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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663
//! Types used in OpenAI API requests and responses.
//! These types are created from component schemas in the [OpenAPI spec](https://github.com/openai/openai-openapi)
use std::{
collections::HashMap,
fmt::Display,
path::{Path, PathBuf},
pin::Pin,
};
use futures::Stream;
use serde::{Deserialize, Serialize};
use crate::{
download::{download_url, save_b64},
error::OpenAIError,
};
#[derive(Debug, Deserialize)]
pub struct Model {
pub id: String,
pub object: String,
pub created: u32,
pub owned_by: String,
}
#[derive(Debug, Deserialize)]
pub struct ListModelResponse {
pub object: String,
pub data: Vec<Model>,
}
#[derive(Serialize, Default, Debug)]
pub struct CreateCompletionRequest {
/// ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.
pub model: String,
/// 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.
#[serde(skip_serializing_if = "Option::is_none")]
pub prompt: Option<String>, // todo check type
/// The suffix that comes after a completion of inserted text.
#[serde(skip_serializing_if = "Option::is_none")]
pub suffix: Option<String>, // todo: default null
/// The maximum number of [tokens](/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).
#[serde(skip_serializing_if = "Option::is_none")]
pub max_tokens: Option<u16>,
/// What [sampling temperature](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277) 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.
#[serde(skip_serializing_if = "Option::is_none")]
pub temperature: Option<f32>, // todo: min:0 ,max: 2, default: 1,
/// 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.
#[serde(skip_serializing_if = "Option::is_none")]
pub top_p: Option<f32>, // todo: min: 0, max: 1, default: 1
/// 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`.
///
#[serde(skip_serializing_if = "Option::is_none")]
pub n: Option<u8>, // min:1 max: 128, default: 1
/// 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.
#[serde(skip_serializing_if = "Option::is_none")]
pub stream: Option<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 us through our [Help center](https://help.openai.com) and describe your use case.
#[serde(skip_serializing_if = "Option::is_none")]
pub logprobs: Option<u8>, // min:0 , max: 5, default: null
/// Echo back the prompt in addition to the completion
#[serde(skip_serializing_if = "Option::is_none")]
pub echo: Option<bool>,
/// Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
#[serde(skip_serializing_if = "Option::is_none")]
pub stop: Option<String>, //todo: type?
/// 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.](/docs/api-reference/parameter-details)
#[serde(skip_serializing_if = "Option::is_none")]
pub presence_penalty: Option<f32>, // min: -2.0, max: 2.0, default 0
/// 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.](/docs/api-reference/parameter-details)
#[serde(skip_serializing_if = "Option::is_none")]
pub frequency_penalty: Option<f32>, // min: -2.0, max: 2.0, default: 0
/// 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`.
#[serde(skip_serializing_if = "Option::is_none")]
pub best_of: Option<u8>, //min: 0, max: 20, default: 1
/// 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](/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.
#[serde(skip_serializing_if = "Option::is_none")]
pub logit_bias: Option<HashMap<String, serde_json::Value>>, // default: null
/// A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse. [Learn more](/docs/usage-policies/end-user-ids).
#[serde(skip_serializing_if = "Option::is_none")]
pub user: Option<String>,
}
#[derive(Debug, Deserialize)]
pub struct Logprobs {
pub tokens: Vec<String>,
pub token_logprobs: Vec<Option<f32>>, // Option is to account for null value in the list
pub top_logprobs: Vec<serde_json::Value>,
pub text_offset: Vec<u32>,
}
#[derive(Debug, Deserialize)]
pub struct Choice {
pub text: String,
pub index: u32,
pub logprobs: Option<Logprobs>,
pub finish_reason: Option<String>,
}
#[derive(Debug, Deserialize)]
pub struct Usage {
pub prompt_tokens: u32,
pub completion_tokens: u32,
pub total_tokens: u32,
}
#[derive(Debug, Deserialize)]
pub struct CreateCompletionResponse {
pub id: String,
pub object: String,
pub created: u32,
pub model: String,
pub choices: Vec<Choice>,
pub usage: Option<Usage>,
}
/// Parsed server side events stream until an [DONE] is received from server.
pub type CompletionResponseStream =
Pin<Box<dyn Stream<Item = Result<CreateCompletionResponse, OpenAIError>>>>;
#[derive(Debug, Serialize, Default)]
pub struct CreateEditRequest {
/// ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.
pub model: String,
/// The input text to use as a starting point for the edit.
#[serde(skip_serializing_if = "Option::is_none")]
pub input: Option<String>, // default ''
/// The instruction that tells the model how to edit the prompt.
pub instruction: String,
/// How many edits to generate for the input and instruction.
#[serde(skip_serializing_if = "Option::is_none")]
pub n: Option<u8>, // min:1 max: 20 default:1
/// What [sampling temperature](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277) 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.
#[serde(skip_serializing_if = "Option::is_none")]
pub temperature: Option<f32>, // todo: min:0 ,max: 2, default: 1,
/// 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.
#[serde(skip_serializing_if = "Option::is_none")]
pub top_p: Option<f32>, // todo: min: 0, max: 1, default: 1
}
#[derive(Debug, Deserialize)]
pub struct CreateEditResponse {
pub id: Option<String>,
pub object: String,
pub created: u32,
pub model: Option<String>,
pub choices: Vec<Choice>,
pub usage: Usage,
}
#[derive(Default, Debug, Serialize)]
pub enum ImageSize {
#[serde(rename = "256x256")]
S256x256,
#[serde(rename = "512x512")]
S512x512,
#[default]
#[serde(rename = "1024x1024")]
S1024x1024,
}
impl Display for ImageSize {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(
f,
"{}",
match self {
ImageSize::S256x256 => "256x256",
ImageSize::S512x512 => "512x512",
ImageSize::S1024x1024 => "1024x1024",
}
)
}
}
#[derive(Debug, Serialize, Default)]
#[serde(rename_all = "lowercase")]
pub enum ResponseFormat {
#[default]
Url,
#[serde(rename = "b64_json")]
B64Json,
}
impl Display for ResponseFormat {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(
f,
"{}",
match self {
ResponseFormat::Url => "url",
ResponseFormat::B64Json => "b64_json",
}
)
}
}
#[derive(Debug, Serialize, Default)]
pub struct CreateImageRequest {
/// A text description of the desired image(s). The maximum length is 1000 characters.
pub prompt: String,
/// The number of images to generate. Must be between 1 and 10.
#[serde(skip_serializing_if = "Option::is_none")]
pub n: Option<u8>, // min:1 max:10 default:1
/// The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.
#[serde(skip_serializing_if = "Option::is_none")]
pub size: Option<ImageSize>,
/// The format in which the generated images are returned. Must be one of `url` or `b64_json`.
#[serde(skip_serializing_if = "Option::is_none")]
pub response_format: Option<ResponseFormat>,
/// A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse. [Learn more](/docs/usage-policies/end-user-ids).
#[serde(skip_serializing_if = "Option::is_none")]
pub user: Option<String>,
}
#[derive(Debug, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum ImageData {
Url(std::sync::Arc<String>),
#[serde(rename = "b64_json")]
B64Json(std::sync::Arc<String>),
}
#[derive(Debug, Deserialize)]
pub struct ImageResponse {
pub created: u32,
pub data: Vec<std::sync::Arc<ImageData>>,
}
#[derive(Debug, Default)]
pub struct ImageInput {
pub path: PathBuf,
}
impl ImageInput {
pub fn new<P: AsRef<Path>>(path: P) -> Self {
ImageInput {
path: PathBuf::from(path.as_ref()),
}
}
}
impl ImageResponse {
pub async fn save<P: AsRef<Path>>(&self, dir: P) -> Result<(), OpenAIError> {
let exists = match Path::try_exists(dir.as_ref()) {
Ok(exists) => exists,
Err(e) => return Err(OpenAIError::FileSaveError(e.to_string())),
};
if !exists {
std::fs::create_dir_all(dir.as_ref())
.map_err(|e| OpenAIError::FileSaveError(e.to_string()))?;
}
let mut handles = vec![];
for id in self.data.clone() {
let dir_buf = PathBuf::from(dir.as_ref());
handles.push(tokio::spawn(async move { id.save(dir_buf).await }));
}
let result = futures::future::join_all(handles).await;
let errors: Vec<OpenAIError> = result
.into_iter()
.filter(|r| r.is_err() || r.as_ref().ok().unwrap().is_err())
.map(|r| match r {
Err(e) => OpenAIError::FileSaveError(e.to_string()),
Ok(inner) => inner.err().unwrap(),
})
.collect();
if errors.len() > 0 {
Err(OpenAIError::FileSaveError(
errors
.into_iter()
.map(|e| e.to_string())
.collect::<Vec<String>>()
.join("; "),
))
} else {
Ok(())
}
}
}
impl ImageData {
async fn save<P: AsRef<Path>>(&self, dir: P) -> Result<(), OpenAIError> {
match self {
ImageData::Url(url) => download_url(url, dir).await?,
ImageData::B64Json(b64_json) => save_b64(b64_json, dir).await?,
}
Ok(())
}
}
#[derive(Debug, Default)]
pub struct CreateImageEditRequest {
/// The image to edit. Must be a valid PNG file, less than 4MB, and square.
pub image: ImageInput,
/// An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.
pub mask: ImageInput,
/// A text description of the desired image(s). The maximum length is 1000 characters.
pub prompt: String,
/// The number of images to generate. Must be between 1 and 10.
pub n: Option<u8>, // min:1 max:10 default:1
/// The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.
pub size: Option<ImageSize>,
/// The format in which the generated images are returned. Must be one of `url` or `b64_json`.
pub response_format: Option<ResponseFormat>,
/// A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse. [Learn more](/docs/usage-policies/end-user-ids).
pub user: Option<String>,
}
#[derive(Debug, Default)]
pub struct CreateImageVariationRequest {
/// The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
pub image: ImageInput,
/// The number of images to generate. Must be between 1 and 10.
pub n: Option<u8>, // min:1 max:10 default:1
/// The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.
pub size: Option<ImageSize>,
/// The format in which the generated images are returned. Must be one of `url` or `b64_json`.
pub response_format: Option<ResponseFormat>,
/// A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse. [Learn more](/docs/usage-policies/end-user-ids).
pub user: Option<String>,
}
#[derive(Debug, Serialize)]
#[serde(untagged)]
pub enum Input {
Single(String),
Array(Vec<String>),
}
impl Default for Input {
fn default() -> Self {
Input::Single("".to_owned())
}
}
#[derive(Debug, Serialize, Default)]
pub enum TextModerationModel {
#[default]
#[serde(rename = "text-moderation-latest")]
Latest,
#[serde(rename = "text-moderation-stable")]
Stable,
}
#[derive(Debug, Serialize, Default)]
pub struct CreateModerationRequest {
/// The input text to classify
pub input: Input,
/// Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`.
///
/// The default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`.
#[serde(skip_serializing_if = "Option::is_none")]
pub model: Option<TextModerationModel>,
}
#[derive(Debug, Deserialize)]
pub struct Category {
pub hate: bool,
#[serde(rename = "hate/threatening")]
pub hate_threatening: bool,
#[serde(rename = "self-harm")]
pub self_harm: bool,
pub sexual: bool,
#[serde(rename = "sexual/minors")]
pub sexual_minors: bool,
pub violence: bool,
#[serde(rename = "violence/graphic")]
pub violence_graphic: bool,
}
#[derive(Debug, Deserialize)]
pub struct CategoryScore {
pub hate: f32,
#[serde(rename = "hate/threatening")]
pub hate_threatening: f32,
#[serde(rename = "self-harm")]
pub self_harm: f32,
pub sexual: f32,
#[serde(rename = "sexual/minors")]
pub sexual_minors: f32,
pub violence: f32,
#[serde(rename = "violence/graphic")]
pub violence_graphic: f32,
}
#[derive(Debug, Deserialize)]
pub struct ContentModerationResult {
pub flagged: bool,
pub categories: Category,
pub category_scores: CategoryScore,
}
#[derive(Debug, Deserialize)]
pub struct CreateModerationResponse {
pub id: String,
pub model: String,
pub results: Vec<ContentModerationResult>,
}
pub struct FileInput {
pub path: PathBuf,
}
impl FileInput {
pub fn new<P: AsRef<Path>>(path: P) -> Self {
Self {
path: PathBuf::from(path.as_ref()),
}
}
}
pub struct CreateFileRequest {
/// Name of the [JSON Lines](https://jsonlines.readthedocs.io/en/latest/) file to be uploaded.
///
/// If the `purpose` is set to "fine-tune", each line is a JSON record with "prompt" and "completion" fields representing your [training examples](/docs/guides/fine-tuning/prepare-training-data).
pub file: FileInput,
/// The intended purpose of the uploaded documents.
///
/// Use "fine-tune" for [Fine-tuning](/docs/api-reference/fine-tunes). This allows us to validate the format of the uploaded file.
pub purpose: String,
}
#[derive(Debug, Deserialize)]
pub struct ListFilesResponse {
pub object: String,
pub data: Vec<OpenAIFile>,
}
#[derive(Debug, Deserialize)]
pub struct DeleteFileResponse {
pub id: String,
pub object: String,
pub deleted: bool,
}
#[derive(Debug, Deserialize, PartialEq)]
pub struct OpenAIFile {
pub id: String,
pub object: String,
pub bytes: u32,
pub created_at: u32,
pub filename: String,
pub purpose: String,
pub status: Option<String>,
pub status_details: Option<serde_json::Value>, // nullable: true
}
#[derive(Debug, Serialize)]
pub struct CreateFineTuneRequest {
/// The ID of an uploaded file that contains training data.
///
/// See [upload file](https://beta.openai.com/docs/api-reference/files/upload) for how to upload a file.
///
/// Your dataset must be formatted as a JSONL file, where each training
/// example is a JSON object with the keys "prompt" and "completion".
/// Additionally, you must upload your file with the purpose `fine-tune`.
///
/// See the [fine-tuning guide](https://beta.openai.com/docs/guides/fine-tuning/creating-training-data) for more details.
pub training_file: String,
/// The ID of an uploaded file that contains validation data.
///
/// If you provide this file, the data is used to generate validation
/// metrics periodically during fine-tuning. These metrics can be viewed in
/// the [fine-tuning results file](https://beta.openai.com/docs/guides/fine-tuning/analyzing-your-fine-tuned-model).
/// Your train and validation data should be mutually exclusive.
///
/// Your dataset must be formatted as a JSONL file, where each validation
/// example is a JSON object with the keys "prompt" and "completion".
/// Additionally, you must upload your file with the purpose `fine-tune`.
///
/// See the [fine-tuning guide](https://beta.openai.com/docs/guides/fine-tuning/creating-training-data) for more details.
pub validation_file: Option<String>,
/// The name of the base model to fine-tune. You can select one of "ada",
/// "babbage", "curie", "davinci", or a fine-tuned model created after 2022-04-21.
/// To learn more about these models, see the [Models](https://beta.openai.com/docs/models) documentation.
pub model: Option<String>,
/// The number of epochs to train the model for. An epoch refers to one
/// full cycle through the training dataset.
pub n_epochs: Option<u32>, // default: 4
/// The batch size to use for training. The batch size is the number of
/// training examples used to train a single forward and backward pass.
///
/// By default, the batch size will be dynamically configured to be
/// ~0.2% of the number of examples in the training set, capped at 256 -
/// in general, we've found that larger batch sizes tend to work better
/// for larger datasets.
pub batch_size: Option<u32>, // default: null
/// The learning rate multiplier to use for training.
/// The fine-tuning learning rate is the original learning rate used for
/// pretraining multiplied by this value.
///
/// By default, the learning rate multiplier is the 0.05, 0.1, or 0.2
/// depending on final `batch_size` (larger learning rates tend to
/// perform better with larger batch sizes). We recommend experimenting
/// with values in the range 0.02 to 0.2 to see what produces the best
/// results.
pub learning_rate_multiplier: Option<f32>, // default: null
/// The weight to use for loss on the prompt tokens. This controls how
/// much the model tries to learn to generate the prompt (as compared
/// to the completion which always has a weight of 1.0), and can add
/// a stabilizing effect to training when completions are short.
///
/// If prompts are extremely long (relative to completions), it may make
/// sense to reduce this weight so as to avoid over-prioritizing
/// learning the prompt.
pub prompt_loss_weight: Option<f32>, // default: 0.01
/// If set, we calculate classification-specific metrics such as accuracy
/// and F-1 score using the validation set at the end of every epoch.
/// These metrics can be viewed in the [results file](https://beta.openai.com/docs/guides/fine-tuning/analyzing-your-fine-tuned-model).
///
/// In order to compute classification metrics, you must provide a
/// `validation_file`. Additionally, you must
/// specify `classification_n_classes` for multiclass classification or
/// `classification_positive_class` for binary classification.
pub compute_classification_metrics: Option<bool>, // default: false
/// The number of classes in a classification task.
///
/// This parameter is required for multiclass classification.
pub classification_n_classes: Option<u32>, // default: null
/// The positive class in binary classification.
///
/// This parameter is needed to generate precision, recall, and F1
/// metrics when doing binary classification.
pub classification_positive_class: Option<String>, // default: null
/// If this is provided, we calculate F-beta scores at the specified
/// beta values. The F-beta score is a generalization of F-1 score.
/// This is only used for binary classification.
///
/// With a beta of 1 (i.e. the F-1 score), precision and recall are
/// given the same weight. A larger beta score puts more weight on
/// recall and less on precision. A smaller beta score puts more weight
/// on precision and less on recall.
pub classification_betas: Option<Vec<f32>>, // default: null
/// A string of up to 40 characters that will be added to your fine-tuned model name.
///
/// For example, a `suffix` of "custom-model-name" would produce a model name like `ada:ft-your-org:custom-model-name-2022-02-15-04-21-04`.
pub suffix: Option<String>, // default: null, minLength:1, maxLength:40
}
#[derive(Debug, Deserialize)]
pub struct ListFineTuneResponse {
pub object: String,
pub data: Vec<FineTune>,
}
#[derive(Debug, Deserialize)]
pub struct FineTune {
pub id: String,
pub object: String,
pub created_at: u32,
pub updated_at: u32,
pub model: String,
pub fine_tuned_model: Option<String>, // nullable: true
pub organization_id: String,
pub status: String,
pub hyperparams: serde_json::Value,
pub training_files: Vec<OpenAIFile>,
pub validation_files: Vec<OpenAIFile>,
pub result_files: Vec<OpenAIFile>,
pub events: Option<Vec<FineTuneEvent>>,
}
#[derive(Debug, Deserialize)]
pub struct FineTuneEvent {
pub object: String,
pub created_at: u32,
pub level: String,
pub message: String,
}
#[derive(Debug, Deserialize)]
pub struct ListFineTuneEventsResponse {
pub object: String,
pub data: Vec<FineTuneEvent>,
}
#[derive(Debug, Deserialize)]
pub struct DeleteModelResponse {
pub id: String,
pub object: String,
pub deleted: bool,
}