Class: Google::Cloud::AIPlatform::V1::GenerateContentResponse::UsageMetadata

Inherits:

Object

• Object
• Google::Cloud::AIPlatform::V1::GenerateContentResponse::UsageMetadata

Extended by:

Protobuf::MessageExts::ClassMethods

Includes:

Protobuf::MessageExts

Defined in:

proto_docs/google/cloud/aiplatform/v1/prediction_service.rb

Overview

Usage metadata about response(s).

Instance Attribute Summary

• #candidates_token_count ⇒ ::Integer

  Number of tokens in the response(s).

• #prompt_token_count ⇒ ::Integer

  Number of tokens in the request.

• #total_token_count ⇒ ::Integer

  Total token count for prompt and response candidates.

Instance Attribute Details

#candidates_token_count ⇒ ::Integer

Returns Number of tokens in the response(s).

Returns:

• (::Integer) —

  Number of tokens in the response(s).

# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 609

class UsageMetadata
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#prompt_token_count ⇒ ::Integer

Returns Number of tokens in the request. When cached_content is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.

Returns:

• (::Integer) —

  Number of tokens in the request. When cached_content is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.

# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 609

class UsageMetadata
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#total_token_count ⇒ ::Integer

Returns Total token count for prompt and response candidates.

Returns:

• (::Integer) —

  Total token count for prompt and response candidates.

# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 609

class UsageMetadata
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end