[LLM] ChatGPT Prompt Engineering for Developers - Chatbot

ChatGPT Prompt Engineering for Developers

 

ChatGPT Prompt Engineering for Developers 

 

7 - Chatbot  정리

 

Setup

import openai

def get_completion(prompt, model="gpt-3.5-turbo"):
    messages = [{"role": "user", "content": prompt}]
    response = openai.ChatCompletion.create(
        model=model,
        messages=messages,
        temperature=0, # this is the degree of randomness of the model's output
    )
    return response.choices[0].message["content"]

def get_completion_from_messages(messages, model="gpt-3.5-turbo", temperature=0):
    response = openai.ChatCompletion.create(
        model=model,
        messages=messages,
        temperature=temperature, # this is the degree of randomness of the model's output
    )
    print(str(response.choices[0].message))
    return response.choices[0].message["content"]

 

Chatbot 

messages - role

 

 

system : ChatGPT가 행동할 작업 명시 

assistant : system 기반 ChatGPT model

user : "나"

 

 

<Message List>

 

** 널리 알려진 농을 셰익스피어 풍으로 바꿔 보자 

 

 

messages =  [  
{'role':'system', 'content':'셰익스피어의 풍으로 농담을 만들어주는 게 너의 일이야.'},    
{'role':'user', 'content':'농담 하나 해줘'},   
{'role':'assistant', 'content':'닭이 왜 길을 건넌 줄 알아?'},   
{'role':'user', 'content':'모르겠는데?'}  ]

response = get_completion_from_messages(messages, temperature=1)
print(response)