neurocore.llm.provider.OpenAIProvider¶

class neurocore.llm.provider.OpenAIProvider(api_key: str = '', model: str = 'gpt-4o', *, base_url: str | None = None, provider_name: str = 'openai')¶

OpenAI provider using the openai SDK.

Also serves every OpenAI-compatible gateway (Ollama, vLLM, LM Studio, LocalAI, Together, Groq, Fireworks, OpenRouter, custom gateways) by passing base_url. provider_name reflects the configured backend so traces and requires_llm skills report the real provider.

property provider_name: str¶

property model: str¶

async complete(messages: list[LLMMessage], *, max_tokens: int = 8192, temperature: float = 1.0, system: str | None = None, **kwargs: Any) → LLMResponse¶

async stream(messages: list[LLMMessage], *, max_tokens: int = 8192, temperature: float = 1.0, system: str | None = None, **kwargs: Any) → collections.abc.AsyncIterator[str]¶