Some or all of the information on this page might not apply to Cloud de Confiance by S3NS. See Differences from Google Cloud for more details.

Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::GenerateContentResponse::UsageMetadata (v1.38.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::GenerateContentResponse::UsageMetadata.

Usage metadata about response(s).

Inherits

Object

Extended By

Google::Protobuf::MessageExts::ClassMethods

Includes

Google::Protobuf::MessageExts

Methods

#cache_tokens_details

def cache_tokens_details() -> ::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>

Returns

(::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>) — Output only. List of modalities of the cached content in the request input.

#cached_content_token_count

def cached_content_token_count() -> ::Integer

Returns

(::Integer) — Output only. Number of tokens in the cached part in the input (the cached content).

#candidates_token_count

def candidates_token_count() -> ::Integer

Returns

(::Integer) — Number of tokens in the response(s).

#candidates_token_count=

def candidates_token_count=(value) -> ::Integer

Parameter

value (::Integer) — Number of tokens in the response(s).

Returns

(::Integer) — Number of tokens in the response(s).

#candidates_tokens_details

def candidates_tokens_details() -> ::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>

Returns

(::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>) — Output only. List of modalities that were returned in the response.

#prompt_token_count

def prompt_token_count() -> ::Integer

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.

#prompt_token_count=

def prompt_token_count=(value) -> ::Integer

Parameter

value (::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.

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.

#prompt_tokens_details

def prompt_tokens_details() -> ::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>

Returns

(::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>) — Output only. List of modalities that were processed in the request input.

#thoughts_token_count

def thoughts_token_count() -> ::Integer

Returns

(::Integer) — Output only. Number of tokens present in thoughts output.

#tool_use_prompt_tokens_details

def tool_use_prompt_tokens_details() -> ::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>

Returns

(::Array<::Google::Cloud::AIPlatform::V1::ModalityTokenCount>) — Output only. A detailed breakdown by modality of the token counts from the results of tool executions, which are provided back to the model as input.

#total_token_count

def total_token_count() -> ::Integer

Returns

(::Integer) — Total token count for prompt and response candidates.

#total_token_count=

def total_token_count=(value) -> ::Integer

Parameter

value (::Integer) — Total token count for prompt and response candidates.

Returns

(::Integer) — Total token count for prompt and response candidates.

#traffic_type

def traffic_type() -> ::Google::Cloud::AIPlatform::V1::GenerateContentResponse::UsageMetadata::TrafficType

Returns

(::Google::Cloud::AIPlatform::V1::GenerateContentResponse::UsageMetadata::TrafficType) — Output only. The traffic type for this request.