Prompt-Engineering-Guide/pages/techniques/pal.ru.mdx
2023-12-31 12:19:20 -06:00

106 lines
5.1 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# PAL (Program-Aided Language Models)
import { Callout, FileTree } from 'nextra-theme-docs'
import {Screenshot} from 'components/screenshot'
import PAL from '../../img/pal.png'
[Gao и др., (2022)](https://arxiv.org/abs/2211.10435) представляют метод, который использует LLM-модели для чтения проблем естественного языка и генерации программ в качестве промежуточных шагов рассуждения. Названные "program-aided language models" (PAL), они отличаются от цепочки мыслей в том, что вместо использования свободного текста для получения решения они передают этот шаг решения в программное окружение, такое как интерпретатор Python.
<Screenshot src={PAL} alt="PAL" />
Источник изображения: [Gao и др., (2022)](https://arxiv.org/abs/2211.10435)
Давайте рассмотрим пример с использованием LangChain и OpenAI GPT-3. Мы заинтересованы в разработке простого приложения, которое способно интерпретировать заданный вопрос и предоставлять ответ, используя интерпретатор Python.
Конкретно, нас интересует создание функциональности, позволяющей использовать LLM для ответов на вопросы, требующие понимания даты. Мы предоставим LLM подсказку, которая включает несколько образцов, взятых [отсюда](https://github.com/reasoning-machines/pal/blob/main/pal/prompt/date_understanding_prompt.py).
Вот импорты, которые нам понадобятся:
```python
import openai
from datetime import datetime
from dateutil.relativedelta import relativedelta
import os
from langchain.llms import OpenAI
from dotenv import load_dotenv
```
Давайте сначала настроим несколько вещей:
```python
load_dotenv()
# API configuration
openai.api_key = os.getenv("OPENAI_API_KEY")
# for LangChain
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
```
Настройка экземпляра модели:
```python
llm = OpenAI(model_name='text-davinci-003', temperature=0)
```
Настройка подсказки + вопроса:
```python
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 3/12/2002.
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'
```
```python
llm_out = llm(DATE_UNDERSTANDING_PROMPT.format(question=question))
print(llm_out)
```
```python
exec(llm_out)
print(born)
```
Это выведет следующее: `02/27/1998`