Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class UsageMetadata.
Usage metadata about response(s).
Generated from protobuf message google.cloud.aiplatform.v1.GenerateContentResponse.UsageMetadata
Namespace
Google \ Cloud \ AIPlatform \ V1 \ GenerateContentResponseMethods
__construct
Constructor.
Parameters | |
---|---|
Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ prompt_token_count |
int
Number of tokens in the request. When |
↳ candidates_token_count |
int
Number of tokens in the response(s). |
↳ total_token_count |
int
|
getPromptTokenCount
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 | |
---|---|
Type | Description |
int |
setPromptTokenCount
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.
Parameter | |
---|---|
Name | Description |
var |
int
|
Returns | |
---|---|
Type | Description |
$this |
getCandidatesTokenCount
Number of tokens in the response(s).
Returns | |
---|---|
Type | Description |
int |
setCandidatesTokenCount
Number of tokens in the response(s).
Parameter | |
---|---|
Name | Description |
var |
int
|
Returns | |
---|---|
Type | Description |
$this |
getTotalTokenCount
Generated from protobuf field int32 total_token_count = 3;
Returns | |
---|---|
Type | Description |
int |
setTotalTokenCount
Generated from protobuf field int32 total_token_count = 3;
Parameter | |
---|---|
Name | Description |
var |
int
|
Returns | |
---|---|
Type | Description |
$this |