ChatGPT Prompting开发实战(五)

一、如何编写有效的prompt

对于大语言模型来说,编写出有效的prompt能够帮助模型更好地理解用户的意图(intents),生成针对用户提问来说是有效的答案,避免用户与模型之间来来回回对话多次但是用户不能从LLM那里得到有意义的反馈。本文通过具体案例演示解析两个能够帮助写出有效的prompts的基本原则。案例使用来自OpenAI的模型"gpt-3.5-turbo"并调用相关的chat API:

二、编写清晰和有具体的指令(instructions)的prompt

要点描述:

使用分割符来清楚标明模型输入的不同部分,可以使用的分割符包括:```, """, < >, <tag> </tag>, :等等。

prompt示例如下:

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)

打印输出结果如下:

To guide a model towards the desired output and reduce irrelevant or incorrect responses, it is important to provide clear and specific instructions, which can be achieved through longer prompts that offer more clarity and context.

要点描述:

如何请求LLM给出一个结构化的输出,常见的结构化输出格式有JSON,HTML等。

prompt示例如下:

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)

打印输出结果如下:

要点描述:

请求模型检查输入文本是否满足给定的条件。

prompt示例如下(能够满足给定条件):

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)

打印输出结果如下:

prompt示例如下(不能满足给定条件):

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)

打印输出结果如下:

相关推荐
qq_5088234043 分钟前
金融量化指标--5Sortino索提诺比率
人工智能·microsoft
AIbase20242 小时前
AI技术架构与GEO算法原理如何重塑搜索引擎可见性
人工智能·搜索引擎·架构
一条数据库2 小时前
AI生成文本检测数据集:基于不平衡数据集(人类94% vs AI 6%)的高效机器学习模型训练,涵盖ChatGPT、Gemini等LLM生成内容
人工智能
山烛3 小时前
OpenCV:图像直方图
人工智能·opencv·计算机视觉·图像直方图
摘星编程3 小时前
AI 帮我写单测:pytest 覆盖率提升 40% 的协作日志
人工智能·pytest·测试驱动开发·代码覆盖率·ai协作开发
荼蘼3 小时前
OpenCV 发票识别全流程:透视变换与轮廓检测详解
人工智能·opencv·计算机视觉
☼←安于亥时→❦3 小时前
PyTorch 梯度与微积分
人工智能·pytorch·python
mahuifa4 小时前
OpenCV 开发 -- 图像阈值处理
人工智能·opencv·计算机视觉
闲人编程4 小时前
图像去雾算法:从物理模型到深度学习实现
图像处理·人工智能·python·深度学习·算法·计算机视觉·去雾
咔咔学姐kk4 小时前
大模型微调技术宝典:Transformer架构,从小白到专家
人工智能·深度学习·学习·算法·transformer