Struct ModelConfig 

pub struct ModelConfig { /* private fields */ }

How one model is served: the default_backend used when the request does not pin a wire format, plus any other_backends reachable over additional formats.

Implementations

impl ModelConfig

pub fn new( model_name: impl Into<ModelId>, default_backend: Backend, other_backends: Option<Vec<Backend>>, ) -> Self

A model named model_name served by default_backend, optionally reachable over additional wire formats via other_backends.

pub fn with_responses_compatibility( self, policy: ResponsesCompatibility, ) -> Self

This method selects the Responses request changes required by the model’s provider.

pub fn with_responses_reasoning(self, policy: ResponsesReasoningPolicy) -> Self

Sets how Responses reasoning items are replayed to this model.

pub fn with_provider_model(self, provider_model: impl Into<ModelId>) -> Self

Sends provider_model upstream in place of model_name. The client is still called with model_name, so several entries can serve one provider model with different backend settings.

Trait Implementations

impl Clone for ModelConfig

fn clone(&self) -> ModelConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelConfig

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

Formats the value using the given formatter.