- 1.18.0 (latest)
- 1.17.0
- 1.16.0
- 1.15.0
- 1.14.0
- 1.13.1
- 1.12.0
- 1.11.0
- 1.10.0
- 1.9.0
- 1.8.0
- 1.7.0
- 1.6.0
- 1.5.0
- 1.4.0
- 1.3.0
- 1.2.0
- 1.1.0
- 1.0.0
- 0.39.0
- 0.38.0
- 0.37.1
- 0.32.0
- 0.31.0
- 0.30.0
- 0.29.0
- 0.28.0
- 0.27.0
- 0.26.2
- 0.25.0
- 0.24.0
- 0.23.0
- 0.22.0
- 0.21.0
- 0.20.0
- 0.19.0
- 0.18.0
- 0.17.0
- 0.16.0
- 0.15.0
- 0.13.0
- 0.12.0
- 0.11.1
- 0.10.0
Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class Candidate.
A response candidate generated from the model.
Generated from protobuf message google.cloud.aiplatform.v1.Candidate
Namespace
Google \ Cloud \ AIPlatform \ V1Methods
__construct
Constructor.
Parameters | |
---|---|
Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ index |
int
Output only. Index of the candidate. |
↳ content |
Google\Cloud\AIPlatform\V1\Content
Output only. Content parts of the candidate. |
↳ score |
float
Output only. Confidence score of the candidate. |
↳ avg_logprobs |
float
Output only. Average log probability score of the candidate. |
↳ logprobs_result |
Google\Cloud\AIPlatform\V1\LogprobsResult
Output only. Log-likelihood scores for the response tokens and top tokens |
↳ finish_reason |
int
Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens. |
↳ safety_ratings |
array<Google\Cloud\AIPlatform\V1\SafetyRating>
Output only. List of ratings for the safety of a response candidate. There is at most one rating per category. |
↳ finish_message |
string
Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when |
↳ citation_metadata |
Google\Cloud\AIPlatform\V1\CitationMetadata
Output only. Source attribution of the generated content. |
↳ grounding_metadata |
Google\Cloud\AIPlatform\V1\GroundingMetadata
Output only. Metadata specifies sources used to ground generated content. |
getIndex
Output only. Index of the candidate.
Returns | |
---|---|
Type | Description |
int |
setIndex
Output only. Index of the candidate.
Parameter | |
---|---|
Name | Description |
var |
int
|
Returns | |
---|---|
Type | Description |
$this |
getContent
Output only. Content parts of the candidate.
Returns | |
---|---|
Type | Description |
Google\Cloud\AIPlatform\V1\Content|null |
hasContent
clearContent
setContent
Output only. Content parts of the candidate.
Parameter | |
---|---|
Name | Description |
var |
Google\Cloud\AIPlatform\V1\Content
|
Returns | |
---|---|
Type | Description |
$this |
getScore
Output only. Confidence score of the candidate.
Returns | |
---|---|
Type | Description |
float |
setScore
Output only. Confidence score of the candidate.
Parameter | |
---|---|
Name | Description |
var |
float
|
Returns | |
---|---|
Type | Description |
$this |
getAvgLogprobs
Output only. Average log probability score of the candidate.
Returns | |
---|---|
Type | Description |
float |
setAvgLogprobs
Output only. Average log probability score of the candidate.
Parameter | |
---|---|
Name | Description |
var |
float
|
Returns | |
---|---|
Type | Description |
$this |
getLogprobsResult
Output only. Log-likelihood scores for the response tokens and top tokens
Returns | |
---|---|
Type | Description |
Google\Cloud\AIPlatform\V1\LogprobsResult|null |
hasLogprobsResult
clearLogprobsResult
setLogprobsResult
Output only. Log-likelihood scores for the response tokens and top tokens
Parameter | |
---|---|
Name | Description |
var |
Google\Cloud\AIPlatform\V1\LogprobsResult
|
Returns | |
---|---|
Type | Description |
$this |
getFinishReason
Output only. The reason why the model stopped generating tokens.
If empty, the model has not stopped generating the tokens.
Returns | |
---|---|
Type | Description |
int |
setFinishReason
Output only. The reason why the model stopped generating tokens.
If empty, the model has not stopped generating the tokens.
Parameter | |
---|---|
Name | Description |
var |
int
|
Returns | |
---|---|
Type | Description |
$this |
getSafetyRatings
Output only. List of ratings for the safety of a response candidate.
There is at most one rating per category.
Returns | |
---|---|
Type | Description |
Google\Protobuf\Internal\RepeatedField |
setSafetyRatings
Output only. List of ratings for the safety of a response candidate.
There is at most one rating per category.
Parameter | |
---|---|
Name | Description |
var |
array<Google\Cloud\AIPlatform\V1\SafetyRating>
|
Returns | |
---|---|
Type | Description |
$this |
getFinishMessage
Output only. Describes the reason the mode stopped generating tokens in
more detail. This is only filled when finish_reason
is set.
Returns | |
---|---|
Type | Description |
string |
hasFinishMessage
clearFinishMessage
setFinishMessage
Output only. Describes the reason the mode stopped generating tokens in
more detail. This is only filled when finish_reason
is set.
Parameter | |
---|---|
Name | Description |
var |
string
|
Returns | |
---|---|
Type | Description |
$this |
getCitationMetadata
Output only. Source attribution of the generated content.
Returns | |
---|---|
Type | Description |
Google\Cloud\AIPlatform\V1\CitationMetadata|null |
hasCitationMetadata
clearCitationMetadata
setCitationMetadata
Output only. Source attribution of the generated content.
Parameter | |
---|---|
Name | Description |
var |
Google\Cloud\AIPlatform\V1\CitationMetadata
|
Returns | |
---|---|
Type | Description |
$this |
getGroundingMetadata
Output only. Metadata specifies sources used to ground generated content.
Returns | |
---|---|
Type | Description |
Google\Cloud\AIPlatform\V1\GroundingMetadata|null |
hasGroundingMetadata
clearGroundingMetadata
setGroundingMetadata
Output only. Metadata specifies sources used to ground generated content.
Parameter | |
---|---|
Name | Description |
var |
Google\Cloud\AIPlatform\V1\GroundingMetadata
|
Returns | |
---|---|
Type | Description |
$this |