大模型提示词工程实践:大模型提示工程实践

原创 已于 2025-08-10 16:34:49 修改 · 1.2k 阅读 · 30 ·
CC 4.0 BY-SA版权
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
文章标签：

#大模型 #语言模型 #python

于 2025-08-10 13:44:41 首次发布

提示词编写指南

学习目标

通过本课程，你将了解到在大模型的使用中，提示词撰写的原则和相关策略。通过编写有效的提示词内容来提高大模型的使用效率。

相关知识点

  • 提示词编写

学习内容

1 提示词编写

提示词是与大模型进行交互的关键部分，编写有效的提示词对于获得准确、有用的结果至关重要。

提示词用于向大模型传达任务要求和相关信息，引导模型生成符合期望的输出。它就像是给模型的 “指令”，告诉模型需要做什么，以及在生成回答时应考虑哪些因素。

以下是常见的类型：

  • 问答型提示词：用于向模型提出问题，获取相关答案。例如，“地球的直径是多少？”“什么是量子力学？”。编写这类提示词时，要确保问题表述准确，避免过于宽泛或复杂的问题。

  • 生成型提示词：要求模型生成文本内容，如文章、故事、诗歌等。例如，“以‘春天的花园’为主题，写一首五言绝句”。在编写时，要明确生成内容的主题、体裁、风格等要求。

  • 分析型提示词：让模型对给定的文本、事件或现象进行分析。比如，“分析一下这部电影的剧情结构和人物塑造”。此类提示词需要明确分析的对象和具体的分析维度。

  • 指令型提示词：指示模型执行特定的操作或任务，如 “将这段文字翻译成英文”“对这段代码进行优化”。编写时要清晰说明操作要求和相关细节。

1.1 依赖环境安装
%pip install openai
1.2 加载大模型

通过openai的接口实例化一个deepseek模型的对象。

import os
import httpx
from openai import OpenAI


# 此课程基于DeepSeek-R1运行，学员可自行前往官网进行api申请
client = OpenAI(
    base_url=<BASE_URL>,
    api_key=<API_KEY>,
    http_client=httpx.Client(verify=False),
)

deepseek回复的内容包含了模型的思考步骤，通过建立extract_after_think函数对大模型返回的信息进行预处理，使得返回的信息只包含最终的回复内容。

from openai import ChatCompletion
def extract_after_think(chat_completion: ChatCompletion) -> str:
  

    content = chat_completion.choices[0].message.content

    start_index = content.find("</think>")
    if start_index != -1:

        return content[start_index + len("</think>"):]
    else:

        return ""

构建get_completion实现调用大模型的封装，输入提示词信息，得到大模型根据提示词信息返回的最终回复。

#请根据实际替换model_name
def get_completion(prompt, temperature=0.6):
    messages = [{"role": "user", "content": prompt}]
    response = client.chat.completions.create(
        model=<model_name>,
        messages=messages,
        stream=False,
        temperature=temperature,
        max_tokens=2048,
        top_p=0.95
    )
    return extract_after_think(response)
1.3 提示词原则

原则一：撰写清晰且具体的指令。
原则二：给模型留出 “思考” 的时间。

1.3.1 撰写清晰且具体的指令

策略一：使用分隔符来清晰指示输入内容中不同的部分。

分隔符可以是以下任何一种：```、“”"、<>、< tag> </ tag >

在提示词的构造中，通过不同的分割符来对不同内容进行分割处理。

例如以下：

通过 ```对text文档和提示词进行一个分割。

prompt = f"""
Summarize the text delimited by triple backticks \ 
into a single sentence.
```{text}```
"""
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)

策略二：对输出的内容进行结构化的要求。

例如使用：

JSON、HTML

大模型根据输入的提示词中规定的输出格式，来对回复的内容进行规定格式的格式化处理。

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)

策略三：要求模型检查条件是否得到满足。

在提示词中设置判断条件，模型根据设定的判断条件进行不同的规定输出。

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)
text_2 = f"""
The sun is shining brightly today, and the birds are \
singing. It's a beautiful day to go for a \ 
walk in the park. The flowers are blooming, and the \ 
trees are swaying gently in the breeze. People \ 
are out and about, enjoying the lovely weather. \ 
Some are having picnics, while others are playing \ 
games or simply relaxing on the grass. It's a \ 
perfect day to spend time outdoors and appreciate the \ 
beauty of nature.
"""
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_2}\"\"\"
"""
response = get_completion(prompt)
print("Completion for Text 2:")
print(response)

策略四：“少样本” 提示法。

少样本提示法是一种通过提供少量示例（通常为 1-5 个）引导大语言模型（LLM）理解任务要求的提示工程方法，无需大量标注数据且降低对指令复杂度的依赖。

在提示词的编写中，给出少量的提示信息，让大模型学习到其中的回复风格。

例如示例：

通过给出一段对话信息，来让大模型知道应该按照什么样的风格来进行回复。

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)
1.3.2 给模型留出 “思考” 的时间

策略一：明确完成一项任务所需的步骤。

在提示词的编写中，给出具体每一步需要完成的工作，让大模型按照步骤一步一步的进行"思考"，给出最终的回复。


```python
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)

在提示词中规定步骤中输出信息格式，使得大模型能够按照规定的格式输出每一步中需要输出的信息。

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)

策略二：指示模型在得出结论之前先自行找出解决方案。

这种提示词策略被称为 “思维链提示法”，其思想是引导模型显式地展示推理步骤，而非直接生成结论，从而提升复杂任务的解决能力。

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)

学生的解决方案实际上是不正确的。

可以通过指示模型先自行得出解决方案来解决这个问题。
prompt = f"“”
Your task is to determine if the student’s solution
is correct or not.
To solve the problem do the following:

  • First, work out your own solution to the problem.
  • Then compare your solution to the student’s solution \
    and evaluate if the student’s solution is correct or not.
    Don’t decide if the student’s solution is correct until
    you have done the problem yourself.

Use the following format:
Question:

question here

Student’s solution:

student's solution here

Actual solution:

steps to work out the solution and your solution here

Is the student’s solution the same as actual solution
just calculated:

yes or no

Student grade:

correct or incorrect

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

Actual solution:
“”"
response = get_completion(prompt)
print(response)

prompt = f"“”
Your task is to determine if the student’s solution
is correct or not.
To solve the problem do the following:

  • First, work out your own solution to the problem.
  • Then compare your solution to the student’s solution \
    and evaluate if the student’s solution is correct or not.
    Don’t decide if the student’s solution is correct until
    you have done the problem yourself.

Use the following format:
Question:

question here

Student’s solution:

student's solution here

Actual solution:

steps to work out the solution and your solution here

Is the student’s solution the same as actual solution
just calculated:

yes or no

Student grade:

correct or incorrect

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

Actual solution:
“”"
response = get_completion(prompt)
print(response)

1.4 模型的局限性：幻觉现象

模型的幻觉是指人工智能模型，尤其是像大型语言模型这类，生成看似合理但实际上与事实不符或完全虚构的内容的现象。

例如，模型可能会 “编造” 出不存在的事件、人物、产品、技术等，或者对已知的事物给出错误的描述、属性及关系等。

博伊（Boie）是一家真实存在的公司，但（AeroGlide UltraSlim Smart Toothbrush）产品名称并不是真实的。

prompt = f"""
Tell me about AeroGlide UltraSlim Smart Toothbrush by Boie
"""
response = get_completion(prompt)
print(response)
WSSWWWSSW
关注
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值