Package com.pulumi.aws.bedrock.outputs

Class AgentAgentPromptOverrideConfigurationPromptConfiguration

  • public final class AgentAgentPromptOverrideConfigurationPromptConfiguration
extends java.lang.Object

    • Method Detail

      • basePromptTemplate

        public java.lang.String basePromptTemplate()
        Returns:
        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](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-placeholders.html).

      • inferenceConfigurations

        public java.util.List<AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration> inferenceConfigurations()
        Returns:
        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](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html). See `inferenceConfiguration` Block for details.

      • parserMode

        public java.lang.String parserMode()
        Returns:
        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 argument as `OVERRIDDEN`, the `overrideLambda` argument in the `promptOverrideConfiguration` block must be specified with the ARN of a Lambda function. Valid values: `DEFAULT`, `OVERRIDDEN`.

      • promptCreationMode

        public java.lang.String promptCreationMode()
        Returns:
        Whether to override the default prompt template for this `promptType`. Set this argument 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. Valid values: `DEFAULT`, `OVERRIDDEN`.

      • promptState

        public java.lang.String promptState()
        Returns:
        Whether to allow the agent to carry out the step specified in the `promptType`. If you set this argument to `DISABLED`, the agent skips that step. Valid Values: `ENABLED`, `DISABLED`.

      • promptType

        public java.lang.String promptType()
        Returns:
        Step in the agent sequence that this prompt configuration applies to. Valid values: `PRE_PROCESSING`, `ORCHESTRATION`, `POST_PROCESSING`, `KNOWLEDGE_BASE_RESPONSE_GENERATION`, `MEMORY_SUMMARIZATION`.