Struct CreateEvalCompletionsRunDataSourceSamplingParams

pub struct CreateEvalCompletionsRunDataSourceSamplingParams {
    pub temperature: Option<f64>,
    pub max_completion_tokens: Option<u64>,
    pub top_p: Option<f64>,
    pub seed: Option<u64>,
    pub response_format: Option<CreateEvalCompletionsRunDataSourceSamplingParamsResponseFormat>,
    pub tools: Option<Vec<ChatCompletionTool>>,
}

Fields

temperature: Option<f64>

A higher temperature increases randomness in the outputs.

max_completion_tokens: Option<u64>

The maximum number of tokens in the generated output.

top_p: Option<f64>

An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

seed: Option<u64>

A seed value to initialize the randomness, during sampling.

response_format: Option<CreateEvalCompletionsRunDataSourceSamplingParamsResponseFormat>

An object specifying the format that the model must output.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

tools: Option<Vec<ChatCompletionTool>>

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

Implementations

impl CreateEvalCompletionsRunDataSourceSamplingParams

pub fn builder() -> CreateEvalCompletionsRunDataSourceSamplingParamsBuilder<((), (), (), (), (), ())>

Create a builder for building CreateEvalCompletionsRunDataSourceSamplingParams. On the builder, call .temperature(...)(optional), .max_completion_tokens(...)(optional), .top_p(...)(optional), .seed(...)(optional), .response_format(...)(optional), .tools(...)(optional) to set the values of the fields. Finally, call .build() to create the instance of CreateEvalCompletionsRunDataSourceSamplingParams.

Trait Implementations

impl Clone for CreateEvalCompletionsRunDataSourceSamplingParams

fn clone(&self) -> CreateEvalCompletionsRunDataSourceSamplingParams

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CreateEvalCompletionsRunDataSourceSamplingParams

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for CreateEvalCompletionsRunDataSourceSamplingParams

fn default() -> CreateEvalCompletionsRunDataSourceSamplingParams

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for CreateEvalCompletionsRunDataSourceSamplingParams

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for CreateEvalCompletionsRunDataSourceSamplingParams

fn eq(&self, other: &CreateEvalCompletionsRunDataSourceSamplingParams) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for CreateEvalCompletionsRunDataSourceSamplingParams

fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for CreateEvalCompletionsRunDataSourceSamplingParams