Pydantic + OpenAI: The Cleanest Way to Get Structured Outputs from LLMs

from pydantic import BaseModel

class PersonInfo(BaseModel):
    name: str
    age: int
    city: str

from openai import OpenAI
import json

client = OpenAI(api_key="your_api_key")

# 以原始字典形式定义 schema
tools = [
    {
        "type": "function",
        "function": {
            "name": "extract_person_info",
            "strict": True,
            "parameters": {
                "type": "object",
                "properties": {
                    "name": {"type": "string"},
                    "age": {"type": "integer"},
                    "city": {"type": "string"}
                },
                "required": ["name", "age", "city"],
                "additionalProperties": False
            }
        }
    }
]

response = client.chat.completions.create(
    model="gpt-4o-mini",
    tools=tools,
    tool_choice={"type": "function", "function": {"name": "extract_person_info"}},
    messages=[
        {"role": "user", "content": "Extract info from: 'Maria is 32 years old and lives in Athens.'"}
    ]
)

# 手动解析 —— 我们得到的是一个普通字典
result = json.loads(response.choices[0].message.tool_calls[0].function.arguments)
print(result["name"])   # "Maria" —— 但如果键缺失了怎么办？KeyError.
print(result["age"])    # 可能是 "32" 而不是 32 —— 类型无法保证

from openai import OpenAI
from pydantic import BaseModel

client = OpenAI(api_key="your_api_key")

class PersonInfo(BaseModel):
    name: str
    age: int
    city: str

response = client.beta.chat.completions.parse(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Extract info from: 'Maria is 32 years old and lives in Athens.'"}
    ],
    response_format=PersonInfo
)

# 我们得到的是一个完整的 Python 对象，类型安全且经过验证
result = response.choices[0].message.parsed
print(result.name)   # "Maria" —— 始终是字符串
print(result.age)    # 32 —— 始终是整数，从不会是字符串
print(result.city)   # "Athens" —— 始终是字符串

from pydantic import BaseModel
from typing import List

class Address(BaseModel):
    street: str
    city: str
    country: str

class ContactInfo(BaseModel):
    name: str
    email: str
    address: Address
    phone_numbers: List[str]

response = client.beta.chat.completions.parse(
    model="gpt-4o-mini",
    messages=[
        {
            "role": "user",
            "content": """从以下内容中提取联系信息：
            'Maria Mouschoutzi,
[email protected]
, 
            Ermou 15, Athens, Greece. 
            Phone: +30 210 1234567, +30 697 8901234'"""
        }
    ],
    response_format=ContactInfo
)

contact = response.choices[0].message.parsed
print(contact.name)                 # "Maria Mouschoutzi"
print(contact.address.city)        # "Athens"
print(contact.phone_numbers[0])    # "+30 210 1234567"

from pydantic import BaseModel, Field
from typing import Optional

class ProductReview(BaseModel):
    product_name: str = Field(description="The name of the product being reviewed")
    rating: int = Field(ge=1, le=5, description="Rating from 1 to 5 stars")
    sentiment: str = Field(description="One of: positive, neutral, negative")
    summary: str = Field(max_length=200, description="A brief summary of the review")
    verified_purchase: Optional[bool] = Field(default=None, description="Whether this is a verified purchase")

response = client.beta.chat.completions.parse(
    model="gpt-4o-mini",
    messages=[
        {
            "role": "user",
            "content": """从以下内容中提取结构化评论：
            'Absolutely love this coffee machine! 
            Makes perfect espresso every time. 
            5 stars, would recommend to anyone.'"""
        }
    ],
    response_format=ProductReview
)

review = response.choices[0].message.parsed
print(review.product_name)   # "coffee machine"
print(review.rating)         # 5
print(review.sentiment)      # "positive"
print(review.summary)        # "Makes perfect espresso every time."

response = client.beta.chat.completions.parse(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "从上面的工作描述中提取信息。"}],
    response_format=JobPosting
)

message = response.choices[0].message

if message.refusal:
    print(f"模型拒绝: {message.refusal}")
else:
    job = message.parsed
    print(f"提取结果: {job.job_title} 在 {job.company_name}")

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

client = OpenAI(api_key="your_api_key")

class SalaryRange(BaseModel):
    min_salary: Optional[int] = Field(default=None, description="年薪最低值（单位：美元）")
    max_salary: Optional[int] = Field(default=None, description="年薪最高值（单位：美元）")
    currency: str = Field(default="USD", description="货币代码")

class JobPosting(BaseModel):
    job_title: str = Field(description="职位名称或角色名称")
    company_name: str = Field(description="招聘公司的名称")
    location: str = Field(description="工作地点，例如 '希腊雅典' 或 '远程'")
    employment_type: str = Field(description="工作类型，可选值为：full-time, part-time, contract, freelance")
    required_skills: List[str] = Field(description="所需技术技能列表")
    years_of_experience: Optional[int] = Field(default=None, description="所需的最低工作经验年限")
    salary: Optional[SalaryRange] = Field(default=None, description="如果提及，薪资范围")
    remote_friendly: bool = Field(description="是否允许远程办公")

job_post_text = """
Senior Python Engineer at pialgorithms (Athens, Greece / Remote)

我们正在寻找一位经验丰富的 Python 开发者加入我们的 AI 团队。
您将负责我们的文档管理系统，使用 LLM 和 RAG 管道构建智能搜索和提取功能。

要求：
- 5 年以上 Python 开发经验
- 精通 FastAPI、LangChain 和向量数据库
- 具备 OpenAI API 和 Pydantic 使用经验
- 熟悉 Docker 和云部署（AWS/GCP）

薪资：6万欧元 - 8.5万欧元 每年
全职职位。支持远程办公。
"""

response = client.beta.chat.completions.parse(
    model="gpt-4o-mini",
    messages=[
        {
            "role": "system",
            "content": "你是从职位描述中提取结构化信息的专家。"
        },
        {
            "role": "user",
            "content": f"从这份职位描述中提取所有相关信息:\n\n{job_post_text}"
        }
    ],
    response_format=JobPosting
)

job = response.choices[0].message.parsed

print(f"职位名称: {job.job_title}")
print(f"公司名称: {job.company_name}")
print(f"工作地点: {job.location}")
print(f"远程办公: {job.remote_friendly}")
print(f"所需技能: {', '.join(job.required_skills)}")
print(f"工作经验: {job.years_of_experience} 年")
if job.salary:
    print(f"薪资范围: {job.salary.min_salary} - {job.salary.max_salary} {job.salary.currency}")

职位名称: 高级Python工程师
公司名称: pialgorithms
工作地点: 希腊雅典 / 远程
远程办公: True
所需技能: Python, FastAPI, LangChain, 向量数据库, OpenAI API, Pydantic, Docker, AWS, GCP
工作经验: 5 年
薪资范围: 60000 - 85000 EUR