Struct PromptRequest

pub struct PromptRequest<'a, M: CompletionModel> { /* private fields */ }

A builder for creating prompt requests with customizable options. Uses generics to track which options have been set during the build process. If you’re using tools, you will want to ensure you use .multi_turn() to add more turns as by default it is 0 (meaning no tool usage). Otherwise, attempting to await (which will send the prompt request) returns crate::completion::request::PromptError::MaxDepthError.

Implementations

impl<'a, M: CompletionModel> PromptRequest<'a, M>

pub fn new(agent: &'a Agent<M>, prompt: impl Into<Message>) -> Self

Create a new PromptRequest with the given prompt and model

impl<'a, M: CompletionModel> PromptRequest<'a, M>

pub fn multi_turn(self, depth: usize) -> PromptRequest<'a, M>

Set the maximum depth for multi-turn conversations (ie, the maximum number of turns an LLM can have calling tools before writing a text response). If the maximum turn number is exceeded, it will return a crate::completion::request::PromptError::MaxDepthError.

pub fn with_history(self, history: &'a mut Vec<Message>) -> PromptRequest<'a, M>

Add chat history to the prompt request.

Trait Implementations

impl<'a, M: CompletionModel> IntoFuture for PromptRequest<'a, M>

Due to: RFC 2515, we have to use a BoxFuture for the IntoFuture implementation. In the future, we should be able to use impl Future<...> directly via the associated type.

type Output = Result<String, PromptError>

The output that the future will produce on completion.

type IntoFuture = Pin<Box<dyn Future<Output = <PromptRequest<'a, M> as IntoFuture>::Output> + Send + 'a>>

Which kind of future are we turning this into?

fn into_future(self) -> Self::IntoFuture

Creates a future from a value.