吴恩达提示词工程课程笔记

CJenny

已于 2025-01-09 17:44:06 修改

阅读量749

点赞数 16

分类专栏：人工智能文章标签：笔记 python prompt ai

于 2025-01-09 16:37:20 首次发布

本文链接：https://blog.youkuaiyun.com/weixin_43791406/article/details/145032870

版权

人工智能专栏收录该内容

6 篇文章

订阅专栏

一、Introduction

二、Guidelines

Principle1: 清晰（不一定是简短的）而具体的指令

Tactic1: 使用分隔符

Triple quotes: “”"
Triple backticks: ```
Triple dashes: —
Angle brackets:< >
XML tags: < tag></ tag>

Tactic2: 要求格式化输出

如输出HTLM、JSON等

Tactic3: 要求模型检查是否满足条件

检查任务是否满足假设条件
考虑潜在的边界条件

Tactic4: 少量训练提示

为模型提供成功执行的示例，然后再让模型执行任务

Principle2: 给模型思考时间

Tactic1: 指定步骤

Step1:
Step2:
Step3:
…
StepN:

Tactic2: 让模型在给出结论之前，先想办法给出解决方案

三、Iterative Prompt Development

提示开发是一个迭代过程。
迭代提示过程
Prompt guidelines:

Be clear and specific
Analyze why result does not give desired output
Refine the idea and prompt
Repeat

根据模型输出的结果不断修正完善提示词信息

Iterative Process

Try something
Analyze where the result does not give what you want
Clarify instructions, give more time to think
Refine prompts with a batch of examples(利用大量示例）

四、 Summarizing

概括客户的评论
生成面向指定客户的摘要，使生成的摘要更适用于业务中某个特定群体的需求
分别写多条评论的摘要
review_1 = ““xxxx””
…
reviews = [review_1, review_2, review_3, review_4]

五、Inferring

提取标签，提取名字，理解文本的情感

六、Transforming

将输入转换为不同的格式
让大模型输出不同格式的文本
正则表达式纠正拼写和语法

七、Expanding

将短文本通过LLM转换为长文本
语言模型的参数temperature：模型探索的程度和随机性

两个辅助函数

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"]


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"]

八、Chatbot

role

系统消息

聊天格式的设置
系统消息有助于在一定程度上设定助手的行为和角色，充当对话的高级指令。

上下文

与语言模型的每次对话都是独立的，这意味着让模型从前期的对话中引用内容，或者记住前期的对话内容，就需要在模型的输入中提供前期的交流内容，提供所有相关信息，以便模型在当前对话中有效地使用。

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)

点餐机器人

辅助函数

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)

提示将从下面建立的用户界面中收集，并追加到一个名为‘上下文（context）’的列表中。每次调用模型时，都会带上这个上下文。模型的响应也会被添加到上下文中

带用户界面（UI）的订单机器人

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