atoti_ai_openai.ChatConfig

final class atoti_ai_openai.ChatConfig

Chat config for OpenAI.

Warning

This feature is experimental, its key is "ai".

See the corresponding Javadoc for more details.

See also

The other ChatConfig implementations.

completions_path: str | None = None

The path to append to the base URL.

extra_body: Mapping[str, bool | int | float | str] | None = None

Additional parameters for OpenAI-compatible servers.

http_headers: Mapping[str, str] | None = None

Custom HTTP headers.

max_completion_tokens: int | None = None

Maximum number of tokens to generate for reasoning models (e.g. o1, o3).

Mutually exclusive with max_tokens.

max_tokens: int | None = None

Maximum number of tokens to generate in the response.

For non-reasoning models. Mutually exclusive with max_completion_tokens.

model: str

The ID of the model to use, for example "gpt-4o".

parallel_tool_calls: bool | None = None

Enable parallel function calling during tool use.

retry_backoff_initial_interval: timedelta | None = None

Initial sleep duration for the exponential backoff policy.

retry_backoff_max_interval: timedelta | None = None

Maximum backoff duration.

retry_max_attempts: int | None = None

Maximum number of retry attempts.

retry_on_client_errors: bool | None = None

If False, throw a NonTransientAiException and do not attempt retry for 4xx client error codes.

seed: int | None = None

Seed for deterministic sampling (Beta).

temperature: float | None = None

Controls randomness in responses from 0.0 (deterministic) to 2.0 (creative).

tool_choice: str | None = None

Tool/function calling behavior ("none", "auto", or a specific function name).

top_p: float | None = None

Nucleus sampling parameter.

Controls diversity via cumulative probability.