1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
use crate::{
config::Config,
error::OpenAIError,
types::{
ChatCompletionResponseStream, CreateChatCompletionRequest, CreateChatCompletionResponse,
},
Client,
};
/// Given a list of messages comprising a conversation, the model will return a response.
///
/// Related guide: [Chat completions](https://platform.openai.com//docs/guides/text-generation)
pub struct Chat<'c, C: Config> {
client: &'c Client<C>,
}
impl<'c, C: Config> Chat<'c, C> {
pub fn new(client: &'c Client<C>) -> Self {
Self { client }
}
/// Creates a model response for the given chat conversation. Learn more in
/// the
///
/// [text generation](https://platform.openai.com/docs/guides/text-generation),
/// [vision](https://platform.openai.com/docs/guides/vision),
///
/// and [audio](https://platform.openai.com/docs/guides/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](https://platform.openai.com/docs/guides/reasoning).
///
/// byot: You must ensure "stream: false" in serialized `request`
#[crate::byot(
T0 = serde::Serialize,
R = serde::de::DeserializeOwned
)]
pub async fn create(
&self,
request: CreateChatCompletionRequest,
) -> Result<CreateChatCompletionResponse, OpenAIError> {
#[cfg(not(feature = "byot"))]
{
if request.stream.is_some() && request.stream.unwrap() {
return Err(OpenAIError::InvalidArgument(
"When stream is true, use Chat::create_stream".into(),
));
}
}
self.client.post("/chat/completions", request).await
}
/// 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](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) 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`
#[crate::byot(
T0 = serde::Serialize,
R = serde::de::DeserializeOwned,
stream = "true",
where_clause = "R: std::marker::Send + 'static"
)]
#[allow(unused_mut)]
pub async fn create_stream(
&self,
mut request: CreateChatCompletionRequest,
) -> Result<ChatCompletionResponseStream, OpenAIError> {
#[cfg(not(feature = "byot"))]
{
if request.stream.is_some() && !request.stream.unwrap() {
return Err(OpenAIError::InvalidArgument(
"When stream is false, use Chat::create".into(),
));
}
request.stream = Some(true);
}
Ok(self.client.post_stream("/chat/completions", request).await)
}
}