PromptVariant

class aws_cdk.aws_bedrock_alpha.PromptVariant(*args: Any, **kwargs)

Bases: object

(experimental) Factory class for creating prompt variants.

Provides static methods to create different types of prompt variants with proper configuration and type safety.

Stability:: experimental
ExampleMetadata:: fixture=default infused

Example:

cmk = kms.Key(self, "cmk")
claude_model = bedrock.BedrockFoundationModel.ANTHROPIC_CLAUDE_SONNET_V1_0

variant1 = bedrock.PromptVariant.text(
    variant_name="variant1",
    model=claude_model,
    prompt_variables=["topic"],
    prompt_text="This is my first text prompt. Please summarize our conversation on: {{topic}}.",
    inference_configuration=bedrock.PromptInferenceConfiguration.text(
        temperature=1,
        top_p=0.999,
        max_tokens=2000
    )
)

prompt1 = bedrock.Prompt(self, "prompt1",
    prompt_name="prompt1",
    description="my first prompt",
    default_variant=variant1,
    variants=[variant1],
    kms_key=cmk
)

Static Methods

classmethod agent(*, agent_alias, prompt_text, model, variant_name, prompt_variables=None)

(experimental) Creates an agent prompt template variant.

Parameters:

agent_alias (IAgentAlias) – (experimental) An alias pointing to the agent version to be used.
prompt_text (str) – (experimental) The text prompt. Variables are used by enclosing its name with double curly braces as in {{variable_name}}.
model (IBedrockInvokable) – (experimental) The model which is used to run the prompt. The model could be a foundation model, a custom model, or a provisioned model.
variant_name (str) – (experimental) The name of the prompt variant.
prompt_variables (Optional[Sequence[str]]) – (experimental) The variables in the prompt template that can be filled in at runtime. Default: - No variables defined.

Return type:

IPromptVariant

Returns:

A PromptVariant configured for agent interactions

Stability:

experimental

classmethod chat(*, messages, inference_configuration=None, system=None, tool_configuration=None, model, variant_name, prompt_variables=None)

(experimental) Creates a chat template variant.

Use this template type when the model supports the Converse API or the Anthropic Claude Messages API. This allows you to include a System prompt and previous User messages and Assistant messages for context.

Parameters:

messages (Sequence[ChatMessage]) – (experimental) The messages in the chat prompt. Must include at least one User Message. The messages should alternate between User and Assistant.
inference_configuration (Optional[PromptInferenceConfiguration]) – (experimental) Inference configuration for the Chat Prompt. Default: - No inference configuration provided.
system (Optional[str]) – (experimental) Context or instructions for the model to consider before generating a response. Default: - No system message provided.
tool_configuration (Union[ToolConfiguration, Dict[str, Any], None]) – (experimental) The configuration with available tools to the model and how it must use them. Default: - No tool configuration provided.
model (IBedrockInvokable) – (experimental) The model which is used to run the prompt. The model could be a foundation model, a custom model, or a provisioned model.
variant_name (str) – (experimental) The name of the prompt variant.
prompt_variables (Optional[Sequence[str]]) – (experimental) The variables in the prompt template that can be filled in at runtime. Default: - No variables defined.

Return type:

IPromptVariant

Returns:

A PromptVariant configured for chat interactions

Stability:

experimental

classmethod text(*, prompt_text, inference_configuration=None, model, variant_name, prompt_variables=None)

(experimental) Creates a text template variant.

Parameters:

prompt_text (str) – (experimental) The text prompt. Variables are used by enclosing its name with double curly braces as in {{variable_name}}.
inference_configuration (Optional[PromptInferenceConfiguration]) – (experimental) Inference configuration for the Text Prompt. Default: - No inference configuration provided.
model (IBedrockInvokable) – (experimental) The model which is used to run the prompt. The model could be a foundation model, a custom model, or a provisioned model.
variant_name (str) – (experimental) The name of the prompt variant.
prompt_variables (Optional[Sequence[str]]) – (experimental) The variables in the prompt template that can be filled in at runtime. Default: - No variables defined.

Return type:

IPromptVariant

Returns:

A PromptVariant configured for text processing

Stability:

experimental