ChatGPT Prompt Engineering for Developers - (7) Expanding

DeepLearning.AI 강의 ChatGPT Prompt Engineering for Developers - Expanding 요약

 

https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/

ChatGPT Prompt Engineering for Developers

 

모델의 입력 파라미터인 temperature를 사용하여 탐색의 정도와 다양성을 모델의 응답에 적용

temperature가 0일 시 모델은 항상 가장 가능성이 높은 다음 단어를 선택

temperature가 높아질 수록 가능성이 덜 높은 단어 중 하나를 선택

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

 

 

자동 응답 커스터마이징

prompt = f"""
You are a customer service AI assistant.
Your task is to send an email reply to a valued customer.
Given the customer email delimited by ```, \
Generate a reply to thank the customer for their review.
If the sentiment is positive or neutral, thank them for \
their review.
If the sentiment is negative, apologize and suggest that \
they can reach out to customer service. 
Make sure to use specific details from the review.
Write in a concise and professional tone.
Sign the email as `AI customer agent`.
Customer review: ```{review}```
Review sentiment: {sentiment}
"""
response = get_completion(prompt)
print(response)

 

 

자동 응답 시 받은 텍스트의 세부 사항을 활용할 것을 지시

prompt = f"""
You are a customer service AI assistant.
Your task is to send an email reply to a valued customer.
Given the customer email delimited by ```, \
Generate a reply to thank the customer for their review.
If the sentiment is positive or neutral, thank them for \
their review.
If the sentiment is negative, apologize and suggest that \
they can reach out to customer service. 
Make sure to use specific details from the review.
Write in a concise and professional tone.
Sign the email as `AI customer agent`.
Customer review: ```{review}```
Review sentiment: {sentiment}
"""
response = get_completion(prompt, temperature=0.7)
print(response)