AI說書 - 從0開始 - 450 | Auto-Big-Bench 定義 GPT 回答函數

我想要一天分享一點「LLM從底層堆疊的技術」，並且每篇文章長度控制在三分鐘以內，讓大家不會壓力太大，但是又能夠每天成長一點。

client = OpenAI()
gptmodel = "gpt-4"

def openai_chat(input_text):
	response = openai.ChatCompletion.create(model = gptmodel,
	                                        messages = [{"role": "system", "content": "You are an expert Natural Language Processing exercise expert."},
	                                                    {"role": "assistant", "content": "1.You can explain any NLP task. 2.Create an example 3.Solve the example"},
	                                                    {"role": "user", "content": input_text}],
	                                        temperature = 0.1)
	return response.choices[0].message.content