Struct FunctionInvokingChatClient 

pub struct FunctionInvokingChatClient<C: ChatClient> { /* private fields */ }

Wraps a ChatClient to automatically execute local tool calls in a loop, mirroring use_function_invocation.

Implementations

impl<C: ChatClient> FunctionInvokingChatClient<C>

pub fn new(inner: C) -> Self

pub fn with_config(self, config: FunctionInvocationConfig) -> Self

Override the function-invocation configuration.

pub fn with_function_middleware( self, middleware: Vec<Arc<FunctionMiddleware>>, ) -> Self

Configure the function-invocation middleware pipeline run around every tool call: middleware may inspect/rewrite FunctionInvocationContext::arguments, short-circuit execution by setting FunctionInvocationContext::result (and either not calling next, or setting terminate = true), or observe a propagated execution error by matching on the Result returned from their own next.run(...) call. Replaces any previously configured middleware.

pub fn inner(&self) -> &C

A reference to the wrapped client.

Trait Implementations

impl<C: ChatClient> ChatClient for FunctionInvokingChatClient<C>

fn get_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Get a complete (non-streaming) response.

fn get_streaming_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatStream>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Get a streaming response as a sequence of updates.

fn model(&self) -> Option<&str>

The default model id for this client, if any.