ChatGPT Prompt Engineering for Developers - (2) Guidelines

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

 

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

ChatGPT Prompt Engineering for Developers

Python 에 openAI 라이브러리 설치

pip install openai

 

https://platform.openai.com/account/api-keys 에서 계정의 secret key 설정 가능

 

 

openAI API key 로드

!export OPENAI_API_KEY='sk-...'

혹은

import openai
openai.api_key = "sk-..."

 

chat completions endpoint 함수

공식 문서: https://platform.openai.com/docs/guides/chat

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"]

 

 

 

효과적인 프롬프트 작성 원칙

1. 명확하고 구체적인 지시를 작성

2. 모델에게 생각할 시간을 줄 것

 

 

구체적 전략

1. 구분자(delimiters)를 사용해 입력 부분을 명확하게 구분

* delimiters: ```, """, <>, <tag></tag>, : 등

text = f"""
You should express what you want a model to do by \ 
providing instructions that are as clear and \ 
specific as you can possibly make them. \ 
This will guide the model towards the desired output, \ 
and reduce the chances of receiving irrelevant \ 
or incorrect responses. Don't confuse writing a \ 
clear prompt with writing a short prompt. \ 
In many cases, longer prompts provide more clarity \ 
and context for the model, which can lead to \ 
more detailed and relevant outputs.
"""
prompt = f"""
Summarize the text delimited by triple backticks \ 
into a single sentence.
```{text}```
"""
response = get_completion(prompt)
print(response)

 

2. 구조화된 출력 (json, html) 요청

prompt = f"""
Generate a list of three made-up book titles along \ 
with their authors and genres. 
Provide them in JSON format with the following keys: 
book_id, title, author, genre.
"""
response = get_completion(prompt)
print(response)

 

3. 주어진 조건을 만족하였는지 모델에게 체크 요청

text_1 = f"""
Making a cup of tea is easy! First, you need to get some \ 
water boiling. While that's happening, \ 
grab a cup and put a tea bag in it. Once the water is \ 
hot enough, just pour it over the tea bag. \ 
Let it sit for a bit so the tea can steep. After a \ 
few minutes, take out the tea bag. If you \ 
like, you can add some sugar or milk to taste. \ 
And that's it! You've got yourself a delicious \ 
cup of tea to enjoy.
"""
prompt = f"""
You will be provided with text delimited by triple quotes. 
If it contains a sequence of instructions, \ 
re-write those instructions in the following format:

Step 1 - ...
Step 2 - …
…
Step N - …

If the text does not contain a sequence of instructions, \ 
then simply write \"No steps provided.\"

\"\"\"{text_1}\"\"\"
"""
response = get_completion(prompt)
print("Completion for Text 1:")
print(response)

 

4. Few-Shots 프롬프팅

prompt = f"""
Your task is to answer in a consistent style.

<child>: Teach me about patience.

<grandparent>: The river that carves the deepest \ 
valley flows from a modest spring; the \ 
grandest symphony originates from a single note; \ 
the most intricate tapestry begins with a solitary thread.

<child>: Teach me about resilience.
"""
response = get_completion(prompt)
print(response)

 

모델에게 생각할 시간을 주기 위한 전략들

1. 주어진 과제를 완성하기 위해 필요한 단계들을 구체적으로 명시

text = f"""
In a charming village, siblings Jack and Jill set out on \ 
a quest to fetch water from a hilltop \ 
well. As they climbed, singing joyfully, misfortune \ 
struck—Jack tripped on a stone and tumbled \ 
down the hill, with Jill following suit. \ 
Though slightly battered, the pair returned home to \ 
comforting embraces. Despite the mishap, \ 
their adventurous spirits remained undimmed, and they \ 
continued exploring with delight.
"""
# example 1
prompt_1 = f"""
Perform the following actions: 
1 - Summarize the following text delimited by triple \
backticks with 1 sentence.
2 - Translate the summary into French.
3 - List each name in the French summary.
4 - Output a json object that contains the following \
keys: french_summary, num_names.

Separate your answers with line breaks.

Text:
```{text}```
"""
response = get_completion(prompt_1)
print("Completion for prompt 1:")
print(response)

 

- 지정된 형식으로 출력을 요청 

prompt_2 = f"""
Your task is to perform the following actions: 
1 - Summarize the following text delimited by 
  <> with 1 sentence.
2 - Translate the summary into French.
3 - List each name in the French summary.
4 - Output a json object that contains the 
  following keys: french_summary, num_names.

Use the following format:
Text: <text to summarize>
Summary: <summary>
Translation: <summary translation>
Names: <list of names in Italian summary>
Output JSON: <json with summary and num_names>

Text: <{text}>
"""
response = get_completion(prompt_2)
print("\nCompletion for prompt 2:")
print(response)

 

2. 성급히 결론을 내기 전에 모델이 자체적인 해결책을 마련하도록 지시

prompt = f"""
Determine if the student's solution is correct or not.

Question:
I'm building a solar power installation and I need \
 help working out the financials. 
- Land costs $100 / square foot
- I can buy solar panels for $250 / square foot
- I negotiated a contract for maintenance that will cost \ 
me a flat $100k per year, and an additional $10 / square \
foot
What is the total cost for the first year of operations 
as a function of the number of square feet.

Student's Solution:
Let x be the size of the installation in square feet.
Costs:
1. Land cost: 100x
2. Solar panel cost: 250x
3. Maintenance cost: 100,000 + 100x
Total cost: 100x + 250x + 100,000 + 100x = 450x + 100,000
"""
response = get_completion(prompt)
print(response)

 

모델의 한계: 환영 현상(Hallucinations)

- LLM은 잘 알려지지 않은 주제에 대한 질문에 답변을 시도 혹은 그럴듯하게 들리지만 실제로는 사실이 아닌 것을 만들어낼 수도 있음

 

환영 현상을 줄이는 추가 전략

- 모델에게 텍스트에서 관련된 인용구를 찾게 하고 이를 사용하여 질문에 답하도록 요청, 답변을 원문에서 추적