聊聊如何设计一个优秀的提示应用程序？
在本指南中，我们将介绍一些高级和有趣的方法，我们可以使用提示工程来执行有用和更高级的任务。
请注意，此部分正在大量开发中。 主题：
- 生成数据
- 程序辅助语言模型
- Python 笔记本
一、生成数据
LLM 具有强大的文本生成能力。使用有效的提示策略可以引导模型产生更好、更一致和更符合事实的响应。LLM 对于生成对运行各种实验有用的数据也特别有用。例如，我们可以使用它为情感分类器生成快速样本，如下所示：
迅速的：
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:登录后复制A:
输出：
Q: 我刚得到了有史以来最好的消息！ A: 积极的 Q: 我们刚刚在工作中得到了加薪！ A: 积极的 Q: 我为今天所取得的成就感到非常自豪。 A: 积极的 Q: 我度过了有史以来最好的一天！ A: 积极的 Q: 我非常期待周末的到来。 A: 积极的 Q: 我刚收到了有史以来最好的礼物！ A: 积极的 Q: 我现在非常开心。 A: 积极的 Q: 我很幸运有这么一支了不起的家庭。 A: 积极的 Q: 外面的天气很阴暗。 A: 消极的 Q: 我刚得到了一些可怕的消息。 A: 消极的登录后复制
这非常有用。我们将此示例用于指南另一部分中的不同测试。
二、PAL（程序辅助语言模型）
Gao 等人 (2022)提出了一种使用 LLM 阅读自然语言问题并生成程序作为中间推理步骤的方法。创造的程序辅助语言模型 (PAL) 与思维链提示的不同之处在于，它不是使用自由格式的文本来获得解决方案，而是将解决方案步骤卸载到编程运行时，例如 Python 解释器。
让我们看一个使用 LangChain 和 OpenAI GPT-3 的例子。我们有兴趣开发一个简单的应用程序，该应用程序能够解释所提出的问题并通过利用 Python 解释器提供答案。
具体来说，我们有兴趣创建一个函数，允许使用 LLM 来回答需要理解日期的问题。我们将为 LLM 提供提示，其中包括从此处采用的一些范例。
这些是我们需要的导入：
import openai from datetime import datetime from dateutil.relativedelta import relativedelta import os from langchain.llms import OpenAI from dotenv import load_dotenv登录后复制
让我们首先配置一些东西：
load_dotenv()登录后复制
API configuration
openai.api_key = os.getenv("OPENAI_API_KEY")登录后复制for LangChain
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")登录后复制设置模型实例：
llm = OpenAI(model_name='text-davinci-003', temperature=0)登录后复制
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'登录后复制llm_out = llm(DATE_UNDERSTANDING_PROMPT.format(question=question)) print(llm_out)登录后复制
exec(llm_out) print(born)登录后复制
这将输出以下内容：02/27/1998
以上就是聊聊如何设计一个优秀的提示应用程序？的详细内容，更多请关注海外IDC网其它相关文章！
【本文来源：美国服务器 http://www.558idc.com/mg.html提供，感恩】