openai_struct/models/
create_completion_request.rs

1/*
2 * OpenAI API
3 *
4 * The OpenAI REST API. Please see pub https://platform.openai.com/docs/api-reference for more details.
5 *
6 * OpenAPI spec pub version: 2.3.0
7 *
8 * Generated pub by: https://github.com/swagger-api/swagger-codegen.git
9 */
10
11#[allow(unused_imports)]
12use serde_json::Value;
13
14#[derive(Debug, Serialize, Deserialize)]
15pub struct CreateCompletionRequest {
16    /// 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`.
17    #[serde(rename = "best_of")]
18    pub best_of: Option<i32>,
19    /// Echo back the prompt in addition to the completion
20    #[serde(rename = "echo")]
21    pub echo: Option<bool>,
22    /// 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/guides/text-generation)
23    #[serde(rename = "frequency_penalty")]
24    pub frequency_penalty: Option<f32>,
25    /// 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) 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.
26    #[serde(rename = "logit_bias")]
27    pub logit_bias: Option<::std::collections::HashMap<String, i32>>,
28    /// Include the log probabilities on the `logprobs` most likely output 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.
29    #[serde(rename = "logprobs")]
30    pub logprobs: Option<i32>,
31    /// The maximum number of [tokens](/tokenizer) that can be generated in the completion.  The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.
32    #[serde(rename = "max_tokens")]
33    pub max_tokens: Option<i32>,
34    /// 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) for descriptions of them.
35    #[serde(rename = "model")]
36    pub model: Value,
37    /// 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`.
38    #[serde(rename = "n")]
39    pub n: Option<i32>,
40    /// 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/guides/text-generation)
41    #[serde(rename = "presence_penalty")]
42    pub presence_penalty: Option<f32>,
43    /// 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.
44    #[serde(rename = "prompt")]
45    pub prompt: Value,
46    /// If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.  Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
47    #[serde(rename = "seed")]
48    pub seed: Option<i64>,
49    #[serde(rename = "stop")]
50    pub stop: Option<crate::models::StopConfiguration>,
51    /// 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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
52    #[serde(rename = "stream")]
53    pub stream: Option<bool>,
54    #[serde(rename = "stream_options")]
55    pub stream_options: Option<crate::models::ChatCompletionStreamOptions>,
56    /// The suffix that comes after a completion of inserted text.  This parameter is only supported for `gpt-3.5-turbo-instruct`.
57    #[serde(rename = "suffix")]
58    pub suffix: Option<String>,
59    /// 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.
60    #[serde(rename = "temperature")]
61    pub temperature: Option<f32>,
62    /// 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.
63    #[serde(rename = "top_p")]
64    pub top_p: Option<f32>,
65    /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids).
66    #[serde(rename = "user")]
67    pub user: Option<String>,
68}
openai_struct/models/create_completion_request.rs

openai_struct/models/
create_completion_request.rs
