Struct OpenAIProvider 

pub struct OpenAIProvider { /* private fields */ }

Implementations

impl OpenAIProvider

pub fn new(api_key: String, model: String, base_url: String) -> Self

Trait Implementations

impl Provider for OpenAIProvider

fn context_size(&self) -> Option<u32>

Best-effort context window size (in tokens) for the configured model. None if the provider cannot infer it; callers should treat that as “don’t render a fullness bar”.

fn clone_box(&self) -> Box<dyn Provider>

Clone the provider into a boxed type.

fn chat<'life0, 'async_trait>( &'life0 self, request: ChatRequest, ) -> Pin<Box<dyn Future<Output = Result<ChatResponse>> + Send + 'async_trait>>

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

fn chat_stream<'life0, 'async_trait>( &'life0 self, request: ChatRequest, ) -> Pin<Box<dyn Future<Output = Result<Receiver<StreamEvent>>> + Send + 'async_trait>>

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

Stream a chat turn. Default impl wraps chat and emits one Done event, so providers without native streaming still work (no incremental thinking).