> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aurelio.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# semantic_router.llms.openai

## OpenAILLM Objects

```python theme={null}
class OpenAILLM(BaseLLM)
```

LLM for OpenAI. Requires an OpenAI API key from [https://platform.openai.com/api-keys](https://platform.openai.com/api-keys).

#### \_\_init\_\_

```python theme={null}
def __init__(name: Optional[str] = None,
             openai_api_key: Optional[str] = None,
             temperature: float = 0.01,
             max_tokens: int = 200)
```

Initialize the OpenAILLM.

**Arguments**:

* `name` (`Optional[str]`): The name of the OpenAI model to use.
* `openai_api_key` (`Optional[str]`): The OpenAI API key.
* `temperature` (`float`): The temperature of the LLM.
* `max_tokens` (`int`): The maximum number of tokens to generate.

#### async\_extract\_tool\_calls\_info

```python theme={null}
async def async_extract_tool_calls_info(
        tool_calls: List[ChatCompletionMessageToolCall]
) -> List[Dict[str, Any]]
```

Extract the tool calls information from the tool calls.

**Arguments**:

* `tool_calls` (`List[ChatCompletionMessageToolCall]`): The tool calls to extract the information from.

**Returns**:

`List[Dict[str, Any]]`: The tool calls information.

#### \_\_call\_\_

```python theme={null}
def __call__(messages: List[Message],
             function_schemas: Optional[List[Dict[str, Any]]] = None) -> str
```

Call the OpenAILLM.

**Arguments**:

* `messages` (`List[Message]`): The messages to pass to the OpenAILLM.
* `function_schemas` (`Optional[List[Dict[str, Any]]]`): The function schemas to pass to the OpenAILLM.

**Returns**:

`str`: The response from the OpenAILLM.

#### acall

```python theme={null}
async def acall(
        messages: List[Message],
        function_schemas: Optional[List[Dict[str, Any]]] = None) -> str
```

Call the OpenAILLM asynchronously.

**Arguments**:

* `messages` (`List[Message]`): The messages to pass to the OpenAILLM.
* `function_schemas` (`Optional[List[Dict[str, Any]]]`): The function schemas to pass to the OpenAILLM.

**Returns**:

`str`: The response from the OpenAILLM.

#### extract\_function\_inputs

```python theme={null}
def extract_function_inputs(
        query: str, function_schemas: List[Dict[str,
                                                Any]]) -> List[Dict[str, Any]]
```

Extract the function inputs from the query.

**Arguments**:

* `query` (`str`): The query to extract the function inputs from.
* `function_schemas` (`List[Dict[str, Any]]`): The function schemas to extract the function inputs from.

**Returns**:

`List[Dict[str, Any]]`: The function inputs.

#### async\_extract\_function\_inputs

```python theme={null}
async def async_extract_function_inputs(
        query: str, function_schemas: List[Dict[str,
                                                Any]]) -> List[Dict[str, Any]]
```

Extract the function inputs from the query asynchronously.

**Arguments**:

* `query` (`str`): The query to extract the function inputs from.
* `function_schemas` (`List[Dict[str, Any]]`): The function schemas to extract the function inputs from.

**Returns**:

`List[Dict[str, Any]]`: The function inputs.

#### get\_schemas\_openai

```python theme={null}
def get_schemas_openai(items: List[Callable]) -> List[Dict[str, Any]]
```

Get function schemas for the OpenAI LLM from a list of functions.

**Arguments**:

* `items` (`List[Callable]`): The functions to get function schemas for.

**Returns**:

`List[Dict[str, Any]]`: The schemas for the OpenAI LLM.