AWS::Bedrock::Agent PromptConfiguration

Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.

Syntax

To declare this entity in your AWS CloudFormation template, use the following syntax:

JSON

{
  "BasePromptTemplate" : String,
  "InferenceConfiguration" : InferenceConfiguration,
  "ParserMode" : String,
  "PromptCreationMode" : String,
  "PromptState" : String,
  "PromptType" : String
}

YAML

  BasePromptTemplate: String
  InferenceConfiguration: 
    InferenceConfiguration
  ParserMode: String
  PromptCreationMode: String
  PromptState: String
  PromptType: String

Properties

BasePromptTemplate

Defines the prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables. For more information, see Configure the prompt templates.

Required: No

Type: String

Minimum: 1

Maximum: 100000

Update requires: No interruption

InferenceConfiguration

Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType. For more information, see Inference parameters for foundation models.

Required: No

Type: InferenceConfiguration

Update requires: No interruption

ParserMode

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType. If you set the field as OVERRIDEN, the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.

Required: No

Type: String

Allowed values: DEFAULT | OVERRIDDEN

Update requires: No interruption

PromptCreationMode

Specifies whether to override the default prompt template for this promptType. Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate. If you leave it as DEFAULT, the agent uses a default prompt template.

Required: No

Type: String

Allowed values: DEFAULT | OVERRIDDEN

Update requires: No interruption

PromptState

Specifies whether to allow the agent to carry out the step specified in the promptType. If you set this value to DISABLED, the agent skips that step. The default state for each promptType is as follows.

• PRE_PROCESSING – ENABLED

• ORCHESTRATION – ENABLED

• KNOWLEDGE_BASE_RESPONSE_GENERATION – ENABLED

• POST_PROCESSING – DISABLED

Required: No

Type: String

Allowed values: ENABLED | DISABLED

Update requires: No interruption

PromptType

The step in the agent sequence that this prompt configuration applies to.

Required: No

Type: String

Allowed values: PRE_PROCESSING | ORCHESTRATION | POST_PROCESSING | KNOWLEDGE_BASE_RESPONSE_GENERATION

Update requires: No interruption