Struct OpenAIProvider 

pub struct OpenAIProvider { /* private fields */ }

OpenAI API provider.

Also supports OpenAI-compatible APIs (Groq, Together, Fireworks, etc.) by specifying a custom base_url.

Also supports Azure OpenAI by specifying an AzureConfig.

Implementations

impl OpenAIProvider

pub fn new(api_key: String, model: String) -> Self

Create a new OpenAI provider with API key and model.

pub fn with_base_url(api_key: String, model: String, base_url: String) -> Self

Create a new OpenAI-compatible provider with a custom base URL.

Use this for providers like Groq, Together, Fireworks, etc. The base_url should be the API base (e.g., “https://api.groq.com/openai/v1”).

pub fn azure( api_key: String, resource: String, deployment: String, api_version: String, ) -> Self

Create a new Azure OpenAI provider.

Azure OpenAI uses a different URL format and authentication header. URL: https://{resource}.openai.azure.com/openai/deployments/{deployment}/chat/completions?api-version={version} Auth: api-key header instead of Authorization: Bearer

pub fn model(&self) -> &str

Returns the model identifier.

pub fn is_azure(&self) -> bool

Returns true if this provider is configured for Azure OpenAI.

Trait Implementations

impl LlmProvider for OpenAIProvider

fn send_msg( &self, client: &HttpClient, messages: &[Message], options: &MessageOptions, ) -> Pin<Box<dyn Future<Output = Result<Message, LlmError>> + Send>>

Send a message to the LLM. Returns the assistant’s response message or an error.

fn send_msg_stream( &self, client: &HttpClient, messages: &[Message], options: &MessageOptions, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<StreamEvent, LlmError>> + Send>>, LlmError>> + Send>>

Send a streaming message to the LLM. Returns a stream of events as they arrive from the API.