Struct CompletionRequest 

pub struct CompletionRequest {
    pub model: String,
    pub messages: Vec<Message>,
    pub max_tokens: u32,
    pub system: Option<String>,
    pub tools: Vec<ToolDefinition>,
    pub stream: bool,
    pub temperature: Option<f32>,
    pub stop_sequences: Vec<String>,
    pub thinking: Option<ThinkingConfig>,
}

A completion request to send to an LLM provider.

Fields

model: String

The model identifier.

messages: Vec<Message>

The conversation messages.

max_tokens: u32

Maximum tokens to generate.

system: Option<String>

Optional system prompt.

tools: Vec<ToolDefinition>

Available tools.

stream: bool

Whether to stream the response.

temperature: Option<f32>

Sampling temperature (0.0-1.0).

stop_sequences: Vec<String>

Stop sequences.

thinking: Option<ThinkingConfig>

Extended thinking configuration.

Implementations

impl CompletionRequest

pub fn new( model: impl Into<String>, messages: Vec<Message>, max_tokens: u32, ) -> Self

Create a new request with required fields.

pub fn system(self, system: impl Into<String>) -> Self

Set the system prompt.

pub fn stream(self, stream: bool) -> Self

Set streaming mode.

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

Set the temperature.

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

Add tools.

pub fn thinking(self, config: ThinkingConfig) -> Self

Set extended thinking configuration.

Trait Implementations

impl Clone for CompletionRequest

fn clone(&self) -> CompletionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CompletionRequest

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

Formats the value using the given formatter.

impl Serialize for CompletionRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.