【Prompting】ChatGPT Prompt Engineering开发指南（6）

在本教程中，第一部分学习生成客户服务电子邮件，这些电子邮件是根据每个客户的评论量身定制的。第二部分将探索如何利用聊天格式与针对特定任务或行为进行个性化或专门化的聊天机器人进行扩展对话。

注意：基本环境设置与前文保持一致，请参考设置。这里适当修改一下get_completion()函数：

@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
def get_completion(prompt, model="gpt-3.5-turbo", temperature = 0):
    messages = [{'role': 'user', 'content': prompt}]
    response = openai.ChatCompletion.create(
        model=model,
        messages=messages,
        max_tokens=1024,
        n=1,
        temperature=temperature,  # this is the degree of randomness of the model's output
        stop=None,
        top_p=1,
        frequency_penalty=0.0,
        presence_penalty=0.6,
    )
    return response['choices'][0]['message']['content']

Expanding

自定义对客户电子邮件的自动回复

# given the sentiment from the lesson on "inferring",
# and the original customer message, customize the email
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.
"""

生成回复：

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)

提醒模型使用客户电子邮件中的详细信息

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)

The Chat Format

新增一个函数，从回复的消息中补全信息：

@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
def get_completion_from_messages(messages, model="gpt-3.5-turbo", temperature=0):
    response = openai.ChatCompletion.create(
        model=model,
        messages=messages,
        temperature=temperature, # this is the degree of randomness of the model's output
    )
#     print(str(response.choices[0].message))
    return response.choices[0]['message']['content']

开始聊天：

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'}  ]

response = get_completion_from_messages(messages, temperature=1)
print(response)

回答：

To get to the other side, good sir!

messages =  [
{'role':'system', 'content':'You are friendly chatbot.'},
{'role':'user', 'content':'Hi, my name is Isa'}  ]
response = get_completion_from_messages(messages, temperature=1)
print(response)

回答：

Hi Isa! It's nice to meet you. How are you feeling today?

messages =  [
{'role':'system', 'content':'You are friendly chatbot.'},
{'role':'user', 'content':'Yes,  can you remind me, What is my name?'}  ]
response = get_completion_from_messages(messages, temperature=1)
print(response)

回答：

I apologize, but as a chatbot, I do not have access to your personal information such as your name. Can you please remind me?

messages =  [
{'role':'system', 'content':'You are friendly chatbot.'},
{'role':'user', 'content':'Hi, my name is Isa'},
{'role':'assistant', 'content': "Hi Isa! It's nice to meet you. \
Is there anything I can help you with today?"},
{'role':'user', 'content':'Yes, you can remind me, What is my name?'}  ]
response = get_completion_from_messages(messages, temperature=1)
print(response)

回答：

Your name is Isa.

订单机器人：我们可以自动化用户提示和助手响应的收集以构建订单机器人。Orderbot将在比萨餐厅接受订单。

def collect_messages(_):
    prompt = inp.value_input
    inp.value = ''
    context.append({'role':'user', 'content':f"{prompt}"})
    response = get_completion_from_messages(context)
    context.append({'role':'assistant', 'content':f"{response}"})
    panels.append(
        pn.Row('User:', pn.pane.Markdown(prompt, width=600)))
    panels.append(
        pn.Row('Assistant:', pn.pane.Markdown(response, width=600, style={'background-color': '#F6F6F6'})))

    return pn.Column(*panels)

绘制面板：

import panel as pn  # GUI
pn.extension()

panels = [] # collect display

context = [ {'role':'system', 'content':"""
You are OrderBot, an automated service to collect orders for a pizza restaurant. \
You first greet the customer, then collects the order, \
and then asks if it's a pickup or delivery. \
You wait to collect the entire order, then summarize it and check for a final \
time if the customer wants to add anything else. \
If it's a delivery, you ask for an address. \
Finally you collect the payment.\
Make sure to clarify all options, extras and sizes to uniquely \
identify the item from the menu.\
You respond in a short, very conversational friendly style. \
The menu includes \
pepperoni pizza  12.95, 10.00, 7.00 \
cheese pizza   10.95, 9.25, 6.50 \
eggplant pizza   11.95, 9.75, 6.75 \
fries 4.50, 3.50 \
greek salad 7.25 \
Toppings: \
extra cheese 2.00, \
mushrooms 1.50 \
sausage 3.00 \
canadian bacon 3.50 \
AI sauce 1.50 \
peppers 1.00 \
Drinks: \
coke 3.00, 2.00, 1.00 \
sprite 3.00, 2.00, 1.00 \
bottled water 5.00 \
"""} ]  # accumulate messages


inp = pn.widgets.TextInput(value="Hi", placeholder='Enter text here…')
button_conversation = pn.widgets.Button(name="Chat!")

interactive_conversation = pn.bind(collect_messages, button_conversation)

dashboard = pn.Column(
    inp,
    pn.Row(button_conversation),
    pn.panel(interactive_conversation, loading_indicator=True, height=300),
)

dashboard

messages =  context.copy()
messages.append(
{'role':'system', 'content':'create a json summary of the previous food order. Itemize the price for each item\
 The fields should be 1) pizza, include size 2) list of toppings 3) list of drinks, include size   4) list of sides include size  5)total price '},
)
 #The fields should be 1) pizza, price 2) list of toppings 3) list of drinks, include size include price  4) list of sides include size include price, 5)total price '},

response = get_completion_from_messages(messages, temperature=0)
print(response)

总结

• Principles:
  • Write clear and specific instructions
  • Give the model time to “think”
• Iterative prompt development
• Capabilitis: Summarizing, Inferring, Transforming, Expanding
• Building a ChatBot

内容来源

1. DeepLearning.AI: 《ChatGPT Prompt Engineering for Developers》