GenerateContentResponse.md

google.generativeai.protos.GenerateContentResponse

View source on GitHub

Response from the model supporting multiple candidate responses.

Safety ratings and content filtering are reported for both prompt in GenerateContentResponse.prompt_feedback and for each candidate in finish_reason and in safety_ratings. The API:

• Returns either all requested candidates or none of them
• Returns no candidates at all only if there was something wrong with the prompt (check prompt_feedback)
• Reports feedback on each candidate in finish_reason and safety_ratings.

Attributes
candidates	MutableSequence[google.ai.generativelanguage.Candidate] Candidate responses from the model.
prompt_feedback	google.ai.generativelanguage.GenerateContentResponse.PromptFeedback Returns the prompt's feedback related to the content filters.
usage_metadata	google.ai.generativelanguage.GenerateContentResponse.UsageMetadata Output only. Metadata on the generation requests' token usage.

Child Classes

class PromptFeedback

class UsageMetadata