openai_struct/models/create_chat_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 CreateChatCompletionRequest {
16 #[serde(rename = "metadata")]
17 pub metadata: Option<crate::models::Metadata>,
18 #[serde(rename = "service_tier")]
19 pub service_tier: Option<crate::models::ServiceTier>,
20 /// 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.
21 #[serde(rename = "temperature")]
22 pub temperature: Option<f32>,
23 /// 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.
24 #[serde(rename = "top_p")]
25 pub top_p: Option<f32>,
26 /// 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).
27 #[serde(rename = "user")]
28 pub user: Option<String>,
29 #[serde(rename = "audio")]
30 pub audio: Option<crate::models::CreateChatCompletionRequestAudio>,
31 /// 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.
32 #[serde(rename = "frequency_penalty")]
33 pub frequency_penalty: Option<f32>,
34 /// Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{\"name\": \"my_function\"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present.
35 #[serde(rename = "function_call")]
36 pub function_call: Option<Value>,
37 /// Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for.
38 #[serde(rename = "functions")]
39 pub functions: Option<Vec<crate::models::ChatCompletionFunctions>>,
40 /// Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. 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.
41 #[serde(rename = "logit_bias")]
42 pub logit_bias: Option<::std::collections::HashMap<String, i32>>,
43 /// Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`.
44 #[serde(rename = "logprobs")]
45 pub logprobs: Option<bool>,
46 /// An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](/docs/guides/reasoning).
47 #[serde(rename = "max_completion_tokens")]
48 pub max_completion_tokens: Option<i32>,
49 /// The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API. This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with [o-series models](/docs/guides/reasoning).
50 #[serde(rename = "max_tokens")]
51 pub max_tokens: Option<i32>,
52 /// A list of messages comprising the conversation so far. Depending on the [model](/docs/models) you use, different message types (modalities) are supported, like [text](/docs/guides/text-generation), [images](/docs/guides/vision), and [audio](/docs/guides/audio).
53 #[serde(rename = "messages")]
54 pub messages: Vec<crate::models::ChatCompletionRequestMessage>,
55 #[serde(rename = "modalities")]
56 pub modalities: Option<crate::models::ResponseModalities>,
57 /// Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](/docs/models) to browse and compare available models.
58 #[serde(rename = "model")]
59 pub model: crate::models::ModelIdsShared,
60 /// How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.
61 #[serde(rename = "n")]
62 pub n: Option<i32>,
63 #[serde(rename = "parallel_tool_calls")]
64 pub parallel_tool_calls: Option<crate::models::ParallelToolCalls>,
65 /// Configuration for a [Predicted Output](/docs/guides/predicted-outputs), which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.
66 #[serde(rename = "prediction")]
67 pub prediction: Option<Value>,
68 /// 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.
69 #[serde(rename = "presence_penalty")]
70 pub presence_penalty: Option<f32>,
71 #[serde(rename = "reasoning_effort")]
72 pub reasoning_effort: Option<crate::models::ReasoningEffort>,
73 /// An object specifying the format that the model must output. Setting to `{ \"type\": \"json_schema\", \"json_schema\": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](/docs/guides/structured-outputs). Setting to `{ \"type\": \"json_object\" }` enables the older JSON mode, which ensures the message the model generates is valid JSON. Using `json_schema` is preferred for models that support it.
74 #[serde(rename = "response_format")]
75 pub response_format: Option<Value>,
76 /// This feature is in Beta. 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.
77 #[serde(rename = "seed")]
78 pub seed: Option<i32>,
79 #[serde(rename = "stop")]
80 pub stop: Option<crate::models::StopConfiguration>,
81 /// Whether or not to store the output of this chat completion request for use in our [model distillation](/docs/guides/distillation) or [evals](/docs/guides/evals) products.
82 #[serde(rename = "store")]
83 pub store: Option<bool>,
84 /// If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](/docs/api-reference/chat/streaming) for more information, along with the [streaming responses](/docs/guides/streaming-responses) guide for more information on how to handle the streaming events.
85 #[serde(rename = "stream")]
86 pub stream: Option<bool>,
87 #[serde(rename = "stream_options")]
88 pub stream_options: Option<crate::models::ChatCompletionStreamOptions>,
89 #[serde(rename = "tool_choice")]
90 pub tool_choice: Option<crate::models::ChatCompletionToolChoiceOption>,
91 /// A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.
92 #[serde(rename = "tools")]
93 pub tools: Option<Vec<crate::models::ChatCompletionTool>>,
94 /// An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used.
95 #[serde(rename = "top_logprobs")]
96 pub top_logprobs: Option<i32>,
97 #[serde(rename = "web_search_options")]
98 pub web_search_options: Option<crate::models::WebSearch>,
99}