结构化输出入门¶

大型语言模型（LLM）是强大的文本生成工具，但从其输出中提取结构化数据可能具有挑战性。结构化输出通过让 LLM 以一致的机器可读格式返回数据来解决此问题。

非结构化输出的问题¶

让我们看看当我们要求 LLM 在没有任何结构的情况下提取信息时会发生什么

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {
            "role": "user",
            "content": "Extract customer: John Doe, age 35, email: john@example.com",
        }
    ],
)

print(response.choices[0].message.content)

输出可能看起来像

Customer Name: John Doe
Age: 35
Email: john@example.com

或者可能是

I found the following customer information:
- Name: John Doe
- Age: 35
- Email address: john@example.com

这种不一致性使得在下游应用程序中可靠地解析信息变得困难。

解决方案：使用 Instructor 实现结构化输出¶

Instructor 通过使用 Pydantic 模型来定义预期的输出结构，从而解决了这个问题

import instructor
from openai import OpenAI
from pydantic import BaseModel, Field, EmailStr

class Customer(BaseModel):
    name: str = Field(description="Customer's full name")
    age: int = Field(description="Customer's age in years", ge=0, le=120)
    email: EmailStr = Field(description="Customer's email address")

client = instructor.from_openai(OpenAI())
customer = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {
            "role": "user",
            "content": "Extract customer: John Doe, age 35, email: john@example.com",
        }
    ],
    response_model=Customer,  # This is the key part
)

print(customer)  # Customer(name='John Doe', age=35, email='john@example.com')
print(f"Name: {customer.name}, Age: {customer.age}, Email: {customer.email}")

这种方法的好处包括

一致性：始终以相同的格式获取数据
验证：年龄必须在 0 到 120 之间，电子邮件必须有效
类型安全：age 始终是整数，而不是字符串
文档：模型字段带有描述，具有自文档功能

复杂示例：嵌套结构¶

Instructor 在处理复杂数据结构时表现出色

from typing import List, Optional
from pydantic import BaseModel, Field
import instructor
from openai import OpenAI

client = instructor.from_openai(OpenAI())

class Address(BaseModel):
    street: str
    city: str
    state: str
    zip_code: str

class Contact(BaseModel):
    email: Optional[str] = None
    phone: Optional[str] = None

class Person(BaseModel):
    name: str
    age: int
    occupation: str
    address: Address
    contact: Contact
    skills: List[str] = Field(description="List of professional skills")

person = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {
            "role": "user",
            "content": """
        Extract detailed information for this person:
        John Smith is a 42-year-old software engineer living at 123 Main St, San Francisco, CA 94105.
        His email is john.smith@example.com and phone is 555-123-4567.
        John is skilled in Python, JavaScript, and cloud architecture.
        """,
        }
    ],
    response_model=Person,
)

print(f"Name: {person.name}")
print(f"Location: {person.address.city}, {person.address.state}")
print(f"Skills: {', '.join(person.skills)}")

安装¶

要开始使用 Instructor，请通过 pip 安装它

pip install instructor pydantic

您还需要为您正在使用的 LLM 提供商设置 API 密钥。

下一步¶

在下一节中，您将学习如何

创建您的首次提取
理解您可以创建的响应模型
设置各种 LLM 提供商的客户端