关于提示的通用技巧¶

在我们深入探讨模式工程的一些重大应用之前，我想为你提供成功的工具。这个笔记本旨在分享一些使用提示以充分利用模型的一般建议。

在你可能认为提示工程就像在记事本中编码一样，需要大量调整这堵文本墙。但通过模式工程，你可以用更少的工作从提示中获得更多的效果。

分类¶

对于分类问题，我们通常发现有两种建模方法。

使用枚举
使用文字常量

在Python中使用枚举，当你需要一组相关的命名常量，并且你希望确保类型安全、可读性以及防止无效值时。枚举对于分组和遍历这些常量非常有帮助。

当你有一小组不变的值，不需要分组或迭代，并且类型安全和防止无效值不太重要时，使用字面量。对于基本的、一次性的值，字面量更简单直接。

在 [1]:

  Copied!     
 
import instructor
from openai import OpenAI

from enum import Enum
from pydantic import BaseModel, Field
from typing_extensions import Literal


client = instructor.patch(OpenAI())


# Tip: Do not use auto() as they cast to 1,2,3,4
class House(Enum):
    Gryffindor = "gryffindor"
    Hufflepuff = "hufflepuff"
    Ravenclaw = "ravenclaw"
    Slytherin = "slytherin"


class Character(BaseModel):
    age: int
    name: str
    house: House

    def say_hello(self):
        print(
            f"Hello, I'm {self.name}, I'm {self.age} years old and I'm from {self.house.value.title()}"
        )


resp = client.chat.completions.create(
    model="gpt-4-1106-preview",
    messages=[{"role": "user", "content": "Harry Potter"}],
    response_model=Character,
)
resp.model_dump()
import instructor from openai import OpenAI from enum import Enum from pydantic import BaseModel, Field from typing_extensions import Literal client = instructor.patch(OpenAI()) # 提示：不要使用 auto()，因为它们会转换为 1,2,3,4 class House(Enum): Gryffindor = "gryffindor" Hufflepuff = "hufflepuff" Ravenclaw = "ravenclaw" Slytherin = "slytherin" class Character(BaseModel): age: int name: str house: House def say_hello(self): print( f"你好，我是 {self.name}，我 {self.age} 岁，我来自 {self.house.value.title()}" ) resp = client.chat.completions.create( model="gpt-4-1106-preview", messages=[{"role": "user", "content": "Harry Potter"}], response_model=Character, ) resp.model_dump()

输出[1] :

{'age': 17, 'name': 'Harry Potter', 'house': <House.Gryffindor: 'gryffindor'>}

在 [2]:

  Copied!     
 
resp.say_hello()
resp.say_hello()

Hello, I'm Harry Potter, I'm 17 years old and I'm from Gryffindor

在 [3]:

  Copied!     
 
class Character(BaseModel):
    age: int
    name: str
    house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"]


resp = client.chat.completions.create(
    model="gpt-4-1106-preview",
    messages=[{"role": "user", "content": "Harry Potter"}],
    response_model=Character,
)
resp.model_dump()
class Character(BaseModel): age: int name: str house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"] resp = client.chat.completions.create( model="gpt-4-1106-preview", messages=[{"role": "user", "content": "哈利·波特"}], response_model=Character, ) resp.model_dump()

输出[3]:

{'age': 11, 'name': 'Harry Potter', 'house': 'Gryffindor'}

任意属性¶

很多时候，有一些长的属性你可能想从数据中提取，而这些属性我们无法预先指定。我们可以通过定义一个任意的键值存储来解决这个问题，如下所示：

在 [4]:

  Copied!     
 
class Property(BaseModel):
    key: str = Field(description="Must be snake case")
    value: str


class Character(BaseModel):
    age: int
    name: str
    house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"]
    properties: list[Property]


resp = client.chat.completions.create(
    model="gpt-4-1106-preview",
    messages=[{"role": "user", "content": "Snape from Harry Potter"}],
    response_model=Character,
)
resp.model_dump()
 class Property(BaseModel): key: str = Field(description="必须是蛇形命名") value: str class Character(BaseModel): age: int name: str house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"] properties: list[Property] resp = client.chat.completions.create( model="gpt-4-1106-preview", messages=[{"role": "user", "content": "Snape from Harry Potter"}], response_model=Character, ) resp.model_dump()

输出[4]：

{'age': 38,
 'name': 'Severus Snape',
 'house': 'Slytherin',
 'properties': [{'key': 'role', 'value': 'Potions Master'},
  {'key': 'patronus', 'value': 'Doe'},
  {'key': 'loyalty', 'value': 'Dumbledore'},
  {'key': 'played_by', 'value': 'Alan Rickman'}]}

限制列表的长度¶

在后面的章节中，我们将讨论如何使用验证器来断言列表的长度，但我们也可以使用提示技巧来枚举值。在这里，我们将定义一个索引来计算属性。

在下面的例子中，我们将不再进行提取，而是进行生成。

在 [5]：

  Copied!     
 
class Property(BaseModel):
    index: str = Field(..., description="Monotonically increasing ID")
    key: str = Field(description="Must be snake case")
    value: str


class Character(BaseModel):
    age: int
    name: str
    house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"]
    properties: list[Property] = Field(
        ...,
        description="Numbered list of arbitrary extracted properties, should be exactly 5",
    )


resp = client.chat.completions.create(
    model="gpt-4-1106-preview",
    messages=[{"role": "user", "content": "Snape from Harry Potter"}],
    response_model=Character,
)
resp.model_dump()
class Property(BaseModel): index: str = Field(..., description="单调递增的ID") key: str = Field(description="必须使用蛇形命名") value: str class Character(BaseModel): age: int name: str house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"] properties: list[Property] = Field( ..., description="任意提取属性的编号列表，必须正好是5个", ) resp = client.chat.completions.create( model="gpt-4-1106-preview", messages=[{"role": "user", "content": "哈利·波特中的斯内普"}], response_model=Character, ) resp.model_dump()

输出[5]：

{'age': 38,
 'name': 'Severus Snape',
 'house': 'Slytherin',
 'properties': [{'index': '1',
   'key': 'position_at_hogwarts',
   'value': 'Potions Master'},
  {'index': '2', 'key': 'patronus_form', 'value': 'Doe'},
  {'index': '3', 'key': 'loyalty', 'value': 'Albus Dumbledore'},
  {'index': '4', 'key': 'played_by', 'value': 'Alan Rickman'},
  {'index': '5', 'key': 'final_act', 'value': 'Protecting Harry Potter'}]}

定义多个实体¶

现在我们看到一个具有许多属性的单一实体，我们可以继续将它们嵌套到许多用户中

在 [6]:

  Copied!     
 
from collections.abc import Iterable


class Character(BaseModel):
    age: int
    name: str
    house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"]


resp = client.chat.completions.create(
    model="gpt-4-1106-preview",
    messages=[{"role": "user", "content": "Five characters from Harry Potter"}],
    response_model=Iterable[Character],
)

for character in resp:
    print(character)
从 collections.abc 导入 Iterable 类 Character(BaseModel): age: int name: str house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"] resp = client.chat.completions.create( model="gpt-4-1106-preview", messages=[{"role": "user", "content": "五个来自哈利·波特的角色"}], response_model=Iterable[Character], ) 对于 character in resp: print(character)

age=11 name='Harry Potter' house='Gryffindor'
age=11 name='Hermione Granger' house='Gryffindor'
age=11 name='Ron Weasley' house='Gryffindor'
age=11 name='Draco Malfoy' house='Slytherin'
age=11 name='Neville Longbottom' house='Gryffindor'

在 [7]：

  Copied!     
 
from collections.abc import Iterable


class Character(BaseModel):
    age: int
    name: str
    house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"]


resp = client.chat.completions.create(
    model="gpt-4-1106-preview",
    messages=[{"role": "user", "content": "Five characters from Harry Potter"}],
    stream=True,
    response_model=Iterable[Character],
)

for character in resp:
    print(character)
from collections.abc import Iterable class Character(BaseModel): age: int name: str house: Literal["Gryffindor", "Hufflepuff", "Ravenclaw", "Slytherin"] resp = client.chat.completions.create( model="gpt-4-1106-preview", messages=[{"role": "user", "content": "来自哈利·波特的五个角色"}], stream=True, response_model=Iterable[Character], ) for character in resp: print(character)

age=11 name='Harry Potter' house='Gryffindor'
age=11 name='Hermione Granger' house='Gryffindor'
age=11 name='Ron Weasley' house='Gryffindor'
age=17 name='Draco Malfoy' house='Slytherin'
age=11 name='Luna Lovegood' house='Ravenclaw'

定义关系¶

我们不仅可以定义用户列表，还可以通过属性列表轻松定义引用列表。这是我学到的关于提示的更有趣的事情之一。

第 [8] 行：

  Copied!     
 
class Character(BaseModel):
    id: int
    name: str
    friends_array: list[int] = Field(description="Relationships to their friends using the id")


resp = client.chat.completions.create(
    model="gpt-4-1106-preview",
    messages=[{"role": "user", "content": "5 kids from Harry Potter"}],
    stream=True,
    response_model=Iterable[Character],
)

for character in resp:
    print(character)
class Character(BaseModel): id: int name: str friends_array: list[int] = Field(description="使用id与朋友的关系") resp = client.chat.completions.create( model="gpt-4-1106-preview", messages=[{"role": "user", "content": "5 kids from Harry Potter"}], stream=True, response_model=Iterable[Character], ) for character in resp: print(character)

id=1 name='Harry Potter' friends_array=[2, 3, 4, 5, 6]
id=2 name='Hermione Granger' friends_array=[1, 3, 4, 5]
id=3 name='Ron Weasley' friends_array=[1, 2, 4, 6]
id=4 name='Neville Longbottom' friends_array=[1, 2, 3, 5]
id=5 name='Luna Lovegood' friends_array=[1, 2, 4, 6]
id=6 name='Draco Malfoy' friends_array=[1, 3, 5]

通过我们讨论的工具，我们可以在生产环境中找到许多实际应用。这些应用包括从记录中提取行动项、生成假数据、填写表单以及创建与生成式UI对应的对象。这些简单的技巧将非常有用。

缺失数据¶

Maybe模式是函数式编程中用于错误处理的一个概念。与抛出异常或返回None不同，你可以使用Maybe类型来封装结果和潜在的错误。

这种模式在进行LLM调用时特别有用，因为为语言模型提供一个逃生舱口可以有效减少幻觉。

在 [9]：

  Copied!     
 
from typing import Optional

class Character(BaseModel):
    age: int
    name: str

class MaybeCharacter(BaseModel):
    result: Optional[Character] = Field(default=None)
    error: bool = Field(default=False)
    message: Optional[str]
来自 typing 导入可选的 class Character（基础模型）： age：整数 name：字符串 class MaybeCharacter（基础模型）： result：可选的[Character] = 字段（默认=无） error：布尔值 = 字段（默认=False） message：可选的[字符串]

在 [10]:

  Copied!     
 
def extract(content: str) -> MaybeCharacter:
    return client.chat.completions.create(
        model="gpt-3.5-turbo",
        response_model=MaybeCharacter,
        messages=[
            {"role": "user", "content": f"Extract `{content}`"},
        ],
    )
def extract(content: str) -> MaybeCharacter: return client.chat.completions.create( model="gpt-3.5-turbo", response_model=MaybeCharacter, messages=[ {"role": "user", "content": f"提取 `{content}`"}, ], )

在 [11]:

  Copied!     
 
extract("Harry Potter")
提取("Harry Potter")

输出[11]：

MaybeCharacter(result=Character(age=17, name='Harry Potter'), error=False, message=None)

在 [12]:

  Copied!     
 
user = extract("404 Error")

if user.error:
    raise ValueError(user.message)
用户 = extract("404 Error") 如果 用户.error: 引发 ValueError(用户.message)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/Users/jasonliu/dev/instructor/docs/tutorials/2-tips.ipynb Cell 20 line 4
      <a href='vscode-notebook-cell:/Users/jasonliu/dev/instructor/docs/tutorials/2-tips.ipynb#X25sZmlsZQ%3D%3D?line=0'>1</a> user = extract("404 Error")
      <a href='vscode-notebook-cell:/Users/jasonliu/dev/instructor/docs/tutorials/2-tips.ipynb#X25sZmlsZQ%3D%3D?line=2'>3</a> if user.error:
----> <a href='vscode-notebook-cell:/Users/jasonliu/dev/instructor/docs/tutorials/2-tips.ipynb#X25sZmlsZQ%3D%3D?line=3'>4</a>     raise ValueError(user.message)

ValueError: 404 Error