Skip to main content

execute_response_request_with_cache

sim_lib_openai_server::routes::responses

Function execute_response_request_with_cache 

Source 
pub fn execute_response_request_with_cache<S, C>(
    cx: &mut Cx,
    store: &mut S,
    cache: &mut OpenAiPlanCache,
    ids: &mut ResponseIdGenerators,
    clock: &mut C,
    request: &GatewayRequest,
) -> ResponseExecution
where
    S: GatewayStore + GatewayResponseObjectStore + GatewayStateStore,
    C: GatewayClock,
Expand description

Executes a /v1/responses request reusing the given plan cache, with no runner or federation targets.