pub struct Edit {
pub model: Model,
pub input: Option<String>,
pub instruction: String,
pub temperature: Option<f32>,
pub top_p: Option<f32>,
pub n: Option<u32>,
}
Expand description
Given a prompt and an instruction, the model will return an edited version of the prompt.
Fields§
§model: Model
§input: Option<String>
§instruction: String
§temperature: Option<f32>
§top_p: Option<f32>
§n: Option<u32>
Implementations§
Source§impl Edit
impl Edit
Sourcepub fn model(self, model: Model) -> Self
pub fn model(self, model: Model) -> Self
ID of the model to use. You can use the text-davinci-edit-001
or
code-davinci-edit-001
model with this endpoint.
Sourcepub fn input(self, content: &str) -> Self
pub fn input(self, content: &str) -> Self
The input text to use as a starting point for the edit.
Sourcepub fn instruction(self, content: &str) -> Self
pub fn instruction(self, content: &str) -> Self
The instruction that tells the model how to edit the prompt.
Sourcepub fn temperature(self, temperature: f32) -> Self
pub fn temperature(self, temperature: f32) -> Self
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p
but not both.
Sourcepub fn top_p(self, top_p: f32) -> Self
pub fn top_p(self, top_p: f32) -> Self
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.