Struct OpenAiProvider 

pub struct OpenAiProvider {
    pub id: String,
    pub base_url: String,
    pub api_key_env: Option<String>,
    pub http: Client,
}

Speaks POST {base}/v1/chat/completions (OpenAI Chat Completions API).

Fields

id: String

Ladder prefix / trace label for this provider ("openai", "groq", "together", …).

base_url: String

Base URL, e.g. https://api.openai.com or https://api.groq.com/openai.

api_key_env: Option<String>

Env var the API key is read from, e.g. "GROQ_API_KEY". None for the built-in openai provider (resolves via Auth: authorization header or OPENAI_API_KEY) and for keyless local endpoints (Ollama / vLLM).

http: Client

Shared, connection-pooled HTTP client.

Trait Implementations

impl Clone for OpenAiProvider

fn clone(&self) -> OpenAiProvider

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OpenAiProvider

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

Formats the value using the given formatter.

impl Provider for OpenAiProvider

fn id(&self) -> &str

Provider identity, e.g. "anthropic".

fn complete<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, req: &'life1 ModelRequest, auth: &'life2 Auth, ) -> Pin<Box<dyn Future<Output = Result<ModelResponse, ProviderError>> + Send + 'async_trait>>

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

Call the model and normalize the result.