Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class UsageMetadata.
Usage metadata about the content generation request and response.
This message provides a detailed breakdown of token usage and other relevant metrics.
Generated from protobuf message google.cloud.aiplatform.v1.UsageMetadata
Namespace
Google \ Cloud \ AIPlatform \ V1Methods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ prompt_token_count |
int
The total number of tokens in the prompt. This includes any text, images, or other media provided in the request. When |
↳ candidates_token_count |
int
The total number of tokens in the generated candidates. |
↳ total_token_count |
int
The total number of tokens for the entire request. This is the sum of |
↳ tool_use_prompt_token_count |
int
Output only. The number of tokens in the results from tool executions, which are provided back to the model as input, if applicable. |
↳ thoughts_token_count |
int
Output only. The number of tokens that were part of the model's generated "thoughts" output, if applicable. |
↳ cached_content_token_count |
int
Output only. The number of tokens in the cached content that was used for this request. |
↳ prompt_tokens_details |
array<ModalityTokenCount>
Output only. A detailed breakdown of the token count for each modality in the prompt. |
↳ cache_tokens_details |
array<ModalityTokenCount>
Output only. A detailed breakdown of the token count for each modality in the cached content. |
↳ candidates_tokens_details |
array<ModalityTokenCount>
Output only. A detailed breakdown of the token count for each modality in the generated candidates. |
↳ tool_use_prompt_tokens_details |
array<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. |
↳ traffic_type |
int
Output only. The traffic type for this request. |
getPromptTokenCount
The total number of tokens in the prompt. This includes any text, images,
or other media provided in the request. When cached_content is set,
this also includes the number of tokens in the cached content.
| Returns | |
|---|---|
| Type | Description |
int |
|
setPromptTokenCount
The total number of tokens in the prompt. This includes any text, images,
or other media provided in the request. When cached_content is set,
this also includes the number of tokens in the cached content.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getCandidatesTokenCount
The total number of tokens in the generated candidates.
| Returns | |
|---|---|
| Type | Description |
int |
|
setCandidatesTokenCount
The total number of tokens in the generated candidates.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getTotalTokenCount
The total number of tokens for the entire request. This is the sum of
prompt_token_count, candidates_token_count,
tool_use_prompt_token_count, and thoughts_token_count.
| Returns | |
|---|---|
| Type | Description |
int |
|
setTotalTokenCount
The total number of tokens for the entire request. This is the sum of
prompt_token_count, candidates_token_count,
tool_use_prompt_token_count, and thoughts_token_count.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getToolUsePromptTokenCount
Output only. The number of tokens in the results from tool executions, which are provided back to the model as input, if applicable.
| Returns | |
|---|---|
| Type | Description |
int |
|
setToolUsePromptTokenCount
Output only. The number of tokens in the results from tool executions, which are provided back to the model as input, if applicable.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getThoughtsTokenCount
Output only. The number of tokens that were part of the model's generated "thoughts" output, if applicable.
| Returns | |
|---|---|
| Type | Description |
int |
|
setThoughtsTokenCount
Output only. The number of tokens that were part of the model's generated "thoughts" output, if applicable.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getCachedContentTokenCount
Output only. The number of tokens in the cached content that was used for this request.
| Returns | |
|---|---|
| Type | Description |
int |
|
setCachedContentTokenCount
Output only. The number of tokens in the cached content that was used for this request.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getPromptTokensDetails
Output only. A detailed breakdown of the token count for each modality in the prompt.
| Returns | |
|---|---|
| Type | Description |
Google\Protobuf\RepeatedField<ModalityTokenCount> |
|
setPromptTokensDetails
Output only. A detailed breakdown of the token count for each modality in the prompt.
| Parameter | |
|---|---|
| Name | Description |
var |
array<ModalityTokenCount>
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getCacheTokensDetails
Output only. A detailed breakdown of the token count for each modality in the cached content.
| Returns | |
|---|---|
| Type | Description |
Google\Protobuf\RepeatedField<ModalityTokenCount> |
|
setCacheTokensDetails
Output only. A detailed breakdown of the token count for each modality in the cached content.
| Parameter | |
|---|---|
| Name | Description |
var |
array<ModalityTokenCount>
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getCandidatesTokensDetails
Output only. A detailed breakdown of the token count for each modality in the generated candidates.
| Returns | |
|---|---|
| Type | Description |
Google\Protobuf\RepeatedField<ModalityTokenCount> |
|
setCandidatesTokensDetails
Output only. A detailed breakdown of the token count for each modality in the generated candidates.
| Parameter | |
|---|---|
| Name | Description |
var |
array<ModalityTokenCount>
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getToolUsePromptTokensDetails
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.
| Returns | |
|---|---|
| Type | Description |
Google\Protobuf\RepeatedField<ModalityTokenCount> |
|
setToolUsePromptTokensDetails
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.
| Parameter | |
|---|---|
| Name | Description |
var |
array<ModalityTokenCount>
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getTrafficType
Output only. The traffic type for this request.
| Returns | |
|---|---|
| Type | Description |
int |
Enum of type TrafficType. |
setTrafficType
Output only. The traffic type for this request.
| Parameter | |
|---|---|
| Name | Description |
var |
int
Enum of type TrafficType. |
| Returns | |
|---|---|
| Type | Description |
$this |
|