Class: Aws::BedrockRuntime::Types::InferenceConfiguration

Inherits:

Struct

• Object
• Struct
• Aws::BedrockRuntime::Types::InferenceConfiguration

Includes:

Structure

Defined in:

lib/aws-sdk-bedrockruntime/types.rb

Overview

Base inference parameters to pass to a model in a call to

Converse][1

or [ConverseStream]. For more information, see

[Inference parameters for foundation models].

If you need to pass additional parameters that the model supports, use the ‘additionalModelRequestFields` request field in the call to `Converse` or `ConverseStream`. For more information, see [Model parameters].

[1]: docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html [2]: docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html [3]: docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[]

Instance Attribute Summary

• #max_tokens ⇒ Integer

  The maximum number of tokens to allow in the generated response.

• #stop_sequences ⇒ Array<String>

  A list of stop sequences.

• #temperature ⇒ Float

  The likelihood of the model selecting higher-probability options while generating a response.

• #top_p ⇒ Float

  The percentage of most-likely candidates that the model considers for the next token.

Instance Attribute Details

#max_tokens ⇒ Integer

The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see [Inference parameters for foundation models].

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

Returns:

• (Integer)

# File 'lib/aws-sdk-bedrockruntime/types.rb', line 1430

class InferenceConfiguration < Struct.new(
  :max_tokens,
  :temperature,
  :top_p,
  :stop_sequences)
  SENSITIVE = []
  include Aws::Structure
end

#stop_sequences ⇒ Array<String>

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

Returns:

• (Array<String>)

# File 'lib/aws-sdk-bedrockruntime/types.rb', line 1430

class InferenceConfiguration < Struct.new(
  :max_tokens,
  :temperature,
  :top_p,
  :stop_sequences)
  SENSITIVE = []
  include Aws::Structure
end

#temperature ⇒ Float

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

The default value is the default value for the model that you are using. For more information, see [Inference parameters for foundation models].

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

Returns:

• (Float)

# File 'lib/aws-sdk-bedrockruntime/types.rb', line 1430

class InferenceConfiguration < Struct.new(
  :max_tokens,
  :temperature,
  :top_p,
  :stop_sequences)
  SENSITIVE = []
  include Aws::Structure
end

#top_p ⇒ Float

The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for ‘topP`, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.

The default value is the default value for the model that you are using. For more information, see [Inference parameters for foundation models].

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

Returns:

• (Float)

# File 'lib/aws-sdk-bedrockruntime/types.rb', line 1430

class InferenceConfiguration < Struct.new(
  :max_tokens,
  :temperature,
  :top_p,
  :stop_sequences)
  SENSITIVE = []
  include Aws::Structure
end