Struct HttpRunner 

pub struct HttpRunner { /* private fields */ }

HTTP-backed ModelRunner for OpenAI-compatible and Ollama endpoints.

Implementations

impl HttpRunner

pub fn new_provider(config: ProviderConfig) -> Self

Builds a runner from an open provider config without changing the HTTP transport path.

pub fn new_openai_compatible( runner: Symbol, model: impl Into<String>, endpoint: impl Into<String>, api_key_env: impl Into<String>, codec: Symbol, timeout: Duration, stream: bool, tools: bool, max_response_bytes: usize, ) -> Self

Builds a runner targeting an OpenAI-compatible /chat/completions endpoint, reading its API key from the api_key_env environment variable.

pub fn new_ollama( runner: Symbol, model: impl Into<String>, locality: Symbol, endpoint: impl Into<String>, codec: Symbol, timeout: Duration, stream: bool, tools: bool, max_response_bytes: usize, ) -> Self

Builds a runner targeting an Ollama endpoint at the given locality.

Trait Implementations

impl Clone for HttpRunner

fn clone(&self) -> HttpRunner

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for HttpRunner

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

Formats the value using the given formatter.

impl ModelRunner for HttpRunner

fn card(&self) -> ModelCard

Returns metadata describing the runner’s advertised model surface.

fn infer(&self, cx: &mut Cx, request: ModelRequest) -> Result<ModelResponse>

Executes one non-streaming inference request.

fn infer_stream( &self, cx: &mut Cx, request: ModelRequest, sink: &mut dyn ModelEventSink, ) -> Result<ModelResponse>

Executes one streaming inference request.

fn bid(&self, _request: &ModelRequest) -> Result<ModelBid, Error>

Returns an availability and score hint for market-style routing.