixins.CfnPromptVersionPropsMixin.ToolInputSchemaProperty(
                json=json
            ),
            name="name"
        )
    )]
)

Attributes

tool_choice

If supported by model, forces the model to request a tool.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolconfiguration.html#cfn-bedrock-promptversion-toolconfiguration-toolchoice

tools

An array of tools that you want to pass to a model.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolconfiguration.html#cfn-bedrock-promptversion-toolconfiguration-tools

ToolInputSchemaProperty

class CfnPromptVersionPropsMixin.ToolInputSchemaProperty(*, json=None)

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:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolinputschema.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# json: Any

tool_input_schema_property = bedrock_mixins.CfnPromptVersionPropsMixin.ToolInputSchemaProperty(
    json=json
)

Attributes

json

The JSON schema for the tool.

For more information, see JSON Schema Reference .

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolinputschema.html#cfn-bedrock-promptversion-toolinputschema-json

ToolProperty

class CfnPromptVersionPropsMixin.ToolProperty(*, cache_point=None, tool_spec=None)

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:

cache_point (Union[IResolvable, CachePointBlockProperty, Dict[str, Any], None]) – CachePoint to include in the tool configuration.
tool_spec (Union[IResolvable, ToolSpecificationProperty, Dict[str, Any], None]) – The specfication for the tool.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-tool.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# json: Any

tool_property = bedrock_mixins.CfnPromptVersionPropsMixin.ToolProperty(
    cache_point=bedrock_mixins.CfnPromptVersionPropsMixin.CachePointBlockProperty(
        type="type"
    ),
    tool_spec=bedrock_mixins.CfnPromptVersionPropsMixin.ToolSpecificationProperty(
        description="description",
        input_schema=bedrock_mixins.CfnPromptVersionPropsMixin.ToolInputSchemaProperty(
            json=json
        ),
        name="name"
    )
)

Attributes

cache_point

CachePoint to include in the tool configuration.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-tool.html#cfn-bedrock-promptversion-tool-cachepoint

tool_spec

The specfication for the tool.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-tool.html#cfn-bedrock-promptversion-tool-toolspec

ToolSpecificationProperty

class CfnPromptVersionPropsMixin.ToolSpecificationProperty(*, description=None, input_schema=None, name=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:

description (Optional[str]) – The description for the tool.
input_schema (Union[IResolvable, ToolInputSchemaProperty, Dict[str, Any], None]) – The input schema for the tool in JSON format.
name (Optional[str]) – The name for the tool.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolspecification.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.mixins_preview.aws_bedrock import mixins as bedrock_mixins

# json: Any

tool_specification_property = bedrock_mixins.CfnPromptVersionPropsMixin.ToolSpecificationProperty(
    description="description",
    input_schema=bedrock_mixins.CfnPromptVersionPropsMixin.ToolInputSchemaProperty(
        json=json
    ),
    name="name"
)

Attributes

description

The description for the tool.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolspecification.html#cfn-bedrock-promptversion-toolspecification-description

input_schema

The input schema for the tool in JSON format.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolspecification.html#cfn-bedrock-promptversion-toolspecification-inputschema

name

The name for the tool.

See:: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-promptversion-toolspecification.html#cfn-bedrock-promptversion-toolspecification-name