Struct TaskChat

pub struct TaskChat<'a> {
    pub messages: Vec<Message<'a>>,
    pub stopping: Stopping<'a>,
    pub sampling: ChatSampling,
    pub logprobs: Logprobs,
}

Fields

messages: Vec<Message<'a>>

The list of messages comprising the conversation so far.

stopping: Stopping<'a>

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

sampling: ChatSampling

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

logprobs: Logprobs

Use this to control the logarithmic probabilities you want to have returned. This is useful to figure out how likely it had been that this specific token had been sampled.

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_logprobs(self, logprobs: Logprobs) -> Self

Sets the logprobs attribute of this TaskChat.

Trait Implementations

impl StreamTask for TaskChat<'_>

type Output = ChatEvent

Output returned by crate::Client::output_of

type ResponseBody = StreamChatResponse

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) -> Option<Self::Output>

Parses the response of the server into higher level structs for the user. None implies the output should be skipped.

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 Task for TaskChat<'_>

type Output = ChatOutput

Output returned by crate::Client::output_of

type ResponseBody = ChatResponse

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.