Struct aleph_alpha_client::TaskCompletion

pub struct TaskCompletion<'a> {
    pub prompt: Prompt<'a>,
    pub stopping: Stopping<'a>,
    pub sampling: Sampling<'a>,
}

Completes a prompt. E.g. continues a text.

Fields

prompt: Prompt<'a>

The prompt (usually text) to be completed. Unconditional completion can be started with an empty string. The prompt may contain a zero shot or few shot task.

stopping: Stopping<'a>

Controls in which circumstances the model will stop generating new tokens.

sampling: Sampling<'a>

Sampling controls how the tokens (“words”) are selected for the completion.

Implementations

impl<'a> TaskCompletion<'a>

pub fn from_text(text: &'a str, maximum_tokens: u32) -> Self

Convinience constructor leaving most setting to default, just completing a given text and taking the maximum anticipated length of the completion.

Trait Implementations

impl Task for TaskCompletion<'_>

type Output = CompletionOutput

Output returned by crate::Client::output_of

type ResponseBody = ResponseCompletion

Expected answer of the Aleph Alpha API

fn build_request( &self, client: &Client, base: &str, model: &str ) -> RequestBuilder

Prepare the request for the Aleph Alpha API. Authentication headers can be assumed to be already set.

fn body_to_output(&self, response: Self::ResponseBody) -> Self::Output

Parses the response of the server into higher level structs for the user.

fn with_model<'a>(&'a self, model: &'a str) -> MethodJob<'a, Self>where Self: Sized,

Turn your task into Job by annotating it with a model name.