from openai import OpenAI def chat_completion( user_prompt: str, model_name: str = "phi4", temperature: float = 0.01, top_p: float = 0.99, ): """ Generates a response from a language model specialized in quantum computing. Args: user_prompt (str): The input prompt provided by the user. model_name (str, optional): The name of the language model to use. Defaults to "phi4". temperature (float, optional): The sampling temperature for response generation, controlling randomness. Defaults to 0.01. top_p (float, optional): The nucleus sampling parameter, determining the probability mass for token selection. Defaults to 0.99. Returns: str: The generated response from the language model. """ client = OpenAI( base_url="http://localhost:11434/v1", api_key="ollama", # Required but ignored ) response = client.chat.completions.create( messages=[ {"role": "system", "content": "You are a quantum computing expert."}, { "role": "user", "content": user_prompt, }, ], temperature=temperature, top_p=top_p, model=model_name, stream=True, # Stream for prevent connection timeout for long response requests ) final_answer = "" for chunk in response: if chunk.choices and chunk.choices[0].delta: final_answer += chunk.choices[0].delta.content return final_answer if __name__ == "__main__": print(chat_completion(user_prompt="Who are you in a sentence", model_name="phi4")) print( chat_completion(user_prompt="Who are you in sentence", model_name="qwen2.5:14b") )