Struct Chat 

pub struct Chat<'c, C>
where
    C: Config,
{ /* private fields */ }

Given a list of messages comprising a conversation, the model will return a response.

Related guide: Chat completions

Implementations

impl<'c, C> Chat<'c, C>

where C: Config,

pub fn new(client: &'c Client<C>) -> Chat<'c, C>

pub async fn create( &self, request: CreateChatCompletionRequest, ) -> Result<CreateChatCompletionResponse, OpenAIError>

Creates a model response for the given chat conversation. Learn more in the

text generation, vision,

and audio guides.

Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models,

refer to the reasoning guide.

byot: You must ensure “stream: false” in serialized request

pub async fn create_stream( &self, request: CreateChatCompletionRequest, ) -> Result<Pin<Box<dyn Stream<Item = Result<CreateChatCompletionStreamResponse, OpenAIError>> + Send>>, OpenAIError>

Creates a completion for the chat message

partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.

ChatCompletionResponseStream is a parsed SSE stream until a [DONE] is received from server.

byot: You must ensure “stream: true” in serialized request