Struct ChatRequest 

pub struct ChatRequest {
    pub model: String,
    pub messages: Vec<ChatMessage>,
    pub temperature: Option<f64>,
    pub max_tokens: Option<u32>,
    pub stop: Option<Vec<String>>,
    pub system_prompt: Option<String>,
    pub tools: Vec<ToolDefinition>,
    pub tool_choice: Option<ToolChoice>,
    pub extra: Map<String, Value>,
}

A request to a chat completion model.

Fields

model: String

Model identifier (e.g., “gpt-4o”, “llama-3-70b”).

messages: Vec<ChatMessage>

Conversation messages.

temperature: Option<f64>

Sampling temperature (0.0–2.0).

max_tokens: Option<u32>

Maximum tokens to generate.

stop: Option<Vec<String>>

Sequences that stop generation.

system_prompt: Option<String>

System prompt override.

tools: Vec<ToolDefinition>

Tools available for the model to call.

tool_choice: Option<ToolChoice>

Controls tool selection behaviour.

extra: Map<String, Value>

Additional provider-specific parameters.

Implementations

impl ChatRequest

pub fn new(model: impl Into<String>, messages: Vec<ChatMessage>) -> Self

Create a new chat request with the given model and messages.

Trait Implementations

impl Clone for ChatRequest

fn clone(&self) -> ChatRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatRequest

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

Formats the value using the given formatter.