DeepLearning.AIとOpenAIが公開したChatGPT Prompt Engineering（5-変換、拡大）

はじめに

ChatGPT Prompt Engineeringを受講したメモです。
全体の目次はこちらをご覧ください。
https://zenn.dev/aerialstairs/articles/aaf5aa9e42c65e

今回は、変換（Transforming）と拡大（Expanding）です。
翻訳、口調の変換、フォーマットの変換が紹介されています。
翻訳などはもちろんですが、フォーマットの変換も便利ですね。
Redlinesの差分表示は知らなかったので勉強になりました。
拡大は、temperatureをあげて、バリエーションをだす方法です。

翻訳

スペイン語に翻訳

prompt = f"""
Translate the following English text to Spanish: \ 
```Hi, I would like to order a blender```
"""

言語を推測

prompt = f"""
Tell me which language this is: 
```Combien coûte le lampadaire?```
"""

複数言語出力

prompt = f"""
Translate the following  text to French and Spanish
and English pirate: \
```I want to order a basketball```
"""

フォーマルと日常的な言い回し

prompt = f"""
Translate the following text to Spanish in both the \
formal and informal forms: 
'Would you like to order a pillow?'
"""

複数の言語をまとめて翻訳

user_messages = [
  "La performance du système est plus lente que d'habitude.",  # System performance is slower than normal         
  "Mi monitor tiene píxeles que no se iluminan.",              # My monitor has pixels that are not lighting
  "Il mio mouse non funziona",                                 # My mouse is not working
  "Mój klawisz Ctrl jest zepsuty",                             # My keyboard has a broken control key
  "我的屏幕在闪烁"                                               # My screen is flashing
] 

for issue in user_messages:
    prompt = f"Tell me what language this is: ```{issue}```"
    lang = get_completion(prompt)
    print(f"Original message ({lang}): {issue}")

    prompt = f"""
    Translate the following  text to English \
    and Korean: ```{issue}```
    """
    response = get_completion(prompt)
    print(response, "\n")

口調の変換

スラングからフォーマルへの変換です。

prompt = f"""
Translate the following from slang to a business letter: 
'Dude, This is Joe, check out this spec on this standing lamp.'
"""

フォーマットの変換

JsonからHtml

data_json = { "resturant employees" :[ 
    {"name":"Shyam", "email":"[e-mail]"},
    {"name":"Bob", "email":"[e-mail]"},
    {"name":"Jai", "email":"[e-mail]"}
]}

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

出力

<table>
  <caption>Restaurant Employees</caption>
  <thead>
    <tr>
      <th>Name</th>
      <th>Email</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td>Shyam</td>
      <td>[e-mail]</td>
    </tr>
    <tr>
      <td>Bob</td>
      <td>[e-mail]</td>
    </tr>
    <tr>
      <td>Jai</td>
      <td>[e-mail]</td>
    </tr>
  </tbody>
</table>

HTML表示

from IPython.display import display, HTML
display(HTML(response))

校正と修正

校正と修正は以下のプロンプトで行えます。

prompt = f"proofread and correct this review: ```{text}```"

条件わけ

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}```"""

修正との差分を表示

Redlinesを使って、修正した文章との差分を表示しています。

from IPython.display import display, Markdown
from redlines import Redlines

diff = Redlines(text,response)
display(Markdown(diff.output_markdown))

拡大

0だと決まった返答になり、1に近づくほど、バリエーションがでます。
下のE-mailの返信例は、temperatureが0.7なので、毎回違うメッセージを返しやすくなっています。

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)