Struct Completion

pub struct Completion<'a> {

    pub prompt: Option<Cow<'a, str>>,
    pub suffix: Option<Cow<'a, str>>,
    pub max_tokens: u32,
    pub temperature: f32,
    pub top_p: f32,
    pub n: u32,
    pub stream: bool,
    pub logprobs: Option<u32>,
    pub echo: bool,
    pub stop: Option<Vec<Cow<'a, str>>>,
    pub presence_penalty: f32,
    pub frequency_penalty: f32,
    pub best_of: u32,
    pub logit_bias: Option<HashMap<Cow<'a, str>, i32>>,
    pub user: Option<Cow<'a, str>>,
}

Given a prompt, the response will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

Fields

prompt: Option<Cow<'a, str>>

The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.

suffix: Option<Cow<'a, str>>

The suffix that comes after a completion of inserted text.

max_tokens: u32

The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model’s context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).

temperature: f32

What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend altering this or top_p but not both.

top_p: f32

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

n: u32

How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

stream: bool

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.

logprobs: Option<u32>

Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5. If you need more than this, please contact support@openai.com and describe your use case.

echo: bool

Echo back the prompt in addition to the completion

stop: Option<Vec<Cow<'a, str>>>

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

presence_penalty: f32

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

frequency_penalty: f32

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

best_of: u32

Generates best_of completions server-side and returns the “best” (the one with the lowest log probability per token). Results cannot be streamed. When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

logit_bias: Option<HashMap<Cow<'a, str>, i32>>

Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

user: Option<Cow<'a, str>>

A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse.

Trait Implementations

impl<'a> Clone for Completion<'a>

fn clone(&self) -> Completion<'a>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<'a> Debug for Completion<'a>

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

Formats the value using the given formatter.

impl Default for Completion<'_>

fn default() -> Self

Returns the “default value” for a type.

impl<'a> Serialize for Completion<'a>

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

where __S: Serializer,

Serialize this value into the given Serde serializer.