Struct AsyncSession 

pub struct AsyncSession<'s> { /* private fields */ }

Available on crate feature async only.

Async wrapper around crate::LanguageModelSession.

Borrows the session for its lifetime; the session itself must outlive all in-flight futures.

Examples

use foundation_models::{LanguageModelSession, SystemLanguageModel};
use foundation_models::async_api::AsyncSession;

if !SystemLanguageModel::is_available() { return Ok(()); }
pollster::block_on(async {
    let session = LanguageModelSession::new();
    let reply = AsyncSession::new(&session).respond("Hi!")?.await?;
    println!("{}", reply.content);
    Ok::<(), Box<dyn std::error::Error>>(())
})

Implementations

impl<'s> AsyncSession<'s>

pub fn new(session: &'s LanguageModelSession) -> Self

Wrap a crate::LanguageModelSession for async use.

pub fn respond(&self, prompt: impl ToPrompt) -> Result<RespondFuture, FMError>

Async version of LanguageModelSession.respond(to:).

Corresponds to the Swift async throws method LanguageModelSession.respond(to:).

Errors

Returns an FMError if the model is unavailable or generation fails.

pub fn respond_with_options( &self, prompt: impl ToPrompt, options: GenerationOptions, ) -> Result<RespondFuture, FMError>

Async version of LanguageModelSession.respond(to:) with GenerationOptions.

Errors

Returns an FMError if the model is unavailable or generation fails.

pub fn respond_generating( &self, prompt: impl ToPrompt, schema: &GenerationSchema, include_schema_in_prompt: bool, options: GenerationOptions, ) -> Result<RespondGeneratingFuture, FMError>

Async version of LanguageModelSession.respond(to:generating:).

Generates a structured GeneratedContent response according to schema. Corresponds to the Swift async throws method LanguageModelSession.respond(to:generating:).

Errors

Returns an FMError if the model is unavailable or generation fails.

Trait Implementations

impl Debug for AsyncSession<'_>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.