ai-agents-llm-configuration-autogpt-only-supports-gpt-4-via-hardcoded-model-in-8f352c89

THEN Modify call_ai_function to read a chosen model from a config file (e.g., config.ini) and use conditional logic to call different AI APIs based on the model value. Replace the hardcoded model with a config-driven approach to support multiple backends.

import configparser

def call_ai_function(function, args, description, config_path="config.ini"):
    config = configparser.ConfigParser()
    config.read(config_path)
    model = config.get("AI", "Chosen_Model", fallback="gpt-4")
    args_str = ", ".join(args)
    messages = [
        {"role": "system", "content": f"You are now the following python function: ```# {description}\n{function}```\n\nOnly respond with your `return` value."},
        {"role": "user", "content": args_str}
    ]
    if model == "gpt-4":
        response = openai.ChatCompletion.create(model=model, messages=messages, temperature=0)
    elif model == "some_other_api":
        response = some_other_api_call(parameters)
    else:
        raise ValueError(f"Unsupported model: {model}")
    return response.choices[0].message["content"]