面向开发人员的 ChatGPT 提示工程 lesson5 inferring

你可以从本文了解到

产品评论文字

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!!
"""

情绪（正面/负面）

prompt = f"""
以下产品评论的情感是什么、 
用三条反斜线划定界限？

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

# Positive

prompt = f"""
以下产品评论的情感是什么、 
用三条反斜线划定界限？

请用一个词来回答，可以是 "正面 "或 "负面"。
或 "负面"。

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

识别情绪类型

prompt = f"""
确定以下评论的作者所表达的情绪的清单。包括不超过 
列表中的五个项目。你的答案的格式为 
用逗号隔开的小写词语。

Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)
satisfied, grateful, impressed, content, pleased

识别愤怒

prompt = f"""
以下评论的作者是在表达愤怒吗？
该评论用三个反斜线划定。
请给出您的答案，是或不是。

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

从客户评论中提取产品和公司名称

prompt = f"""
从评论文本中找出以下物品： 
- 评论者购买的物品
- 制造该物品的公司

该评论以三条反斜线为界。
将你的响应格式化为一个JSON对象，以 
"Item "和 "Brand "为键。
如果信息不存在，使用 "未知 "作为值。
作为值。
使你的响应尽可能的短。
  
Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)

# {
#   "Item": "lamp with additional storage",
#   "Brand": "Lumina"
# }

一次执行多个任务

prompt = f"""
从评论文本中找出以下物品： 
- 情绪（积极或消极）
- 评论者是否在表达愤怒？(真或假)
- 评论者购买的物品
- 制造该物品的公司

评论以三条反斜线为界。
将您的回复格式化为JSON对象，其中包括 
"Sentiment", "Anger", "Item "和 "Brand "作为键。
如果这些信息不存在，请使用 "未知"。
作为值。
使你的回答尽可能简短。
将 "愤怒 "的值格式化为一个布尔值。

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

# {
#   "Sentiment": "积极",
#   "Anger": false,
#   "Item": "灯",
#   "Brand": "Lumina"
# }

推断主题

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.
"""

推断 5 个主题

prompt = f"""
确定在以下文本中讨论的五个主题。
下面的文字是由三个反斜线划定的。

使每个项目有一到两个字的长度。

将你的回答格式化为由逗号分隔的项目清单。

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

# 主题清单：
# - 调查公共部门员工的满意度
# - NASA是最受欢迎的部门
# - NASA员工对工作的评价
# - 社会保障管理局的满意度最低
# - 政府承诺改善所有部门的工作满意度

对某些主题进行新闻提醒

response.split(sep=',')
# ['主题清单：\n- 调查公共部门员工的满意度\n- NASA是最受欢迎的部门\n- NASA员工对工作的评价\n- 社会保障管理局的满意度最低\n- 政府承诺改善所有部门的工作满意度']

topic_list = [
    "nasa", "local government", "engineering", 
    "employee satisfaction", "federal government"
]

prompt = f"""
判断以下列表中的每个项目是否是以下文本中的一个主题？
中的每一项是否是下面文本中的一个主题，该文本
是用三条反斜线划定的。

请以列表的形式给出你的答案，每个主题的答案为0或1。

List of topics: {", ".join(topic_list)}

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

# nasa: 1
# local government: 0
# engineering: 0
# employee satisfaction: 1
# federal government: 1

topic_dict = {i.split(': ')[0]: int(i.split(': ')[1]) for i in response.split(sep='\n')}
if topic_dict['nasa'] == 1:
    print("ALERT: New NASA story!")

# ALERT: New NASA story!