简历信息提取系统，使用Pydantic模型定义数据结构，并通过大语言模型（如GPT）从非结构化的简历文本中提取结构化信息。以下是详细解析：
核心功能
-
数据建模：用Pydantic的
Resume类严格定义简历字段和校验规则。 -
格式转换：自动统一日期格式（如
1990-05-15→05-15-1990）。 -
大模型交互：通过Prompt工程让AI提取信息并返回标准JSON。
核心代码
from datetime import datetime, date
from typing import List, Optional
from pydantic import BaseModel, Field, field_validator, EmailStr, model_validator# 定义这个pydantic模型是关键的关键
class Resume(BaseModel):name: Optional[str] = Field(None, description="求职者姓名，如果没找到就置为空字符串")city: Optional[str] = Field(None, description="求职者居住地，如果没找到就置为空字符串")birthday: Optional[str] = Field(None, description="求职者生日，如果没找到就置为空字符串")phone: Optional[str] = Field(None, description="求职者手机号，如果没找到就置为空字符串")email: Optional[str] = Field(None, description="求职者邮箱，如果没找到就置为空字符串")education: Optional[List[str]] = Field(None, description="求职者教育背景")experience: Optional[List[str]] = Field(None, description="求职者工作或实习经历，如果没找到就置为空字符串")project: Optional[List[str]] = Field(None, description="求职者项目经历，如果没找到就置为空字符串")certificates: Optional[List[str]] = Field(None, description="求职者资格证书，如果没找到就置为空字符串")@field_validator("birthday", mode="before")def validate_and_convert_date(cls, raw_date):if raw_date is None:return Noneif isinstance(raw_date, str):# List of acceptable date formatsdate_formats = ['%d-%m-%Y', '%Y-%m-%d', '%d/%m/%Y', '%m-%d-%Y']for fmt in date_formats:try:# Attempt to parse the date string with the current formatparsed_date = datetime.strptime(raw_date, fmt).date()# Return the date in MM-DD-YYYY format as a stringreturn parsed_date.strftime('%m-%d-%Y')except ValueError:continue # Try the next format# If none of the formats match, raise an errorraise ValueError(f"Invalid date format for 'consultation_date'. Expected one of: {', '.join(date_formats)}.")if isinstance(raw_date, date):# Convert date object to MM-DD-YYYY formatreturn raw_date.strftime('%m-%d-%Y')raise ValueError("Invalid type for 'consultation_date'. Must be a string or a date object.")class ResumeOpenAI:def __init__(self):self.resume_profile = Resume()self.output_schema = self.resume_profile.model_json_schema()self.template = """You are an expert in analyzing resumes. Use the following JSON schema to extract relevant information:```json{output_schema}```jsonExtract the information from the following document and provide a structured JSON response strictly adhering to the schema above. Please remove any ```json ``` characters from the output. Do not make up any information. If a field cannot be extracted, mark it as `n/a`.Document:----------------{resume_content}----------------"""def create_prompt(self, output_schema, resume_content):return self.template.format(output_schema=output_schema,resume_content=resume_content)def run(self, resume_content):try:response = client.chat.completions.create(model=chat_model,# 不是所有模型都支持response_format，要看一下调用的模型是否支持这个参数# 千问、智谱的模型一般支持response_format={ "type": "json_object" },messages=[{"role": "system", "content": "你是一位专业的简历信息提取专家。"},{"role": "user", "content": self.create_prompt(self.output_schema, resume_content)}],)result = response.choices[0].message.contentexcept Exception as e:print(f"Error occurred: {e}")return resultresume_openai = ResumeOpenAI()
