Struct TaskChat

pub struct TaskChat<'a> {
    pub messages: Vec<Message<'a>>,
    pub maximum_tokens: Option<u32>,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
}

Fields

messages: Vec<Message<'a>>

The list of messages comprising the conversation so far.

maximum_tokens: Option<u32>

The maximum number of tokens to be generated. Completion will terminate after the maximum number of tokens is reached. Increase this value to allow for longer outputs. A text is split into tokens. Usually there are more tokens than words. The total number of tokens of prompt and maximum_tokens depends on the model. If maximum tokens is set to None, no outside limit is opposed on the number of maximum tokens. The model will generate tokens until it generates one of the specified stop_sequences or it reaches its technical limit, which usually is its context window.

temperature: Option<f64>

A temperature encourages the model to produce less probable outputs (“be more creative”). Values are expected to be between 0 and 1. Try high values for a more random (“creative”) response.

top_p: Option<f64>

Introduces random sampling for generated tokens by randomly selecting the next token from the smallest possible set of tokens whose cumulative probability exceeds the probability top_p. Set to 0 to get the same behaviour as None.

Implementations

impl<'a> TaskChat<'a>

pub fn with_message(message: Message<'a>) -> Self

Creates a new TaskChat containing one message with the given role and content. All optional TaskChat attributes are left unset.

pub fn with_messages(messages: Vec<Message<'a>>) -> Self

Creates a new TaskChat containing the given messages. All optional TaskChat attributes are left unset.

pub fn push_message(self, message: Message<'a>) -> Self

Pushes a new Message to this TaskChat.

pub fn with_maximum_tokens(self, maximum_tokens: u32) -> Self

Sets the maximum token attribute of this TaskChat.

pub fn with_temperature(self, temperature: f64) -> Self

Sets the temperature attribute of this TaskChat.

pub fn with_top_p(self, top_p: f64) -> Self

Sets the top_p attribute of this TaskChat.

Trait Implementations

impl<'a> StreamTask for TaskChat<'a>

type Output = ChatStreamChunk

Output returned by crate::Client::output_of

type ResponseBody = ChatEvent

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(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.

impl<'a> Task for TaskChat<'a>

type Output = ChatOutput

Output returned by crate::Client::output_of

type ResponseBody = ResponseChat

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.