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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
use std::borrow::Cow;
use std::collections::HashMap;
use serde::Serialize;
use hyper::{Body, Request};
use crate::endpoints::request::Endpoint;
/// Given a prompt, the response will return one or more predicted completions,
/// and can also return the probabilities of alternative tokens at each position.
#[derive(Debug, Clone, Serialize)]
pub struct Completion<'a> {
/// The prompt(s) to generate completions for, encoded as a string, array of strings,
/// array of tokens, or array of token arrays.
/// Note that `<|endoftext|>` is the document separator that the model sees during training,
/// so if a prompt is not specified the model will generate as if from the beginning of a new document.
pub prompt: Option<Cow<'a, str>>,
/// The suffix that comes after a completion of inserted text.
pub suffix: Option<Cow<'a, str>>,
/// The maximum number of tokens to generate in the completion.
/// The token count of your prompt plus max_tokens cannot exceed the model's context length.
/// Most models have a context length of 2048 tokens (except for the newest models, which support 4096).
pub max_tokens: u32,
/// What sampling temperature to use. Higher values means the model will take more risks.
/// Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.
/// We generally recommend altering this or top_p but not both.
pub temperature: f32,
/// An alternative to sampling with temperature, called nucleus sampling, where the model
/// considers the results of the tokens with top_p probability mass. So 0.1 means only
/// the tokens comprising the top 10% probability mass are considered.
/// We generally recommend altering this or temperature but not both.
pub top_p: f32,
/// How many completions to generate for each prompt.
/// Note: Because this parameter generates many completions,
/// it can quickly consume your token quota. Use carefully and ensure that
/// you have reasonable settings for max_tokens and stop.
pub n: u32,
/// Whether to stream back partial progress.
/// If set, tokens will be sent as data-only server-sent events as they become available,
/// with the stream terminated by a data: `[DONE]` message.
pub stream: bool,
/// Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens.
/// For example, if logprobs is 5, the API will return a list of the 5 most likely tokens.
/// The API will always return the logprob of the sampled token,
/// so there may be up to logprobs+1 elements in the response.
/// The maximum value for logprobs is 5.
/// If you need more than this, please contact support@openai.com and describe your use case.
pub logprobs: Option<u32>,
/// Echo back the prompt in addition to the completion
pub echo: bool,
/// Up to 4 sequences where the API will stop generating further tokens.
/// The returned text will not contain the stop sequence.
pub stop: Option<Vec<Cow<'a, str>>>,
/// Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they
/// appear in the text so far, increasing the model's likelihood to talk about new topics.
pub presence_penalty: f32,
/// Number between -2.0 and 2.0.
/// Positive values penalize new tokens based on their existing frequency in the text so far,
/// decreasing the model's likelihood to repeat the same line verbatim.
pub frequency_penalty: f32,
/// Generates `best_of` completions server-side and returns the
/// "best" (the one with the lowest log probability per token). Results cannot be streamed.
/// When used with n, best_of controls the number of candidate completions and n specifies
/// how many to return – best_of must be greater than n.
/// Note: Because this parameter generates many completions, it can quickly consume your token
/// quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.
pub best_of: u32,
/// Modify the likelihood of specified tokens appearing in the completion.
/// Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer)
/// to an associated bias value from -100 to 100. You can use this tokenizer tool (which works
/// for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically,
/// the bias is added to the logits generated by the model prior to sampling. The exact effect
/// will vary per model, but values between -1 and 1 should decrease or increase likelihood
/// of selection; values like -100 or 100 should result in a ban or exclusive selection
/// of the relevant token.
pub logit_bias: Option<HashMap<Cow<'a, str>, i32>>,
/// A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse.
pub user: Option<Cow<'a, str>>
}
impl Default for Completion<'_> {
fn default() -> Self {
Self {
prompt: Some(Cow::Borrowed("<|endoftext|>")),
suffix: None,
max_tokens: 16,
temperature: 1.,
top_p: 1.,
n: 1,
stream: false,
logprobs: None,
echo: false,
stop: None,
presence_penalty: 0.,
frequency_penalty: 0.,
best_of: 1,
logit_bias: Some(HashMap::new()),
user: Some(Cow::Borrowed(""))
}
}
}
impl Endpoint for Completion<'_> {
const ENDPOINT: &'static str = "https://api.openai.com/v1/engines/{}/completions";
fn request(
&self,
auth_token: &str,
engine_id: Option<&str>
) -> Request<Body> {
let endpoint = Self::ENDPOINT.replace("{}", engine_id.unwrap());
let serialized = serde_json::to_string(&self)
.expect("Failed to serialize request");
trace!("endpoint={}, serialized={}", endpoint, serialized);
super::request::post!(endpoint, auth_token, serialized)
}
}