Struct ChatCompletionRequestBody

pub struct ChatCompletionRequestBody {

    pub model: String,
    pub messages: Vec<Message>,
    pub store: Option<bool>,
    pub frequency_penalty: Option<f32>,
    pub logit_bias: Option<FxHashMap<String, i32>>,
    pub logprobs: Option<bool>,
    pub top_logprobs: Option<u8>,
    pub max_completion_tokens: Option<u64>,
    pub n: Option<u32>,
    pub modalities: Option<Vec<String>>,
    pub presence_penalty: Option<f32>,
    pub temperature: Option<f32>,
    pub response_format: Option<ChatCompletionResponseFormat>,
}

Request body structure for OpenAI Chat Completion API.

This structure contains all the parameters that can be sent to the OpenAI Chat Completion endpoint. Most fields are optional and will be omitted from the JSON if not set.

Fields

• model - ID of the model to use (required)
• messages - List of conversation messages (required)
• store - Whether to store the output for the user
• frequency_penalty - Penalty for token frequency (-2.0 to 2.0)
• logit_bias - Modify likelihood of specified tokens
• logprobs - Whether to return log probabilities
• top_logprobs - Number of most likely tokens to return (0-20)
• max_completion_tokens - Maximum tokens to generate
• n - Number of completion choices to generate
• modalities - Output types the model should generate
• presence_penalty - Penalty for token presence (-2.0 to 2.0)
• temperature - Sampling temperature (0-2)
• response_format - Output format specification

Example

use openai_tools::chat::ChatCompletionRequestBody;
use openai_tools::common::Message;

let mut body = ChatCompletionRequestBody::new("gpt-4o-mini".to_string());
body.messages = vec![Message::from_string("user".to_string(), "Hello!".to_string())];
body.temperature = Some(0.7);

Fields

model: String

ID of the model to use. (https://platform.openai.com/docs/models#model-endpoint-compatibility)

messages: Vec<Message>

A list of messages comprising the conversation so far.

store: Option<bool>

Whether or not to store the output of this chat completion request for user. false by default.

frequency_penalty: Option<f32>

-2.0 ~ 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.

logit_bias: Option<FxHashMap<String, i32>>

Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens to an associated bias value from 100 to 100.

logprobs: Option<bool>

Whether to return log probabilities of the output tokens or not.

top_logprobs: Option<u8>

0 ~ 20. Specify the number of most likely tokens to return at each token position, each with an associated log probability.

max_completion_tokens: Option<u64>

An upper bound for the number of tokens that can be generated for a completion.

n: Option<u32>

How many chat completion choices to generate for each input message. 1 by default.

modalities: Option<Vec<String>>

Output types that you would like the model to generate for this request. [“text”] for most models.

presence_penalty: Option<f32>

-2.0 ~ 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.

temperature: Option<f32>

0 ~ 2. What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

response_format: Option<ChatCompletionResponseFormat>

An object specifying the format that the model must output. (https://platform.openai.com/docs/guides/structured-outputs)

Implementations

impl ChatCompletionRequestBody

pub fn new(model_id: String) -> Self

Creates a new ChatCompletionRequestBody with the specified model ID.

All other fields are initialized to their default values and can be configured using the builder pattern methods.

Arguments

• model_id - The ID of the OpenAI model to use

Returns

A new ChatCompletionRequestBody instance with the model ID set.

Example

use openai_tools::chat::ChatCompletionRequestBody;

let body = ChatCompletionRequestBody::new("gpt-4o-mini".to_string());
assert_eq!(body.model, "gpt-4o-mini");

pub fn default() -> Self

Creates a new ChatCompletionRequestBody with all fields set to default values.

This is equivalent to using Default::default() but provides a more explicit way to create an empty request body.

Returns

A new ChatCompletionRequestBody instance with default values.

Trait Implementations

impl Clone for ChatCompletionRequestBody

fn clone(&self) -> ChatCompletionRequestBody

Returns a duplicate of the value.

const fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ChatCompletionRequestBody

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ChatCompletionRequestBody

fn default() -> ChatCompletionRequestBody

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChatCompletionRequestBody

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ChatCompletionRequestBody

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.