Struct LlmRequest 

pub struct LlmRequest {
    pub messages: Vec<ChatMessage>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub temperature: Option<f32>,
    pub max_tokens: Option<u32>,
    pub force_json: bool,
    pub reasoning: Option<Reasoning>,
}

A request to an LLM provider for chat completion.

Fields

messages: Vec<ChatMessage>

tools: Option<Vec<ToolDefinition>>

temperature: Option<f32>

max_tokens: Option<u32>

force_json: bool

reasoning: Option<Reasoning>

What this request asks of a reasoning model; None defers to whatever default the provider was configured with, and then to the model’s own.

Implementations

impl LlmRequest

pub fn new(messages: Vec<ChatMessage>) -> Self

pub fn reasoning(self, reasoning: Reasoning) -> Self

pub fn temperature(self, temp: f32) -> Self

pub fn max_tokens(self, tokens: u32) -> Self

pub fn tools(self, tools: Vec<ToolDefinition>) -> Self

pub fn force_json(self, force: bool) -> Self

Trait Implementations

impl Clone for LlmRequest

fn clone(&self) -> LlmRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LlmRequest

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

Formats the value using the given formatter.