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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
//!
//! Given a prompt, the model will return one or more predicted completions,
//! and can also return the probabilities of alternative tokens at each position.
//!
//! Source: OpenAI documentation

////////////////////////////////////////////////////////////////////////////////

use std::collections::HashMap;

use crate::openai::{
    endpoint::{
        endpoint_filter, request_endpoint, request_endpoint_stream, Endpoint, EndpointVariant,
    },
    types::{
        common::Error,
        completion::{Chunk, CompletionResponse},
        model::Model,
    },
};
use log::{debug, warn};
use serde::{Deserialize, Serialize};
use serde_with::serde_as;

/// Given a prompt, the model will return one or more predicted completions,
/// and can also return the probabilities of alternative tokens at each
/// position.
#[serde_as]
#[derive(Serialize, Deserialize, Debug)]
pub struct Completion {
    pub model: Model,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub prompt: Option<Vec<String>>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub stream: Option<bool>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub suffix: Option<String>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub temperature: Option<f32>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub top_p: Option<f32>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub n: Option<u32>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub logprobs: Option<u32>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub echo: Option<Vec<bool>>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub stop: Option<Vec<String>>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub max_tokens: Option<u32>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub presence_penalty: Option<f32>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub frequency_penalty: Option<f32>,

    #[serde_as(as = "Option<Vec<(_,_)>>")]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub best_of: Option<HashMap<String, u32>>,

    #[serde_as(as = "Option<Vec<(_,_)>>")]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub logit_bias: Option<HashMap<String, f32>>,

    #[serde(skip_serializing_if = "Option::is_none")]
    pub user: Option<String>,
}

impl Default for Completion {
    fn default() -> Self {
        Self {
            model: Model::TEXT_DAVINCI_003,
            prompt: None,
            stream: Some(false),
            temperature: None,
            top_p: None,
            n: None,
            stop: None,
            max_tokens: None,
            presence_penalty: None,
            frequency_penalty: None,
            logit_bias: None,
            user: None,
            suffix: None,
            logprobs: None,
            echo: None,
            best_of: None,
        }
    }
}

impl Completion {
    /// ID of the model to use. You can use the [List models API](https://platform.openai.com/docs/api-reference/models/list) to see all of
    /// your available models, or see our [Model overview](https://platform.openai.com/docs/models/overview) for descriptions of
    /// them.
    pub fn model(self, model: Model) -> Self {
        Self { model, ..self }
    }

    /// Add message to prompt.
    /// 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 fn prompt(self, content: &str) -> Self {
        let mut prompt = vec![];
        if let Some(prmp) = self.prompt {
            prompt.extend(prmp);
        }
        prompt.push(String::from(content));

        Self {
            prompt: Some(prompt),
            ..self
        }
    }

    /// The suffix that comes after a completion of inserted text.
    pub fn suffix(self, suffix: String) -> Self {
        Self {
            suffix: Some(suffix),
            ..self
        }
    }

    /// What sampling temperature to use, between 0 and 2. Higher values like 0.
    /// 8 will make the output more random, while lower values like 0.2 will
    /// make it more focused and deterministic.
    ///
    /// We generally recommend altering this or `top_p` but not both.
    pub fn temperature(self, temperature: f32) -> Self {
        Self {
            temperature: Some(temperature),
            ..self
        }
    }

    /// 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 fn top_p(self, top_p: f32) -> Self {
        Self {
            top_p: Some(top_p),
            ..self
        }
    }

    /// 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 fn n(self, n: u32) -> Self {
        Self { n: Some(n), ..self }
    }
    /// 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 us through our **Help center** and describe your use
    /// case.
    pub fn logprobs(self, logprobs: u32) -> Self {
        Self {
            logprobs: Some(logprobs),
            ..self
        }
    }

    /// Echo back the prompt in addition to the completion
    pub fn echo(self, echo: Vec<bool>) -> Self {
        Self {
            echo: Some(echo),
            ..self
        }
    }

    /// Up to 4 sequences where the API will stop generating further tokens.
    /// The returned text will not contain the stop sequence.
    pub fn stop(self, stop: Vec<String>) -> Self {
        Self {
            stop: Some(stop),
            ..self
        }
    }

    /// The maximum number of [tokens](https://platform.openai.com/tokenizer) 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 fn max_tokens(self, max_tokens: u32) -> Self {
        Self {
            max_tokens: Some(max_tokens),
            ..self
        }
    }

    /// 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.
    ///
    /// [See more information about frequency and presence penalties.](https://platform.openai.com/docs/api-reference/parameter-details)
    pub fn presence_penalty(self, presence_penalty: f32) -> Self {
        Self {
            presence_penalty: Some(presence_penalty),
            ..self
        }
    }

    /// 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.
    ///
    /// [See more information about frequency and presence penalties.](https://platform.openai.com/docs/api-reference/parameter-details)
    pub fn frequency_penalty(self, frequency_penalty: f32) -> Self {
        Self {
            frequency_penalty: Some(frequency_penalty),
            ..self
        }
    }

    /// Generates `best_of` completions server-side and returns the "best" (the
    /// one with the highest 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 fn best_of(self, best_of: HashMap<String, u32>) -> Self {
        Self {
            best_of: Some(best_of),
            ..self
        }
    }

    /// 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](https://platform.openai.com/tokenizer?view=bpe) (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.
    ///
    /// As an example, you can pass `{"50256": -100}` to prevent the
    /// <|endoftext|> token from being generated.
    pub fn logit_bias(self, logit_bias: HashMap<String, f32>) -> Self {
        Self {
            logit_bias: Some(logit_bias),
            ..self
        }
    }

    /// A unique identifier representing your end-user, which can help OpenAI
    /// to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
    pub fn user(self, user: &str) -> Self {
        Self {
            user: Some(user.into()),
            ..self
        }
    }

    /// Send completion request to OpenAI using streamed method.
    ///
    /// Whether to stream back partial progress. If set, 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.
    pub async fn stream_completion<F>(
        self,
        mut cb: Option<F>,
    ) -> Result<Vec<Chunk>, Box<dyn std::error::Error>>
    where
        F: FnMut(Chunk),
    {
        let data = Self {
            stream: Some(true),
            ..self
        };

        if !endpoint_filter(&data.model, &Endpoint::Completion_v1) {
            return Err("Model not compatible with this endpoint".into());
        }

        let mut ret_val: Vec<Chunk> = vec![];

        request_endpoint_stream(&data, &Endpoint::Completion_v1, EndpointVariant::None,|res| {
            if let Ok(chunk_data_raw) = res {
                chunk_data_raw.split("\n").for_each(|chunk_data| {
                    let chunk_data = chunk_data.trim().to_string();
                    if &chunk_data == "data: [DONE]" {
                        debug!(target: "openai", "Last chunk received.");
                        return;
                    }
                    if chunk_data.starts_with("data: ") {
                        // Strip response content:
                        let stripped_chunk = &chunk_data.trim()[6..];
                        if let Ok(message_chunk) = serde_json::from_str::<Chunk>(stripped_chunk) {
                            ret_val.push(message_chunk.clone());
                            if let Some(cb) = &mut cb {
                                cb(message_chunk);
                            }
                        } else {
                            if let Ok(response_error) = serde_json::from_str::<Error>(&stripped_chunk) {
                                warn!(target: "openai",
                                    "OpenAI error code {}: `{:?}`",
                                    response_error.error.code.unwrap_or(0),
                                    stripped_chunk
                                );
                            } else {
                                warn!(target: "openai", "Completion response not deserializable.");
                            }
                        }
                    }
                });
            }
        })
        .await?;

        Ok(ret_val)
    }

    /// Send completion request to OpenAI.
    pub async fn completion(self) -> Result<CompletionResponse, Box<dyn std::error::Error>> {
        
        let data = Self {
            stream: None,
            ..self
        };

        if !endpoint_filter(&data.model, &Endpoint::Completion_v1) {
            return Err("Model not compatible with this endpoint".into());
        }

        let mut completion_response: Option<CompletionResponse> = None;

        request_endpoint(&data, &Endpoint::Completion_v1, EndpointVariant::None, |res| {
            if let Ok(text) = res {
                if let Ok(response_data) = serde_json::from_str::<CompletionResponse>(&text) {
                    debug!(target: "openai", "Response parsed, completion response deserialized.");
                    completion_response = Some(response_data);
                } else {
                    if let Ok(response_error) = serde_json::from_str::<Error>(&text) {
                        warn!(target: "openai",
                            "OpenAI error code {}: `{:?}`",
                            response_error.error.code.unwrap_or(0),
                            text
                        );
                    } else {
                        warn!(target: "openai", "Completion response not deserializable.");
                    }
                }
            }
        })
        .await?;

        if let Some(response_data) = completion_response {
            Ok(response_data)
        } else {
            Err("No response or error parsing response".into())
        }
    }
}