interface ChatPromptVariantProps 🔹

Language	Type name
.NET	Amazon.CDK.AWS.Bedrock.Alpha.ChatPromptVariantProps
Go	github.com/aws/aws-cdk-go/awsbedrockalpha/v2#ChatPromptVariantProps
Java	software.amazon.awscdk.services.bedrock.alpha.ChatPromptVariantProps
Python	aws_cdk.aws_bedrock_alpha.ChatPromptVariantProps
TypeScript (source)	@aws-cdk/aws-bedrock-alpha » ChatPromptVariantProps

Properties for creating a chat prompt variant.

Example

const cmk = new kms.Key(this, 'cmk', {});

const variantChat = bedrock.PromptVariant.chat({
  variantName: 'variant1',
  model: bedrock.BedrockFoundationModel.ANTHROPIC_CLAUDE_3_5_SONNET_V1_0,
  messages: [
    bedrock.ChatMessage.user('From now on, you speak Japanese!'),
    bedrock.ChatMessage.assistant('Konnichiwa!'),
    bedrock.ChatMessage.user('From now on, you speak {{language}}!'),
  ],
  system: 'You are a helpful assistant that only speaks the language you`re told.',
  promptVariables: ['language'],
  toolConfiguration: {
    toolChoice: bedrock.ToolChoice.AUTO,
    tools: [
      bedrock.Tool.function({
        name: 'top_song',
        description: 'Get the most popular song played on a radio station.',
        inputSchema: {
          type: 'object',
          properties: {
            sign: {
              type: 'string',
              description: 'The call sign for the radio station for which you want the most popular song. Example calls signs are WZPZ and WKR.',
            },
          },
          required: ['sign'],
        },
      }),
    ],
  },
});

new bedrock.Prompt(this, 'prompt1', {
  promptName: 'prompt-chat',
  description: 'my first chat prompt',
  defaultVariant: variantChat,
  variants: [variantChat],
  kmsKey: cmk,
});

Properties

Name	Type	Description
messages🔹	ChatMessage[]	The messages in the chat prompt.
model🔹	IBedrockInvokable	The model which is used to run the prompt.
variantName🔹	string	The name of the prompt variant.
inferenceConfiguration?🔹	PromptInferenceConfiguration	Inference configuration for the Chat Prompt.
promptVariables?🔹	string[]	The variables in the prompt template that can be filled in at runtime.
system?🔹	string	Context or instructions for the model to consider before generating a response.
toolConfiguration?🔹	ToolConfiguration	The configuration with available tools to the model and how it must use them.

---

messages🔹

Type: ChatMessage[]

The messages in the chat prompt.

Must include at least one User Message. The messages should alternate between User and Assistant.

---

model🔹

Type: IBedrockInvokable

The model which is used to run the prompt.

The model could be a foundation model, a custom model, or a provisioned model.

---

variantName🔹

Type: string

The name of the prompt variant.

---

inferenceConfiguration?🔹

Type: PromptInferenceConfiguration (optional, default: No inference configuration provided.)

Inference configuration for the Chat Prompt.

---

promptVariables?🔹

Type: string[] (optional, default: No variables defined.)

The variables in the prompt template that can be filled in at runtime.

---

system?🔹

Type: string (optional, default: No system message provided.)

Context or instructions for the model to consider before generating a response.

---

toolConfiguration?🔹

Type: ToolConfiguration (optional, default: No tool configuration provided.)

The configuration with available tools to the model and how it must use them.