Class: Aws::BedrockAgentRuntime::Types::PromptConfiguration

Inherits:

Struct

• Object
• Struct
• Aws::BedrockAgentRuntime::Types::PromptConfiguration

Includes:

Structure

Defined in:

lib/aws-sdk-bedrockagentruntime/types.rb

Overview

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

[1]: docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[:base_prompt_template]

Instance Attribute Summary

• #additional_model_request_fields ⇒ Hash, ...

  If the Converse or ConverseStream operations support the model, ‘additionalModelRequestFields` contains additional inference parameters, beyond the base set of inference parameters in the `inferenceConfiguration` field.

• #base_prompt_template ⇒ String

  Defines the prompt template with which to replace the default prompt template.

• #foundation_model ⇒ String

  The foundation model to use.

• #inference_configuration ⇒ Types::InferenceConfiguration

  Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the ‘promptType`.

• #parser_mode ⇒ String

  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`.

• #prompt_creation_mode ⇒ String

  Specifies whether to override the default prompt template for this ‘promptType`.

• #prompt_state ⇒ String

  Specifies whether to allow the inline agent to carry out the step specified in the ‘promptType`.

• #prompt_type ⇒ String

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

Instance Attribute Details

#additional_model_request_fields ⇒ Hash, ...

If the Converse or ConverseStream operations support the model, ‘additionalModelRequestFields` contains additional inference parameters, beyond the base set of inference parameters in the `inferenceConfiguration` field.

For more information, see *Inference request parameters and response fields for foundation models* in the Amazon Bedrock user guide.

Returns:

• (Hash, Array, String, Numeric, Boolean)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end

#base_prompt_template ⇒ String

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].

[1]: docs.aws.amazon.com/bedrock/latest/userguide/prompt-placeholders.html [2]: docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts-configure.html

Returns:

• (String)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end

#foundation_model ⇒ String

The foundation model to use.

Returns:

• (String)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end

#inference_configuration ⇒ Types::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].

[1]: docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html

Returns:

• (Types::InferenceConfiguration)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end

#parser_mode ⇒ String

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 `OVERRIDDEN`, the `overrideLambda` field in the

PromptOverrideConfiguration][1

must be specified with the ARN of a

Lambda function.

[1]: docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_PromptOverrideConfiguration.html

Returns:

• (String)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end

#prompt_creation_mode ⇒ String

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.

Returns:

• (String)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end

#prompt_state ⇒ String

Specifies whether to allow the inline 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`

Returns:

• (String)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end

#prompt_type ⇒ String

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

Returns:

• (String)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 6697

class PromptConfiguration < Struct.new(
  :additional_model_request_fields,
  :base_prompt_template,
  :foundation_model,
  :inference_configuration,
  :parser_mode,
  :prompt_creation_mode,
  :prompt_state,
  :prompt_type)
  SENSITIVE = [:base_prompt_template]
  include Aws::Structure
end