Llms

openai_call(prompt, use_gpt4=False, temperature=0.5, max_tokens=100)

Calls OpenAI API to generate a response to a given prompt.

Parameters:

Name	Type	Description	Default
prompt	str	The prompt to generate a response to.	required
use_gpt4	bool	Whether to use GPT-4 or GPT-3.5. Defaults to False.	False
temperature	float	The temperature of the response. Defaults to 0.5.	0.5
max_tokens	int	The maximum number of tokens to generate. Defaults to 100.	100

Returns:

Name	Type	Description
str		The generated response.

Examples:

>>> openai_call("Hello, how are you?")
"I'm doing great, thanks for asking!"

Notes

The OpenAI API key must be set in the environment variable OPENAI_API_KEY.

Source code in autoresearcher/llms/openai.py

def openai_call(
    prompt: str, use_gpt4: bool = False, temperature: float = 0.5, max_tokens: int = 100
):
    """
    Calls OpenAI API to generate a response to a given prompt.
    Args:
      prompt (str): The prompt to generate a response to.
      use_gpt4 (bool, optional): Whether to use GPT-4 or GPT-3.5. Defaults to False.
      temperature (float, optional): The temperature of the response. Defaults to 0.5.
      max_tokens (int, optional): The maximum number of tokens to generate. Defaults to 100.
    Returns:
      str: The generated response.
    Examples:
      >>> openai_call("Hello, how are you?")
      "I'm doing great, thanks for asking!"
    Notes:
      The OpenAI API key must be set in the environment variable OPENAI_API_KEY.
    """
    if not use_gpt4:
        # Call GPT-3.5 turbo model
        messages = [{"role": "user", "content": prompt}]
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=messages,
            temperature=temperature,
            max_tokens=max_tokens,
            top_p=1,
            frequency_penalty=0,
            presence_penalty=0,
        )
        return response.choices[0].message.content.strip()
    else:
        # Call GPT-4 chat model
        messages = [{"role": "user", "content": prompt}]
        response = openai.ChatCompletion.create(
            model="gpt-4",
            messages=messages,
            temperature=temperature,
            max_tokens=max_tokens,
            n=1,
            stop=None,
        )
        return response.choices[0].message.content.strip()