Class GeminiGenerationConfiguration

Namespace

Uralstech.UGemini.Models.Generation

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

public class GeminiGenerationConfiguration

Inheritance

object

GeminiGenerationConfiguration

Extension Methods

GeminiFieldMaskGenerator.GetFieldMask(object)

Fields

CandidateCount

Number of generated responses to return.

public int CandidateCount

Field Value

int

Remarks

Currently, this value can only be set to 1. If unset, this will default to 1.

EnableEnhancedCivicAnswers

Enables enhanced civic answers. It may not be available for all models.

public bool? EnableEnhancedCivicAnswers

Field Value

bool?

FrequencyPenalty

Frequency penalty applied to the next token's logprobs, multiplied by the number of times each token has been seen in the response so far.

public float FrequencyPenalty

Field Value

float

Remarks

A positive penalty will discourage the use of tokens that have already been used, proportional to the number
of times the token has been used: The more a token is used, the more dificult it is for the model to use that
token again increasing the vocabulary of responses.

Caution: A negative penalty will encourage the model to reuse tokens proportional to the number of times the
token has been used. Small negative values will reduce the vocabulary of a response. Larger negative values
will cause the model to start repeating a common token until it hits the
MaxOutputTokens limit: "...the the the the the...".

Logprobs

Only valid if ResponseLogprobs = true. This sets the number of top logprobs to return at each decoding step in the LogprobsResult.

public int Logprobs

Field Value

int

MaxOutputTokens

The maximum number of tokens to include in a candidate.

public int MaxOutputTokens

Field Value

int

MediaResolution

If specified, the media resolution specified will be used.

public GeminiMediaResolution MediaResolution

Field Value

GeminiMediaResolution

PresencePenalty

Presence penalty applied to the next token's logprobs if the token has already been seen in the response.

public float PresencePenalty

Field Value

float

Remarks

This penalty is binary on/off and not dependant on the number of times the token is used (after the first). Use
FrequencyPenalty for a penalty that increases with each use. A positive penalty will
discourage the use of tokens that have already been used in the response, increasing the vocabulary. A negative
penalty will encourage the use of tokens that have already been used in the response, decreasing the vocabulary.

ResponseLogprobs

If true, export the logprobs results in response.

public bool? ResponseLogprobs

Field Value

bool?

ResponseMimeType

Output response type of the generated candidate text.

public GeminiResponseType ResponseMimeType

Field Value

GeminiResponseType

Remarks

Only available in the beta API.

ResponseModalities

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.

public GeminiModality[] ResponseModalities

Field Value

GeminiModality[]

Remarks

A model may have multiple combinations of supported modalities. If the requested modalities do not match any of the supported combinations, an error will be returned. An empty list is equivalent to requesting only text.

Document and Video are not supported.

ResponseSchema

Output response schema of the generated candidate text when response mime type can have schema.

public GeminiSchema ResponseSchema

Field Value

GeminiSchema

Remarks

If set, a compatible GeminiResponseType must also be set. Compatible types: Json and Enum.

Only available in the beta API.

Seed

Seed used in decoding. If not set, the request uses a randomly generated seed.

public int? Seed

Field Value

int?

SpeechConfig

The speech generation config.

public GeminiSpeechConfig SpeechConfig

Field Value

GeminiSpeechConfig

StopSequences

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.

public string[] StopSequences

Field Value

string[]

Temperature

Controls the randomness of the output. Values can range from 0.0 - 2.0.

public float Temperature

Field Value

float

ThinkingConfig

Config for thinking features. An error will be returned if this field is set for models that don't support thinking.

public GeminiThinkingConfig ThinkingConfig

Field Value

GeminiThinkingConfig

TopK

The maximum number of tokens to consider when sampling.

public int TopK

Field Value

int

Remarks

Models use nucleus sampling or combined Top-k and nucleus sampling. Top-k sampling considers the set of topK most
probable tokens. Models running with nucleus sampling don't allow topK setting.

TopP

The maximum cumulative probability of tokens to consider when sampling.

public float TopP

Field Value

float

Remarks

The model uses combined Top-k and nucleus sampling.

Tokens are sorted based on their assigned probabilities so that only the most likely tokens are considered.
Top-k sampling directly limits the maximum number of tokens to consider, while Nucleus sampling limits
number of tokens based on the cumulative probability.