Vertex AI V1 API - Module Google::Cloud::AIPlatform::V1::Candidate::FinishReason (v0.44.0)

Reference documentation and code samples for the Vertex AI V1 API module Google::Cloud::AIPlatform::V1::Candidate::FinishReason.

The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.

Constants

FINISH_REASON_UNSPECIFIED

value: 0
The finish reason is unspecified.

STOP

value: 1
Natural stop point of the model or provided stop sequence.

MAX_TOKENS

value: 2
The maximum number of tokens as specified in the request was reached.

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.

RECITATION

value: 4
The token generation was stopped as the response was flagged for unauthorized citations.

OTHER

value: 5
All other reasons that stopped the token generation

BLOCKLIST

value: 6
The token generation was stopped as the response was flagged for the terms which are included from the terminology blocklist.

PROHIBITED_CONTENT

value: 7
The token generation was stopped as the response was flagged for the prohibited contents.

SPII

value: 8
The token generation was stopped as the response was flagged for Sensitive Personally Identifiable Information (SPII) contents.

MALFORMED_FUNCTION_CALL

value: 9
The function call generated by the model is invalid.