Struct InferenceGatewayClient

pub struct InferenceGatewayClient { /* private fields */ }

Client for interacting with the Inference Gateway API

Implementations

impl InferenceGatewayClient

pub fn new(base_url: &str) -> Self

Creates a new client instance

Arguments

• base_url - Base URL of the Inference Gateway API

pub fn with_tools(self, tools: Option<Vec<Tool>>) -> Self

Provides tools to use for generation

Arguments

• tools - List of tools to use for generation

Returns

Self with the tools set

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

Sets an authentication token for the client

Arguments

• token - JWT token for authentication

Returns

Self with the token set

pub fn with_max_tokens(self, max_tokens: Option<i32>) -> Self

Sets the maximum number of tokens to generate

Arguments

• max_tokens - Maximum number of tokens to generate

Returns

Self with the maximum tokens set

Trait Implementations

impl Debug for InferenceGatewayClient

Implement Debug for InferenceGatewayClient

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

Formats the value using the given formatter.

impl InferenceGatewayAPI for InferenceGatewayClient

fn generate_content_stream( &self, provider: Provider, model: &str, messages: Vec<Message>, ) -> impl Stream<Item = Result<SSEvents, GatewayError>> + Send

Stream content generation directly using the backend SSE stream.

async fn list_models(&self) -> Result<Vec<ProviderModels>, GatewayError>

Lists available models from all providers

async fn list_models_by_provider( &self, provider: Provider, ) -> Result<ProviderModels, GatewayError>

Lists available models by a specific provider

async fn generate_content( &self, provider: Provider, model: &str, messages: Vec<Message>, ) -> Result<GenerateResponse, GatewayError>

Generates content using a specified model

async fn health_check(&self) -> Result<bool, GatewayError>

Checks if the API is available