Struct openai_flows::completion::CompletionRequest

pub struct CompletionRequest {
    pub model: String,
    pub prompt: String,
    pub suffix: Option<String>,
    pub n: u8,
    pub best_of: u8,
    pub max_tokens: u16,
    pub temperature: f32,
    pub top_p: f32,
    pub logprobs: Option<u8>,
    pub presence_penalty: f32,
    pub frequency_penalty: f32,
}

Request struct for the completion.

The default model is “text-davinci-003”.

For more detail about parameters, please refer to OpenAI docs

Fields

model: String

The ID or name of the model to use for completion.

prompt: String

The text to be used as the prompt for completion.

suffix: Option<String>

An optional suffix to append to the prompt before completion.

n: u8

The number of completions to generate.

best_of: u8

The number of completions to consider and return the best from.

max_tokens: u16

The maximum number of tokens in the generated completions.

temperature: f32

Controls the randomness of the generated completions.

top_p: f32

Nucleus sampling: controls the diversity of the generated completions.

logprobs: Option<u8>

Whether to include log probabilities for each token in the completions.

presence_penalty: f32

Penalty to discourage the model from generating repetitive completions.

frequency_penalty: f32

Penalty to discourage the model from using low-frequency words in completions.

Trait Implementations

impl Debug for CompletionRequest

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

Formats the value using the given formatter.

impl Default for CompletionRequest

fn default() -> CompletionRequest

Returns the “default value” for a type.

impl Serialize for CompletionRequest

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.