GenerationConfig class final

Configuration options for model generation and outputs. Not all parameters are configurable for every model.

Constructors

GenerationConfig({int? candidateCount, List<String> stopSequences = const [], int? maxOutputTokens, double? temperature, double? topP, int? topK, int? seed, String responseMimeType = '', Schema? responseSchema, Value? responseJsonSchema, Value? responseJsonSchemaOrdered, double? presencePenalty, double? frequencyPenalty, bool? responseLogprobs, int? logprobs, bool? enableEnhancedCivicAnswers, List<GenerationConfig_Modality> responseModalities = const [], SpeechConfig? speechConfig, ThinkingConfig? thinkingConfig, ImageConfig? imageConfig, GenerationConfig_MediaResolution? mediaResolution})
GenerationConfig.fromJson(Object? j)
factory

Properties

candidateCount → int?
Optional. Number of generated responses to return. If unset, this will default to 1. Please note that this doesn't work for previous generation models (Gemini 1.0 family)
final
enableEnhancedCivicAnswers → bool?
Optional. Enables enhanced civic answers. It may not be available for all models.
final
frequencyPenalty → double?
Optional. Frequency penalty applied to the next token's logprobs, multiplied by the number of times each token has been seen in the respponse so far.
final
hashCode → int
The hash code for this object.
no setterinherited
imageConfig → ImageConfig?
Optional. Config for image generation. An error will be returned if this field is set for models that don't support these config options.
final
logprobs → int?
Optional. Only valid if google.ai.generativelanguage.v1beta.GenerationConfig.response_logprobs. This sets the number of top logprobs to return at each decoding step in the Candidate.logprobs_result. The number must be in the range of 0, 20.
final
maxOutputTokens → int?
Optional. The maximum number of tokens to include in a response candidate.
final
mediaResolution → GenerationConfig_MediaResolution?
Optional. If specified, the media resolution specified will be used.
final
presencePenalty → double?
Optional. Presence penalty applied to the next token's logprobs if the token has already been seen in the response.
final
qualifiedName → String
The fully qualified name of this message, i.e., google.protobuf.Duration or google.rpc.ErrorInfo.
finalinherited
responseJsonSchema → Value?
Optional. Output schema of the generated response. This is an alternative to response_schema that accepts JSON Schema.
final
responseJsonSchemaOrdered → Value?
Optional. An internal detail. Use responseJsonSchema rather than this field.
final
responseLogprobs → bool?
Optional. If true, export the logprobs results in response.
final
responseMimeType → String
Optional. MIME type of the generated candidate text. Supported MIME types are: text/plain: (default) Text output. application/json: JSON response in the response candidates. text/x.enum: ENUM as a string response in the response candidates. Refer to the docs for a list of all supported text MIME types.
final
responseModalities → List<GenerationConfig_Modality>
Optional. The requested modalities of the response. Represents the set of modalities that the model can return, and should be expected in the response. This is an exact match to the modalities of the response.
final
responseSchema → Schema?
Optional. Output schema of the generated candidate text. Schemas must be a subset of the OpenAPI schema and can be objects, primitives or arrays.
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
seed → int?
Optional. Seed used in decoding. If not set, the request uses a randomly generated seed.
final
speechConfig → SpeechConfig?
Optional. The speech generation config.
final
stopSequences → List<String>
Optional. The set of character sequences (up to 5) that will stop output generation. If specified, the API will stop at the first appearance of a stop_sequence. The stop sequence will not be included as part of the response.
final
temperature → double?
Optional. Controls the randomness of the output.
final
thinkingConfig → ThinkingConfig?
Optional. Config for thinking features. An error will be returned if this field is set for models that don't support thinking.
final
topK → int?
Optional. The maximum number of tokens to consider when sampling.
final
topP → double?
Optional. The maximum cumulative probability of tokens to consider when sampling.
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