Struct OpenAiProvider 

pub struct OpenAiProvider { /* private fields */ }

Built-in provider for the OpenAI Chat Completions API.

Also compatible with Azure OpenAI and any OpenAI-compatible endpoint. Requires the openai feature flag.

Example

use llm_agent_runtime::providers::OpenAiProvider;
let provider = OpenAiProvider::new("sk-...");
// For Azure or custom endpoints:
let custom = OpenAiProvider::with_base_url("sk-...", "https://my-endpoint/v1");

Implementations

impl OpenAiProvider

pub fn new(api_key: impl Into<String>) -> Self

Create a new OpenAI provider with the default base URL.

pub fn with_base_url( api_key: impl Into<String>, base_url: impl Into<String>, ) -> Self

Create a provider pointing to a custom base URL (e.g. Azure, local models).

pub fn with_max_concurrent_streams( api_key: impl Into<String>, base_url: impl Into<String>, max: usize, ) -> Self

Create a provider with a custom limit on concurrent streaming tasks.

Trait Implementations

impl LlmProvider for OpenAiProvider

fn complete_with_options<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, options: CompletionOptions<'life2>, ) -> Pin<Box<dyn Future<Output = Result<String, AgentRuntimeError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Complete with per-request options (max_tokens, temperature, timeout).

Honours options.max_tokens and options.temperature when set, falling back to the API default when unset.

fn complete<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, model: &'life2 str, ) -> Pin<Box<dyn Future<Output = Result<String, AgentRuntimeError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Send a prompt to the model and return the completion text.

fn stream_complete<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, model: &'life2 str, ) -> Pin<Box<dyn Future<Output = Result<Receiver<Result<String, AgentRuntimeError>>, AgentRuntimeError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Stream the completion token-by-token.