text_completions

See the litellm documention.

Text completions generate a continuation of a single prompt string, making them ideal for tasks like autocomplete, code completion, or single-turn text generation. This is contrast to chat completions, which are meant for multi-turn conversations, where the input is a list of messages with roles (like “user” and “assistant”), allowing the model to maintain context and produce more coherent, context-aware responses across multiple exchanges. Use text completions for simple, stateless tasks, and chat completions for interactive, context-dependent scenarios.

text_completion

text_completion(
   *args,
   cache_enabled: bool,
   cache_path: typing.Union[str, pathlib.Path, NoneType],
   cache_key_prefix: typing.Optional[str],
   include_model_in_cache_key: bool,
   return_cache_key: bool,
   enable_retries: bool,
   retry_on_exceptions: typing.Optional[list[Exception]],
   retry_on_all_exceptions: bool,
   max_retries: typing.Optional[int],
   retry_delay: typing.Optional[int],
   **kwargs
)

This function is a wrapper around a corresponding function in the litellm library, see this for a full list of the available arguments.

---

response = text_completion(
    model="gpt-4o-mini",
    prompt="1 + 1 = ",
)
response.choices[0].text

'1 + 1 = 2.'

async_text_completion (async)

async_text_completion(
   *args,
   cache_enabled: bool,
   cache_path: typing.Union[str, pathlib.Path, NoneType],
   cache_key_prefix: typing.Optional[str],
   include_model_in_cache_key: bool,
   return_cache_key: bool,
   enable_retries: bool,
   retry_on_exceptions: typing.Optional[list[Exception]],
   retry_on_all_exceptions: bool,
   max_retries: typing.Optional[int],
   retry_delay: typing.Optional[int],
   timeout: typing.Optional[int],
   **kwargs
)

---

response = await async_text_completion(
    model="gpt-4o-mini",
    prompt="1 + 2 = ",
)
response.choices[0].text

'1 + 2 = 3.'