Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class FinishReason.
The reason why the model stopped generating tokens.
If empty, the model has not stopped generating the tokens.
Protobuf type google.cloud.aiplatform.v1.Candidate.FinishReason
Namespace
Google \ Cloud \ AIPlatform \ V1 \ CandidateMethods
static::name
Parameter | |
---|---|
Name | Description |
value |
mixed
|
static::value
Parameter | |
---|---|
Name | Description |
name |
mixed
|
Constants
FINISH_REASON_UNSPECIFIED
Value: 0
The finish reason is unspecified.
Generated from protobuf enum FINISH_REASON_UNSPECIFIED = 0;
STOP
Value: 1
Natural stop point of the model or provided stop sequence.
Generated from protobuf enum STOP = 1;
MAX_TOKENS
Value: 2
The maximum number of tokens as specified in the request was reached.
Generated from protobuf enum MAX_TOKENS = 2;
SAFETY
Value: 3
The token generation was stopped as the response was flagged for safety reasons. NOTE: When streaming the Candidate.content will be empty if content filters blocked the output.
Generated from protobuf enum SAFETY = 3;
RECITATION
Value: 4
The token generation was stopped as the response was flagged for unauthorized citations.
Generated from protobuf enum RECITATION = 4;
OTHER
Value: 5
All other reasons that stopped the token generation
Generated from protobuf enum OTHER = 5;