提示应用程序

在这份指南中，我们将介绍一些高级且有趣的方法，利用提示工程来执行有用且更复杂的任务。

请注意，本节正在积极开发中。

主题：

• 生成数据
• 程序辅助语言模型
• Python 笔记本

生成数据

LLM 具有强大的文本生成能力。通过有效的提示策略，可以引导模型生成更好、更一致且更真实的信息。LLM 对于生成实验所需的各类数据也非常有用。例如，我们可以使用它来为情感分类器生成快速样本，如下所示：

提示：

Produce 10 exemplars for sentiment analysis. Examples are categorized as either positive or negative. Produce 2 negative examples and 8 positive examples. Use this format for the examples:
Q: <sentence>
A: <sentiment>
​

输出：

Q: I just got the best news ever!
A: Positive

Q: We just got a raise at work!
A: Positive

Q: I'm so proud of what I accomplished today.
A: Positive

Q: I'm having the best day ever!
A: Positive

Q: I'm really looking forward to the weekend.
A: Positive

Q: I just got the best present ever!
A: Positive

Q: I'm so happy right now.
A: Positive

Q: I'm so blessed to have such an amazing family.
A: Positive

Q: The weather outside is so gloomy.
A: Negative

Q: I just got some terrible news.
A: Negative
​

这非常有用。我们用这个例子在指南的另一部分进行不同的测试。

这里还有一个提示示例，展示了如何利用 LLM 进行数据标注/增强任务。

提示：

produce 3 wine reviews and label taste, flavor, aroma related token; present the result as a json file, in addition add the coordinate of each term for NER task
​

输出：

[
  {
    "review": "This Chardonnay has a rich, creamy texture with notes of vanilla and buttery oak. The taste is smooth and well-balanced, with a hint of tropical fruit on the finish.",
    "tokens": [
      {"text": "rich", "label": "flavor", "start": 5, "end": 9},
      {"text": "creamy", "label": "texture", "start": 10, "end": 16},
      {"text": "vanilla", "label": "flavor", "start": 28, "end": 35},
      {"text": "buttery", "label": "flavor", "start": 40, "end": 47},
      {"text": "oak", "label": "aroma", "start": 48, "end": 51},
      {"text": "smooth", "label": "taste", "start": 61, "end": 67},
      {"text": "well-balanced", "label": "taste", "start": 68, "end": 81},
      {"text": "hint", "label": "flavor", "start": 89, "end": 93},
      {"text": "tropical fruit", "label": "flavor", "start": 98, "end": 112},
      {"text": "finish", "label": "taste", "start": 116, "end": 122}
    ]
  },
  {
    "review": "This Cabernet Sauvignon has a bold, full-bodied flavor with notes of black cherry and dark chocolate. The aroma is rich and complex, with hints of tobacco and leather.",
    "tokens": [
      {"text": "bold", "label": "flavor", "start": 5, "end": 9},
      {"text": "full-bodied", "label": "texture", "start": 10, "end": 21},
      {"text": "black cherry", "label": "flavor", "start": 30, "end": 42},
      {"text": "dark chocolate", "label": "flavor", "start": 47, "end": 60},
      {"text": "rich", "label": "aroma", "start": 69, "end": 73},
      {"text": "complex", "label": "aroma", "start": 78, "end": 85},
      {"text": "hints", "label": "aroma", "start": 90, "end": 96},
      {"text": "tobacco", "label": "aroma", "start": 101, "end": 108},
      {"text": "leather", "label": "aroma", "start": 113, "end": 120}
    ]
  },
  {
    "review": "This Riesling has a crisp, refreshing taste with notes of green apple and honey. The aroma is floral and fruity, with a hint of citrus.",
    "tokens": [
      {"text": "crisp", "label": "texture", "start": 5, "end": 10},
      {"text": "refreshing", "label": "texture", "start": 12, "end": 22},
      {"text": "green apple", "label": "flavor", "start": 31, "end": 42},
    ]
  }
​

PAL（程序辅助语言模型）

Gao 等，2022 提出了一种方法，使用 LLM 读取自然语言问题并生成程序作为中间推理步骤。称为程序辅助语言模型（PAL），与思维链提示不同的是，它不是通过自由形式文本获得解决方案，而是将解决方案步骤卸载到程序化运行时，如 Python 解释器。

让我们看一个使用 LangChain 和 OpenAI GPT-3 的示例。我们希望开发一个简单的应用程序，能够理解所提出的问题并利用 Python 解释器提供答案。

具体来说，我们希望创建一个函数，允许使用 LLM 来回答需要日期理解的问题。我们将向 LLM 提供一个提示，其中包含从 这里 引用的一些示例。

我们需要以下导入：

import openai
from datetime import datetime
from dateutil.relativedelta import relativedelta
import os
from langchain.llms import OpenAI
from dotenv import load_dotenv
​

首先配置一些内容：

load_dotenv()

# API configuration
openai.api_key = os.getenv("OPENAI_API_KEY")

# for LangChain
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
​

设置模型实例：

llm = OpenAI(model_name='text-davinci-003', temperature=0)
​

设置提示+问题：

question = "Today is 27 February 2023. I was born exactly 25 years ago. What is the date I was born in MM/DD/YYYY?"

DATE_UNDERSTANDING_PROMPT = """
# Q: 2015 is coming in 36 hours. What is the date one week from today in MM/DD/YYYY?
# If 2015 is coming in 36 hours, then today is 36 hours before.
today = datetime(2015, 1, 1) - relativedelta(hours=36)
# One week from today,
one_week_from_today = today + relativedelta(weeks=1)
# The answer formatted with %m/%d/%Y is
one_week_from_today.strftime('%m/%d/%Y')
# Q: The first day of 2019 is a Tuesday, and today is the first Monday of 2019. What is the date today in MM/DD/YYYY?
# If the first day of 2019 is a Tuesday, and today is the first Monday of 2019, then today is 6 days later.
today = datetime(2019, 1, 1) + relativedelta(days=6)
# The answer formatted with %m/%d/%Y is
today.strftime('%m/%d/%Y')
# Q: The concert was scheduled to be on 06/01/1943, but was delayed by one day to today. What is the date 10 days ago in MM/DD/YYYY?
# If the concert was scheduled to be on 06/01/1943, but was delayed by one day to today, then today is one day later.
today = datetime(1943, 6, 1) + relativedelta(days=1)
# 10 days ago,
ten_days_ago = today - relativedelta(days=10)
# The answer formatted with %m/%d/%Y is
ten_days_ago.strftime('%m/%d/%Y')
# Q: It is 4/19/1969 today. What is the date 24 hours later in MM/DD/YYYY?
# It is 4/19/1969 today.
today = datetime(1969, 4, 19)
# 24 hours later,
later = today + relativedelta(hours=24)
# The answer formatted with %m/%d/%Y is
today.strftime('%m/%d/%Y')
# Q: Jane thought today is 3/11/2002, but today is in fact Mar 12, which is 1 day later. What is the date 24 hours later in MM/DD/YYYY?
# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/1/2002.
today = datetime(2002, 3, 12)
# 24 hours later,
later = today + relativedelta(hours=24)
# The answer formatted with %m/%d/%Y is
later.strftime('%m/%d/%Y')
# Q: Jane was born on the last day of Feburary in 2001. Today is her 16-year-old birthday. What is the date yesterday in MM/DD/YYYY?
# If Jane was born on the last day of Feburary in 2001 and today is her 16-year-old birthday, then today is 16 years later.
today = datetime(2001, 2, 28) + relativedelta(years=16)
# Yesterday,
yesterday = today - relativedelta(days=1)
# The answer formatted with %m/%d/%Y is
yesterday.strftime('%m/%d/%Y')
# Q: {question}
""".strip() + '\n'
​

llm_out = llm(DATE_UNDERSTANDING_PROMPT.format(question=question))
print(llm_out)
​

exec(llm_out)
print(born)
​

这将输出：02/27/1998

Python 笔记本

更多示例即将推出！

上一节 (高级提示)

下一节 (ChatGPT)

声明:
本文件灏天文库团队进行了翻译。尽管我们力求准确，但请注意，翻译可能包含错误或不准确之处。原文档以其原始语言为准。我们不对因使用此翻译而产生的任何误解或误译负责。