今天我学习了DeepLearning.AI的 Prompt Engineering 的在线课程,我想和大家一起分享一下该门课程的一些主要内容。以下是我写的关于该课程的前两篇博客:
- 大型语言模(LLM)之提示词工程(一)
- 大型语言模(LLM)之提示词工程(二)
- 大型语言模(LLM)之提示词工程(三)
今天我们来学习第三部分内容:转换(Transforming)。
转换(Transforming)
今天我们将探索如何使用大型语言模型进行文本转换任务,例如语言翻译、拼写和语法检查、语气调整和格式转换。
首先我们需要设置通过API来访问大型语言模型(LLM)的主要代码:
为防止出现Rate limits问题,我们需要安装一个为回退和重试提供函数装饰器的库 backoff
# pip install backoffimport openai
import backoff openai.api_key ='YOUR_OPENAI_API_KEY'@backoff.on_exception(backoff.expo, openai.error.RateLimitError)
def get_completion(prompt, model="gpt-3.5-turbo", temperature=0): messages = [{"role": "user", "content": prompt}]response = openai.ChatCompletion.create(model=model,messages=messages,temperature=temperature, )return response.choices[0].message["content"]
翻译
大型语言模型LLM,一般会使用多种语言的资源进行训练的大型语言模型。 这使模型能够进行多语言翻译工作。 以下是如何使用此功能的一些示例。
下面是将英语翻译成西班牙语的例子:
#将英语翻译成西班牙语prompt = f"""
Translate the following English text to Spanish: \
```Hi, I would like to order a blender```
"""
response = get_completion(prompt)
print(response)
下面是让LLM识别文本是属于哪种语言:
prompt = f"""
Tell me which language this is:
```Combien coûte le lampadaire?```
"""
response = get_completion(prompt)
print(response)
将文本翻译成法语、西班牙语和英语:
prompt = f"""
Translate the following text to French and Spanish
and English pirate: \
```I want to order a basketball```
"""
response = get_completion(prompt)
print(response)
将文本翻译成正式和非正式的西班牙语:
prompt = f"""
Translate the following text to Spanish in both the \
formal and informal forms:
'Would you like to order a pillow?'
"""
response = get_completion(prompt)
print(response)
通用翻译器
想象一下,假如您在一家大型跨国电子商务公司的IT部门负责 人。客户正在用他们各自的的母语向您发送有关 IT 问题的消息。 您的员工来自世界各地,且只他们只用自己的的母语。 此时你就需要一个万能翻译器!
user_messages = ["La performance du système est plus lente que d'habitude.", # System performance is slower than normal "Mi monitor tiene píxeles que no se iluminan.", # My monitor has pixels that are not lighting"Il mio mouse non funziona", # My mouse is not working"Mój klawisz Ctrl jest zepsuty", # My keyboard has a broken control key"我的屏幕在闪烁" # My screen is flashing
]
下面我们要把上述不同语言的客户问题翻译成英语和中文 :
for issue in user_messages:prompt = f"Tell me what language this is: ```{issue}```"lang = get_completion(prompt)print(f"Original message ({lang}): {issue}")prompt = f"""Translate the following text to English \and Chinese: ```{issue}```"""response = get_completion(prompt)print(response, "\n")
语调转换
LLM可以根据不同的受众输出不同语调的内容。下面是一段英语俚语的对白,我们要求LLM将其转换成商业信函语调。
prompt = f"""
Translate the following from slang to a business letter:
'Dude, This is Joe, check out this spec on this standing lamp.'
"""
response = get_completion(prompt)
print(response)
格式转换
LLM还可以在不同的格式之间进行转换。 提示语应描述输入和输出格式。下面我们要将一个来自于JSON格式的python字典转换为HTML格式:
data_json = { "resturant employees" :[ {"name":"Shyam", "email":"shyamjaiswal@gmail.com"},{"name":"Bob", "email":"bob32@gmail.com"},{"name":"Jai", "email":"jai87@gmail.com"}
]}prompt = f"""
Translate the following python dictionary from JSON to an HTML \
table with column headers and title: {data_json}
"""
response = get_completion(prompt)
print(response)
接下来我们要展示这个HTML页面:
from IPython.display import display, Markdown, Latex, HTML, JSON
display(HTML(response))
拼写检查/语法检查
这里我们有一些常见的语法和拼写问题的例子以及大型语言模型(LLM)的回应。
要向 LLM 发出您希望它校对您的文本的信号,您可以指示模型“校对”或“校对并更正”。下面的几段文本中存在语法错误或者拼写错误,我们要让LLM来检查并纠错文本中的错误。
text = [ "The girl with the black and white puppies have a ball.", # The girl has a ball."Yolanda has her notebook.", # ok"Its going to be a long day. Does the car need it’s oil changed?", # Homonyms"Their goes my freedom. There going to bring they’re suitcases.", # Homonyms"Your going to need you’re notebook.", # Homonyms"That medicine effects my ability to sleep. Have you heard of the butterfly affect?", # Homonyms"This phrase is to cherck chatGPT for speling abilitty" # spelling
]
for t in text:prompt = f"""Proofread and correct the following textand rewrite the corrected version. If you don't findand errors, just say "No errors found". Don't use any punctuation around the text:```{t}```"""response = get_completion(prompt)print(response)
下面我们尝试让LLM来对中文的句子进行纠错,看看它是否能找出错误:
text = [ "我们的公司是一家专业的电脑唯修,服务态度好,价格公道", "他们在学校里学习了很多关于历史,数学和科学呢的知识。", "我们去了一家新开的餐厅,才很好吃,服务员也很友好。", "你得先做完作业,在出去玩!", "那青山碧岭中随风起伏的阵阵林涛声,仿佛是大自然奏响的一枝交响乐.", "七夕,只是牛郎与织女的节日,与俄们这些凡人无关。", "我的人生有两件非常幸运的事情,一个是遇见了你,一个是将和你走过余生。"
]
for t in text:prompt = f"""检查一下下面的本文是否存在错别字或者语法错误,如果有错误就重新改写句子。你在回复的时候必须输出2个句子,一句是原始文本,另一句是修改后的文本,如果没有发现任何错误,就说“没有找到错误”。请使用以下格式输出:原始文本:这里是原始文本修改后的文本:这里是修改后的文本原始文本:{t}"""response = get_completion(prompt)print(response)print()
总体感觉LLM对中文的错别字还是比较熟悉,对一些很明显的错别字纠错成功率可以达到100%,但是对于最后一句,我们运行了多次程序后发现有时候LLM对最后一句的回复是:没有找到错误。大家可以尝试一下看看LLM对中文错别字的识别率到底有多少。
下面我们给LLM提供一篇英语短文,让它来对短文纠错:
text = f"""
Got this for my daughter for her birthday cuz she keeps taking \
mine from my room. Yes, adults also like pandas too. She takes \
it everywhere with her, and it's super soft and cute. One of the \
ears is a bit lower than the other, and I don't think that was \
designed to be asymmetrical. It's a bit small for what I paid for it \
though. I think there might be other options that are bigger for \
the same price. It arrived a day earlier than expected, so I got \
to play with it myself before I gave it to my daughter.
"""
prompt = f"proofread and correct this review: ```{text}```"
response = get_completion(prompt)
print(response)
由于短文内容比较长,我们使用一个校对工具来看看LLM到底做了哪些修改:
from redlines import Redlinesdiff = Redlines(text,response)
display(Markdown(diff.output_markdown))
这里我们可以清晰的发现LLM对原文做的修改。
下面我们让LLM将上述原文修改为APA风格的文章(APA 风格是学术期刊文章和书籍等学术文件的写作风格和格式)
prompt = f"""
proofread and correct this review. Make it more compelling.
Ensure it follows APA style guide and targets an advanced reader.
Output in markdown format.
Text: ```{text}```
"""
response = get_completion(prompt)
display(Markdown(response))
总结
今晚我们学习了如果让大型语言模型LLM实现多语言翻译功能、语言识别、错别字/语法检查、语调转换等功能。希望今天的内容能对大家有所帮助!