GenerateContentResponse class final
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_reasonandsafety_ratings.
Constructors
-
GenerateContentResponse({List<
Candidate> candidates = const [], GenerateContentResponse_PromptFeedback? promptFeedback, GenerateContentResponse_UsageMetadata? usageMetadata, String modelVersion = '', String responseId = ''}) - GenerateContentResponse.fromJson(Object? j)
-
factory
Properties
-
candidates
→ List<
Candidate> -
Candidate responses from the model.
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- modelVersion → String
-
Output only. The model version used to generate the response.
final
- promptFeedback → GenerateContentResponse_PromptFeedback?
-
Returns the prompt's feedback related to the content filters.
final
- qualifiedName → String
-
The fully qualified name of this message, i.e.,
google.protobuf.Durationorgoogle.rpc.ErrorInfo.finalinherited - responseId → String
-
Output only. response_id is used to identify each response.
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- usageMetadata → GenerateContentResponse_UsageMetadata?
-
Output only. Metadata on the generation requests' token usage.
final
Methods
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
toJson(
) → Object -
toString(
) → String -
A string representation of this object.
override
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited
Constants
- fullyQualifiedName → const String