Struct ChatCompletionRequest 

pub struct ChatCompletionRequest {

    pub model: String,
    pub temperature: Option<Option<f64>>,
    pub top_p: Option<f64>,
    pub max_tokens: Option<Option<i32>>,
    pub stream: Option<bool>,
    pub stop: Option<Box<Stop>>,
    pub random_seed: Option<Option<i32>>,
    pub metadata: Option<Option<HashMap<String, Value>>>,
    pub messages: Vec<MessagesInner>,
    pub response_format: Option<Box<ResponseFormat>>,
    pub tools: Option<Option<Vec<Tool>>>,
    pub tool_choice: Option<Box<ToolChoice>>,
    pub presence_penalty: Option<f64>,
    pub frequency_penalty: Option<f64>,
    pub n: Option<Option<i32>>,
    pub prediction: Option<Box<Prediction>>,
    pub parallel_tool_calls: Option<bool>,
    pub prompt_mode: Option<Option<MistralPromptMode>>,
    pub guardrails: Option<Option<Vec<GuardrailConfig>>>,
    pub safe_prompt: Option<bool>,
}

Fields

model: String

ID of the model to use. You can use the List Available Models API to see all of your available models, or see our Model overview for model descriptions.

temperature: Option<Option<f64>>

top_p: Option<f64>

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.

max_tokens: Option<Option<i32>>

stream: Option<bool>

Whether to stream back partial progress. If set, tokens will be sent as data-only server-side events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.

stop: Option<Box<Stop>>

random_seed: Option<Option<i32>>

metadata: Option<Option<HashMap<String, Value>>>

messages: Vec<MessagesInner>

The prompt(s) to generate completions for, encoded as a list of dict with role and content.

response_format: Option<Box<ResponseFormat>>

tools: Option<Option<Vec<Tool>>>

tool_choice: Option<Box<ToolChoice>>

presence_penalty: Option<f64>

The presence_penalty determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative.

frequency_penalty: Option<f64>

The frequency_penalty penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition.

n: Option<Option<i32>>

prediction: Option<Box<Prediction>>

Enable users to specify expected results, optimizing response times by leveraging known or predictable content. This approach is especially effective for updating text documents or code files with minimal changes, reducing latency while maintaining high-quality results.

parallel_tool_calls: Option<bool>

Whether to enable parallel function calling during tool use, when enabled the model can call multiple tools in parallel.

prompt_mode: Option<Option<MistralPromptMode>>

guardrails: Option<Option<Vec<GuardrailConfig>>>

safe_prompt: Option<bool>

Whether to inject a safety prompt before all conversations.

Implementations

impl ChatCompletionRequest

pub fn new(model: String, messages: Vec<MessagesInner>) -> ChatCompletionRequest

Trait Implementations

impl Clone for ChatCompletionRequest

fn clone(&self) -> ChatCompletionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatCompletionRequest

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

Formats the value using the given formatter.

impl Default for ChatCompletionRequest

fn default() -> ChatCompletionRequest

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChatCompletionRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ChatCompletionRequest

fn eq(&self, other: &ChatCompletionRequest) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ChatCompletionRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ChatCompletionRequest