google.generativeai.protos.Candidate
A response candidate generated from the model.
Attributes |
|---|
|
`index`
|
`int`
Output only. Index of the candidate in the
list of response candidates.
|
|
`content`
|
`google.ai.generativelanguage.Content`
Output only. Generated content returned from
the model.
|
|
`finish_reason`
|
`google.ai.generativelanguage.Candidate.FinishReason`
Optional. Output only. The reason why the
model stopped generating tokens.
If empty, the model has not stopped generating
tokens.
|
|
`safety_ratings`
|
`MutableSequence[google.ai.generativelanguage.SafetyRating]`
List of ratings for the safety of a response
candidate.
There is at most one rating per category.
|
|
`citation_metadata`
|
`google.ai.generativelanguage.CitationMetadata`
Output only. Citation information for model-generated
candidate.
This field may be populated with recitation information for
any text included in the ``content``. These are passages
that are "recited" from copyrighted material in the
foundational LLM's training data.
|
|
`token_count`
|
`int`
Output only. Token count for this candidate.
|
|
`grounding_attributions`
|
`MutableSequence[google.ai.generativelanguage.GroundingAttribution]`
Output only. Attribution information for sources that
contributed to a grounded answer.
This field is populated for ``GenerateAnswer`` calls.
|
|
`grounding_metadata`
|
`google.ai.generativelanguage.GroundingMetadata`
Output only. Grounding metadata for the candidate.
This field is populated for ``GenerateContent`` calls.
|
|
`avg_logprobs`
|
`float`
Output only.
|
|
`logprobs_result`
|
`google.ai.generativelanguage.LogprobsResult`
Output only. Log-likelihood scores for the
response tokens and top tokens
|
Child Classes
class FinishReason
View source on GitHub