Class GoogleCloudAiplatformV1beta1GenerationConfig

Generation config.

Inheritance
object
GoogleCloudAiplatformV1beta1GenerationConfig
Implements
Inherited Members
Namespace: Google.Apis.FirebaseML.v2beta.Data
Assembly: Google.Apis.FirebaseML.v2beta.dll
Syntax
public class GoogleCloudAiplatformV1beta1GenerationConfig : IDirectResponseSchema

Properties

AudioTimestamp

Optional. If enabled, audio timestamp will be included in the request to the model.

Declaration
[JsonProperty("audioTimestamp")]
public virtual bool? AudioTimestamp { get; set; }
Property Value
Type Description
bool?

CandidateCount

Optional. Number of candidates to generate.

Declaration
[JsonProperty("candidateCount")]
public virtual int? CandidateCount { get; set; }
Property Value
Type Description
int?

ETag

The ETag of the item.

Declaration
public virtual string ETag { get; set; }
Property Value
Type Description
string

FrequencyPenalty

Optional. Frequency penalties.

Declaration
[JsonProperty("frequencyPenalty")]
public virtual float? FrequencyPenalty { get; set; }
Property Value
Type Description
float?

Logprobs

Optional. Logit probabilities.

Declaration
[JsonProperty("logprobs")]
public virtual int? Logprobs { get; set; }
Property Value
Type Description
int?

MaxOutputTokens

Optional. The maximum number of output tokens to generate per message.

Declaration
[JsonProperty("maxOutputTokens")]
public virtual int? MaxOutputTokens { get; set; }
Property Value
Type Description
int?

PresencePenalty

Optional. Positive penalties.

Declaration
[JsonProperty("presencePenalty")]
public virtual float? PresencePenalty { get; set; }
Property Value
Type Description
float?

ResponseLogprobs

Optional. If true, export the logprobs results in response.

Declaration
[JsonProperty("responseLogprobs")]
public virtual bool? ResponseLogprobs { get; set; }
Property Value
Type Description
bool?

ResponseMimeType

Optional. Output response mimetype of the generated candidate text. Supported mimetype: - text/plain: (default) Text output. - application/json: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.

Declaration
[JsonProperty("responseMimeType")]
public virtual string ResponseMimeType { get; set; }
Property Value
Type Description
string

ResponseSchema

Optional. The Schema object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an OpenAPI 3.0 schema object. If set, a compatible response_mime_type must also be set. Compatible mimetypes: application/json: Schema for JSON response.

Declaration
[JsonProperty("responseSchema")]
public virtual GoogleCloudAiplatformV1beta1Schema ResponseSchema { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1Schema

RoutingConfig

Optional. Routing configuration.

Declaration
[JsonProperty("routingConfig")]
public virtual GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfig RoutingConfig { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfig

Seed

Optional. Seed.

Declaration
[JsonProperty("seed")]
public virtual int? Seed { get; set; }
Property Value
Type Description
int?

StopSequences

Optional. Stop sequences.

Declaration
[JsonProperty("stopSequences")]
public virtual IList<string> StopSequences { get; set; }
Property Value
Type Description
IList<string>

Temperature

Optional. Controls the randomness of predictions.

Declaration
[JsonProperty("temperature")]
public virtual float? Temperature { get; set; }
Property Value
Type Description
float?

TopK

Optional. If specified, top-k sampling will be used.

Declaration
[JsonProperty("topK")]
public virtual float? TopK { get; set; }
Property Value
Type Description
float?

TopP

Optional. If specified, nucleus sampling will be used.

Declaration
[JsonProperty("topP")]
public virtual float? TopP { get; set; }
Property Value
Type Description
float?

Implements