ChatGPT 프롬프트 엔지니어링 가이드 - 下

1편에서는 프롬프트 엔지니어링에 대한 원칙 및 사용 시 주의해야 할 부분에 대해서 다뤘습니다. 

2023.07.31 - [💻 코딩·개발·분석] - ChatGPT 프롬프트 엔지니어링 가이드 - 上

ChatGPT 프롬프트 엔지니어링 가이드 - 上

>> 수강 링크 <<

 

 

나머지 부분에서는 요약, 추론, 변환, 확장, 챗봇 개발 등 어떻게 ChatGPT를 활용할 수 있는지에 대한 내용을 다뤘습니다. 

---

Python Notebook 다운로드

ChatGPT-Prompt-Eng.zip

0.04MB

---

핵심 내용 요약정리 (Key Takeaways)

 

요약 (Summarizing)

• 단어, 문장, 글자수를 제한하여 원하는 길이의 결과값을 얻는다.
• 특정 부분에 집중하도록 프롬프트를 작성한다.
• "요약 (Summarize)" 대신에 "추출 (Extract)"이라는 용어를 사용해 본다

 

추론 (Inferring)

• 감성 분석 (Sentiment Analysis), 엔티티추출 (NER), 토픽 등의 자연어처리 수행
• 한 번에 다양한 종류의 라벨 또한 추출 가능
• 특정 토픽이 출현했을 때 알림을 줄 수도 있음

 

변환 (Transforming)

• 다양한 언어로 번역 가능
• 언어의 톤, 형식, 문법 체크 등이 가능함

 

확장 (Expanding)

• ChatGPT API의 Temperature 파라미터 조정으로 창의적인 답변을 유도할 수 있음 (일관성은 떨어짐)
• 위의 내용을 바탕으로 고객에게 자동으로 답변해 주는 이메일을 작성하는 AI봇 생성
• "AI가 작성했다"는 고지를 하는 것을 권고

일관성을 원한다면 Temperature을 0으로 , 창의적인 답변을 원하면 1에 가깝게 설정

 

 

챗봇 (Chatbot)

• 챗봇 형태로 사용을 하기 위해서는 대화 내용을 저장한 형태의 리스트를 제공해야 함
• ex) messages =  [  
  {'role':'system', 'content':'You are an assistant that speaks like Shakespeare.'},    
  {'role':'user', 'content':'tell me a joke'},   
  {'role':'assistant', 'content':'Why did the chicken cross the road'},   
  {'role':'user', 'content':'I don\'t know'}  ]

 

---

강의 노트 (프롬프트 예시)

강의 중에 다뤄진 대표적인 프롬프트 양식을 가져왔습니다. 

 

4. Summarizing 

prod_review = """
Got this panda plush toy for my daughter's birthday, \
who loves it and takes it everywhere. It's soft and \ 
super cute, and its face has a friendly look. It's \ 
a bit small for what I paid though. I think there \ 
might be other options that are bigger for the \ 
same price. It arrived a day earlier than expected, \ 
so I got to play with it myself before I gave it \ 
to her.
"""

# 글자수를 30자로 지정
prompt = f"""
Your task is to generate a short summary of a product \
review from an ecommerce site. 

Summarize the review below, delimited by triple 
backticks, in at most 30 words. 

Review: ```{prod_review}```
"""


# 가격과 값어치에 대한 내용을 중점적으로 요약
prompt = f"""
Your task is to generate a short summary of a product \
review from an ecommerce site to give feedback to the \
pricing deparmtment, responsible for determining the \
price of the product.  

Summarize the review below, delimited by triple 
backticks, in at most 30 words, and focusing on any aspects \
that are relevant to the price and perceived value. 

Review: ```{prod_review}```
"""

# "요약" 대신 "추출"이라는 단어를 대신 사용
prompt = f"""
Your task is to extract relevant information from \ 
a product review from an ecommerce site to give \
feedback to the Shipping department. 

From the review below, delimited by triple quotes \
extract the information relevant to shipping and \ 
delivery. Limit to 30 words. 

Review: ```{prod_review}```
"""

 

 

5. Inferring

lamp_review = """
Needed a nice lamp for my bedroom, and this one had \
additional storage and not too high of a price point. \
Got it fast.  The string to our lamp broke during the \
transit and the company happily sent over a new one. \
Came within a few days as well. It was easy to put \
together.  I had a missing part, so I contacted their \
support and they very quickly got me the missing piece! \
Lumina seems to me to be a great company that cares \
about their customers and products!!
"""

# 긍정-부정 여부 체크
prompt = f"""
What is the sentiment of the following product review, 
which is delimited with triple backticks?

Give your answer as a single word, either "positive" \
or "negative".

Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)


# 리뷰에서 제품, 회사명 추출 (NER)
prompt = f"""
Identify the following items from the review text: 
- Item purchased by reviewer
- Company that made the item

The review is delimited with triple backticks. \
Format your response as a JSON object with \
"Item" and "Brand" as the keys. 
If the information isn't present, use "unknown" \
as the value.
Make your response as short as possible.
  
Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)



# 토픽 추출하기 
story = """
In a recent survey conducted by the government, 
public sector employees were asked to rate their level 
of satisfaction with the department they work at. 
The results revealed that NASA was the most popular 
department with a satisfaction rating of 95%.

One NASA employee, John Smith, commented on the findings, 
stating, "I'm not surprised that NASA came out on top. 
It's a great place to work with amazing people and 
incredible opportunities. I'm proud to be a part of 
such an innovative organization."

The results were also welcomed by NASA's management team, 
with Director Tom Johnson stating, "We are thrilled to 
hear that our employees are satisfied with their work at NASA. 
We have a talented and dedicated team who work tirelessly 
to achieve our goals, and it's fantastic to see that their 
hard work is paying off."

The survey also revealed that the 
Social Security Administration had the lowest satisfaction 
rating, with only 45% of employees indicating they were 
satisfied with their job. The government has pledged to 
address the concerns raised by employees in the survey and 
work towards improving job satisfaction across all departments.
"""

prompt = f"""
Determine five topics that are being discussed in the \
following text, which is delimited by triple backticks.

Make each item one or two words long. 

Format your response as a list of items separated by commas.

Text sample: '''{story}'''
"""
response = get_completion(prompt)
print(response)

 

6. Transforming

# 기본 번역 (다국어 지원)
prompt = f"""
Translate the following English text to Spanish: \ 
```Hi, I would like to order a blender```
"""
response = get_completion(prompt)
print(response)


# 톤 변환 
prompt = f"""
Translate the following from slang to a business letter: 
'Dude, This is Joe, check out this spec on this standing lamp.'
"""
response = get_completion(prompt)
print(response)


# 출력 포맷 변환 (HTML로 변환)
data_json = { "resturant employees" :[ 
    {"name":"Shyam", "email":"shyamjaiswal@gmail.com"},
    {"name":"Bob", "email":"bob32@gmail.com"},
    {"name":"Jai", "email":"jai87@gmail.com"}
]}

prompt = f"""
Translate the following python dictionary from JSON to an HTML \
table with column headers and title: {data_json}
"""


# 맞춤법 및 문법 체크
text = [ 
  "The girl with the black and white puppies have a ball.",  # The girl has a ball.
  "Yolanda has her notebook.", # ok
  "Its going to be a long day. Does the car need it’s oil changed?",  # Homonyms
  "Their goes my freedom. There going to bring they’re suitcases.",  # Homonyms
  "Your going to need you’re notebook.",  # Homonyms
  "That medicine effects my ability to sleep. Have you heard of the butterfly affect?", # Homonyms
  "This phrase is to cherck chatGPT for speling abilitty"  # spelling
]
for t in text:
    prompt = f"""Proofread and correct the following text
    and rewrite the corrected version. If you don't find
    and errors, just say "No errors found". Don't use 
    any punctuation around the text:
    ```{t}```"""
    response = get_completion(prompt)
    print(response)

 

 

7. Expanding 

# 고객의 리뷰에 자동으로 답장을 하는 AI 답변 생성하기

sentiment = "negative"

# review for a blender
review = f"""
So, they still had the 17 piece system on seasonal \
sale for around $49 in the month of November, about \
half off, but for some reason (call it price gouging) \
around the second week of December the prices all went \
up to about anywhere from between $70-$89 for the same \
system. And the 11 piece system went up around $10 or \
so in price also from the earlier sale price of $29. \
So it looks okay, but if you look at the base, the part \
where the blade locks into place doesn’t look as good \
as in previous editions from a few years ago, but I \
plan to be very gentle with it (example, I crush \
very hard items like beans, ice, rice, etc. in the \ 
blender first then pulverize them in the serving size \
I want in the blender then switch to the whipping \
blade for a finer flour, and use the cross cutting blade \
first when making smoothies, then use the flat blade \
if I need them finer/less pulpy). Special tip when making \
smoothies, finely cut and freeze the fruits and \
vegetables (if using spinach-lightly stew soften the \ 
spinach then freeze until ready for use-and if making \
sorbet, use a small to medium sized food processor) \ 
that you plan to use that way you can avoid adding so \
much ice if at all-when making your smoothie. \
After about a year, the motor was making a funny noise. \
I called customer service but the warranty expired \
already, so I had to buy another one. FYI: The overall \
quality has gone done in these types of products, so \
they are kind of counting on brand recognition and \
consumer loyalty to maintain sales. Got it in about \
two days.
"""

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)