offerpai/offerpai_python_ai
6
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

添加Ai 简历解析

Browse Source
This commit is contained in:
zk
2026-04-02 16:01:08 +08:00
parent 4de721ffca
commit ff0993e431
14 changed files with 441 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/ai/models.py
+2
View File
@@ -27,6 +27,8 @@ class LLM(Enum):
DOUBAO_LITE_128K = ("doubao-lite-128k", *_VOLCENGINE)
DEEPSEEK_V3 = ("deepseek-v3-250324", *_VOLCENGINE)
DEEPSEEK_R1 = ("deepseek-r1-250528", *_VOLCENGINE)
DOUBAO_SEED_LIST = ("doubao-seed-2-0-lite-260215", *_VOLCENGINE)
DOUBAO_SEED_PRO = ("doubao-seed-2-0-pro-260215", *_VOLCENGINE)
# 心缘
GPT_4O = ("gpt-4o", *_CARDIAC)
app/api/resume.py
+25
View File
@@ -0,0 +1,25 @@
"""简历上传解析接口"""
from fastapi import APIRouter, UploadFile, File
from app.core.context import RequestContext
from app.core.database import get_db
from app.services.resume_parse_service import ResumeParseService
router = APIRouter(prefix="/resume", tags=["简历"])
@router.post("/upload", summary="上传简历文件并AI解析")
async def upload_resume(file: UploadFile = File(...)):
"""上传简历文件（PDF/Word/TXT），AI解析后生成结构化简历，返回简历ID"""
user_id = RequestContext.user_id.get()
content = await file.read()
service = ResumeParseService()
# 文件解析 + AI 结构化（不占数据库连接）
parsed = await service.parse_and_extract(file.filename, content)
# 短事务：只做数据库写入
resume_id = None
async for session in get_db():
resume_id = await service.save_resume(session, user_id, file.filename, parsed)
return {"resumeId": resume_id}
app/main.py
+2
View File
@@ -31,8 +31,10 @@ app.add_middleware(
# ========== 路由注册 ==========
from app.api.health import router as health_router
from app.api.resume import router as resume_router
app.include_router(health_router)
app.include_router(resume_router)
# ==============================
if __name__ == "__main__":
app/models/user_resume.py
+40
View File
@@ -0,0 +1,40 @@
"""用户简历表（bg_user_resume）
简历维度信息 + 个人基本信息合并存储
"""
from datetime import datetime
from typing import Optional
from sqlalchemy import BigInteger, Integer, String, DateTime, JSON
from sqlalchemy.orm import Mapped, mapped_column
from app.core.database import Base
class UserResume(Base):
"""用户简历表 bg_user_resume"""
__tablename__ = "bg_user_resume"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
user_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="用户ID")
# 简历维度信息
resume_name: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="简历名称")
target_position: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="目标岗位")
is_default: Mapped[int] = mapped_column(Integer, default=0, comment="是否默认简历 0=否 1=是")
sort_order: Mapped[Optional[int]] = mapped_column(Integer, nullable=True, comment="排序序号")
# 个人信息
avatar_url: Mapped[Optional[str]] = mapped_column(String(512), nullable=True, comment="头像URL")
name: Mapped[Optional[str]] = mapped_column(String(64), nullable=True, comment="真实姓名")
email: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="邮箱")
mobile_number: Mapped[Optional[str]] = mapped_column(String(20), nullable=True, comment="手机号码")
city: Mapped[Optional[str]] = mapped_column(String(64), nullable=True, comment="所在城市")
wechat_number: Mapped[Optional[str]] = mapped_column(String(64), nullable=True, comment="微信号")
portfolio_url: Mapped[Optional[str]] = mapped_column(String(512), nullable=True, comment="作品集链接")
skills: Mapped[Optional[list]] = mapped_column(JSON, nullable=True, comment="技能标签列表")
certificates: Mapped[Optional[list]] = mapped_column(JSON, nullable=True, comment="证书标签列表")
summary: Mapped[Optional[str]] = mapped_column(String(2000), nullable=True, comment="个人概述")
create_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, comment="创建时间")
update_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, onupdate=datetime.now, comment="更新时间")
app/models/user_resume_competition.py
+25
View File
@@ -0,0 +1,25 @@
"""简历-竞赛经历表（bg_user_resume_competition）"""
from datetime import datetime
from typing import Optional
from sqlalchemy import BigInteger, Integer, String, DateTime, JSON
from sqlalchemy.orm import Mapped, mapped_column
from app.core.database import Base
class UserResumeCompetition(Base):
"""简历-竞赛经历表 bg_user_resume_competition"""
__tablename__ = "bg_user_resume_competition"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
resume_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联bg_user_resume.id")
user_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="用户ID")
competition_name: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="竞赛名称")
award: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="获奖情况")
award_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="获奖时间，格式：2023.07")
description: Mapped[Optional[list]] = mapped_column(JSON, nullable=True, comment="描述段落 [{id, text}]")
sort_order: Mapped[Optional[int]] = mapped_column(Integer, nullable=True, comment="排序序号")
create_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, comment="创建时间")
update_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, onupdate=datetime.now, comment="更新时间")
app/models/user_resume_education.py
+28
View File
@@ -0,0 +1,28 @@
"""简历-教育经历表（bg_user_resume_education）"""
from datetime import datetime
from typing import Optional
from sqlalchemy import BigInteger, Integer, String, DateTime, JSON
from sqlalchemy.orm import Mapped, mapped_column
from app.core.database import Base
class UserResumeEducation(Base):
"""简历-教育经历表 bg_user_resume_education"""
__tablename__ = "bg_user_resume_education"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
resume_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联bg_user_resume.id")
user_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="用户ID")
school: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="学校名称")
major: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="专业")
degree: Mapped[Optional[str]] = mapped_column(String(32), nullable=True, comment="学历：大专/本科/硕士/博士")
study_type: Mapped[Optional[str]] = mapped_column(String(32), nullable=True, comment="学习形式：全日制/非全日制")
start_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="开始时间，格式：2023.09")
end_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="结束时间，格式：2024.06")
description: Mapped[Optional[list]] = mapped_column(JSON, nullable=True, comment="描述段落 [{id, text}]")
sort_order: Mapped[Optional[int]] = mapped_column(Integer, nullable=True, comment="排序序号")
create_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, comment="创建时间")
update_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, onupdate=datetime.now, comment="更新时间")
app/models/user_resume_internship.py
+26
View File
@@ -0,0 +1,26 @@
"""简历-实习经历表（bg_user_resume_internship）"""
from datetime import datetime
from typing import Optional
from sqlalchemy import BigInteger, Integer, String, DateTime, JSON
from sqlalchemy.orm import Mapped, mapped_column
from app.core.database import Base
class UserResumeInternship(Base):
"""简历-实习经历表 bg_user_resume_internship"""
__tablename__ = "bg_user_resume_internship"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
resume_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联bg_user_resume.id")
user_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="用户ID")
company_name: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="公司名称")
position: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="职位")
start_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="开始时间，格式：2023.06")
end_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="结束时间，格式：2023.09")
description: Mapped[Optional[list]] = mapped_column(JSON, nullable=True, comment="描述段落 [{id, text}]")
sort_order: Mapped[Optional[int]] = mapped_column(Integer, nullable=True, comment="排序序号")
create_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, comment="创建时间")
update_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, onupdate=datetime.now, comment="更新时间")
app/models/user_resume_project.py
+27
View File
@@ -0,0 +1,27 @@
"""简历-项目经历表（bg_user_resume_project）"""
from datetime import datetime
from typing import Optional
from sqlalchemy import BigInteger, Integer, String, DateTime, JSON
from sqlalchemy.orm import Mapped, mapped_column
from app.core.database import Base
class UserResumeProject(Base):
"""简历-项目经历表 bg_user_resume_project"""
__tablename__ = "bg_user_resume_project"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
resume_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联bg_user_resume.id")
user_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="用户ID")
company_name: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="所属公司")
project_name: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="项目名称")
role: Mapped[Optional[str]] = mapped_column(String(64), nullable=True, comment="担任角色")
start_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="开始时间，格式：2023.06")
end_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="结束时间，格式：2023.09")
description: Mapped[Optional[list]] = mapped_column(JSON, nullable=True, comment="描述段落 [{id, text}]")
sort_order: Mapped[Optional[int]] = mapped_column(Integer, nullable=True, comment="排序序号")
create_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, comment="创建时间")
update_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, onupdate=datetime.now, comment="更新时间")
app/models/user_resume_work.py
+26
View File
@@ -0,0 +1,26 @@
"""简历-工作经历表（bg_user_resume_work）"""
from datetime import datetime
from typing import Optional
from sqlalchemy import BigInteger, Integer, String, DateTime, JSON
from sqlalchemy.orm import Mapped, mapped_column
from app.core.database import Base
class UserResumeWork(Base):
"""简历-工作经历表 bg_user_resume_work"""
__tablename__ = "bg_user_resume_work"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
resume_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联bg_user_resume.id")
user_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="用户ID")
company_name: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="公司名称")
position: Mapped[Optional[str]] = mapped_column(String(128), nullable=True, comment="职位")
start_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="开始时间，格式：2023.06")
end_date: Mapped[Optional[str]] = mapped_column(String(16), nullable=True, comment="结束时间，格式：2023.09")
description: Mapped[Optional[list]] = mapped_column(JSON, nullable=True, comment="描述段落 [{id, text}]")
sort_order: Mapped[Optional[int]] = mapped_column(Integer, nullable=True, comment="排序序号")
create_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, comment="创建时间")
update_time: Mapped[datetime] = mapped_column(DateTime, default=datetime.now, onupdate=datetime.now, comment="更新时间")
app/services/resume_parse_service.py
+208
View File
@@ -0,0 +1,208 @@
"""简历解析 Service
上传简历文件 → 解析为纯文本 → AI 结构化 → 写入数据库。
依赖：file_parser（文件解析工具）、LLM（AI模型）
使用表：bg_user_resume（主表）、bg_user_resume_education/work/internship/project/competition（5张子表）
"""
import asyncio
import json
import shortuuid
from langchain_core.messages import SystemMessage, HumanMessage
from sqlalchemy.ext.asyncio import AsyncSession
from app.ai.models import LLM
from app.core.logger import log
from app.models.user_resume import UserResume
from app.models.user_resume_competition import UserResumeCompetition
from app.models.user_resume_education import UserResumeEducation
from app.models.user_resume_internship import UserResumeInternship
from app.models.user_resume_project import UserResumeProject
from app.models.user_resume_work import UserResumeWork
from app.tool.file_parser import parse_to_text
from app.tool.snowflake import next_id
_SYSTEM_PROMPT = """你是一个专业的简历解析助手。请将用户提供的简历纯文本解析为结构化JSON。
输出格式要求（严格按此JSON结构输出，不要输出任何其他内容）：
```json
{
"name": "姓名",
"email": "邮箱",
"mobileNumber": "手机号",
"city": "所在城市",
"wechatNumber": "微信号（如有）",
"portfolioUrl": "作品集链接（如有）",
"skills": ["技能1", "技能2"],
"certificates": ["证书1", "证书2"],
"summary": "个人概述/自我评价",
"education": [
{
"school": "学校名称",
"major": "专业",
"degree": "学历（大专/本科/硕士/博士）",
"studyType": "学习形式（全日制/非全日制）",
"startDate": "2020.09",
"endDate": "2024.06",
"description": ["描述段落1", "描述段落2"]
}
],
"work": [
{
"companyName": "公司名称",
"position": "职位",
"startDate": "2024.07",
"endDate": "2025.03",
"description": ["工作描述段落1", "工作描述段落2"]
}
],
"internship": [
{
"companyName": "公司名称",
"position": "实习职位",
"startDate": "2023.06",
"endDate": "2023.09",
"description": ["实习描述段落1"]
}
],
"project": [
{
"companyName": "所属公司（如有）",
"projectName": "项目名称",
"role": "担任角色",
"startDate": "2023.03",
"endDate": "2023.12",
"description": ["项目描述段落1"]
}
],
"competition": [
{
"competitionName": "竞赛名称",
"award": "获奖情况",
"awardDate": "2023.07",
"description": ["竞赛描述段落1"]
}
]
}
```
规则：
1. 时间格式统一为 YYYY.MM（如 2023.09），如果只有年份则写 YYYY.01
2. 没有的字段填 null，没有的数组填 []
3. description 是字符串数组，每个元素是一个描述段落
4. 区分工作经历和实习经历：明确标注"实习"的归入 internship，其余归入 work
5. 只输出 JSON，不要输出任何解释文字"""
class ResumeParseService:
async def parse_and_extract(self, filename: str, content: bytes) -> dict:
"""文件解析 + AI 结构化，不涉及数据库操作"""
# 1. 文件解析为纯文本（同步操作丢线程池）
log.info(f"开始解析简历文件: {filename}")
text = await asyncio.to_thread(parse_to_text, filename, content)
if not text or not text.strip():
raise ValueError("文件内容为空，无法解析")
log.info(f"文件解析完成，文本长度: {len(text)}")
# 2. AI 结构化解析
log.info("开始AI结构化解析")
parsed = await self._ai_parse(text)
log.info("AI结构化解析完成")
return parsed
async def _ai_parse(self, text: str) -> dict:
"""调用 AI 将纯文本解析为结构化 JSON"""
llm = LLM.DOUBAO_SEED_PRO.create(temperature=0)
messages = [SystemMessage(content=_SYSTEM_PROMPT), HumanMessage(content=text)]
response = await llm.ainvoke(messages)
# 提取 JSON（兼容 markdown 代码块包裹）
raw = response.content.strip()
if raw.startswith("```"):
raw = raw.split("\n", 1)[1] if "\n" in raw else raw[3:]
raw = raw.rsplit("```", 1)[0]
return json.loads(raw)
async def save_resume(self, session: AsyncSession, user_id: int, filename: str, parsed: dict) -> int:
"""将解析结果写入主表 + 5张子表，返回简历ID"""
resume_id = next_id()
# 主表
resume = UserResume(
id=resume_id, user_id=user_id,
resume_name=filename.rsplit(".", 1)[0],
target_position=None, is_default=0, sort_order=0,
name=parsed.get("name"), email=parsed.get("email"),
mobile_number=parsed.get("mobileNumber"), city=parsed.get("city"),
wechat_number=parsed.get("wechatNumber"), portfolio_url=parsed.get("portfolioUrl"),
skills=parsed.get("skills") or [], certificates=parsed.get("certificates") or [],
summary=parsed.get("summary"),
)
session.add(resume)
# 教育经历
for i, edu in enumerate(parsed.get("education") or []):
session.add(UserResumeEducation(
id=next_id(), resume_id=resume_id, user_id=user_id,
school=edu.get("school"), major=edu.get("major"),
degree=edu.get("degree"), study_type=edu.get("studyType"),
start_date=edu.get("startDate"), end_date=edu.get("endDate"),
description=_to_description_paragraphs(edu.get("description")),
sort_order=i,
))
# 工作经历
for i, work in enumerate(parsed.get("work") or []):
session.add(UserResumeWork(
id=next_id(), resume_id=resume_id, user_id=user_id,
company_name=work.get("companyName"), position=work.get("position"),
start_date=work.get("startDate"), end_date=work.get("endDate"),
description=_to_description_paragraphs(work.get("description")),
sort_order=i,
))
# 实习经历
for i, intern in enumerate(parsed.get("internship") or []):
session.add(UserResumeInternship(
id=next_id(), resume_id=resume_id, user_id=user_id,
company_name=intern.get("companyName"), position=intern.get("position"),
start_date=intern.get("startDate"), end_date=intern.get("endDate"),
description=_to_description_paragraphs(intern.get("description")),
sort_order=i,
))
# 项目经历
for i, proj in enumerate(parsed.get("project") or []):
session.add(UserResumeProject(
id=next_id(), resume_id=resume_id, user_id=user_id,
company_name=proj.get("companyName"), project_name=proj.get("projectName"),
role=proj.get("role"),
start_date=proj.get("startDate"), end_date=proj.get("endDate"),
description=_to_description_paragraphs(proj.get("description")),
sort_order=i,
))
# 竞赛经历
for i, comp in enumerate(parsed.get("competition") or []):
session.add(UserResumeCompetition(
id=next_id(), resume_id=resume_id, user_id=user_id,
competition_name=comp.get("competitionName"), award=comp.get("award"),
award_date=comp.get("awardDate"),
description=_to_description_paragraphs(comp.get("description")),
sort_order=i,
))
await session.flush()
log.info(f"简历保存完成，resumeId: {resume_id}")
return resume_id
def _to_description_paragraphs(texts: list[str] | None) -> list[dict] | None:
"""将字符串数组转为 [{id, text}] 格式的描述段落"""
if not texts:
return None
return [{"id": shortuuid.ShortUUID().random(length=8), "text": t} for t in texts if t]
app/tool/file_parser.py
+2 -2
View File
@@ -60,9 +60,9 @@ def parse_to_text(filename: str, content: bytes) -> str:
if suffix == ".pdf":
return parse_pdf(content)
elif suffix in (".docx", ".doc"):
elif suffix == ".docx":
return parse_docx(content)
elif suffix == ".txt":
return parse_txt(content)
else:
raise ValueError(f"不支持的文件类型: {suffix}，支持: .pdf, .docx, .doc, .txt")
raise ValueError(f"不支持的文件类型: {suffix}，支持: .pdf, .docx, .txt")
app/tool/snowflake.py
+10
View File
@@ -0,0 +1,10 @@
"""雪花 ID 生成工具"""
from snowflake import SnowflakeGenerator
_gen = SnowflakeGenerator(1)
def next_id() -> int:
"""生成一个雪花 ID"""
return next(_gen)