Struct RoutingExplainParams 

pub struct RoutingExplainParams {
    pub model: String,
    pub messages: Vec<ChatCompletionRequestMessage>,
    pub temperature: Option<f64>,
    pub max_tokens: Option<u32>,
    pub max_completion_tokens: Option<u32>,
    pub top_p: Option<f64>,
}

Arguments for crate::resources::Routing::explain. messages reuses the async-openai request-message type, so a request can be dry-run before it is sent.

Fields

model: String

Model to plan for.

messages: Vec<ChatCompletionRequestMessage>

Conversation to plan for.

temperature: Option<f64>

Optional sampling temperature.

max_tokens: Option<u32>

Optional legacy output-token cap. Prefer Self::max_completion_tokens; the gateway coerces this into max_completion_tokens before forwarding to any OpenAI-compatible provider.

max_completion_tokens: Option<u32>

Optional canonical output-token cap (the current OpenAI standard). Takes precedence over Self::max_tokens when both are set.

top_p: Option<f64>

Optional nucleus-sampling top-p.

Implementations

impl RoutingExplainParams

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

A dry-run for model over messages with default sampling.

Trait Implementations

impl Clone for RoutingExplainParams

fn clone(&self) -> RoutingExplainParams

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RoutingExplainParams

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

Formats the value using the given formatter.

impl Serialize for RoutingExplainParams

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

where __S: Serializer,

Serialize this value into the given Serde serializer.