Struct StreamingPromptRequest 

pub struct StreamingPromptRequest<M, P>
where
    M: CompletionModel,
    P: PromptHook<M> + 'static,
{ /* 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 expect to continuously call tools, you will want to ensure you use the .multi_turn() argument to add more turns as by default, it is 0 (meaning only 1 tool round-trip). Otherwise, attempting to await (which will send the prompt request) can potentially return crate::completion::request::PromptError::MaxTurnsError if the agent decides to call tools back to back.

Implementations

impl<M, P> StreamingPromptRequest<M, P>

where M: CompletionModel + 'static, <M as CompletionModel>::StreamingResponse: WasmCompatSend + GetTokenUsage, P: PromptHook<M>,

pub fn new( agent: Arc<Agent<M>>, prompt: impl Into<Message>, ) -> StreamingPromptRequest<M, ()>

Create a new StreamingPromptRequest with the given prompt and model. Note: This creates a request without an agent hook. Use from_agent to include the agent’s hook.

pub fn from_agent<P2>( agent: &Agent<M, P2>, prompt: impl Into<Message>, ) -> StreamingPromptRequest<M, P2>

where P2: PromptHook<M>,

Create a new StreamingPromptRequest from an agent, cloning the agent’s data and default hook.

pub fn multi_turn(self, turns: usize) -> Self

Set the maximum Turns 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::MaxTurnsError.

pub fn with_history(self, history: Vec<Message>) -> Self

Add chat history to the prompt request.

When history is provided, the final FinalResponse will include the updated chat history (original messages + new user prompt + assistant response).

let mut stream = agent
    .stream_prompt("Hello")
    .with_history(vec![])
    .await;
// ... consume stream ...
// Access updated history from FinalResponse::history()

pub fn with_hook<P2>(self, hook: P2) -> StreamingPromptRequest<M, P2>

where P2: PromptHook<M>,

Attach a per-request hook for tool call events. This overrides any default hook set on the agent.

Trait Implementations

impl<M, P> IntoFuture for StreamingPromptRequest<M, P>

where M: CompletionModel + 'static, <M as CompletionModel>::StreamingResponse: WasmCompatSend, P: PromptHook<M> + 'static,

type Output = Pin<Box<dyn Stream<Item = Result<MultiTurnStreamItem<<M as CompletionModel>::StreamingResponse>, StreamingError>> + Send>>

The output that the future will produce on completion.

type IntoFuture = Pin<Box<dyn Future<Output = <StreamingPromptRequest<M, P> as IntoFuture>::Output> + Send>>

Which kind of future are we turning this into?

fn into_future(self) -> Self::IntoFuture

Creates a future from a value.