offerpai/offerpai_python_ai
7
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

重构简历优化

Browse Source
This commit is contained in:
zk
2026-06-23 18:21:30 +08:00
parent 1edc28e332
commit 2f38c80207
11 changed files with 99 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/ai/model_config.py
+6 -2
View File
@@ -44,14 +44,18 @@ class ResumeExtractorModel:
PARSE = LLM.DOUBAO_PRO_32K.create(temperature=0)
class ResumePolisherModel:
"""简历段落润色模块"""
# 段落润色：仅做格式/错字/表达优化，不改内容，低温度保证稳定
POLISH = LLM.DEEPSEEK_V4_FLASH.create(temperature=0.2)
class DiagnoserModel:
"""简历诊断模块"""
# 模块诊断：逐条分析经历记录的问题(错别字/无量化/弱相关等)
MODULE = LLM.DEEPSEEK_V4_FLASH.create(temperature=0)
# 整体评价：汇总所有诊断结果生成总结性评语
SUMMARY = LLM.DEEPSEEK_V4_FLASH.create(temperature=0.3)
# 内容润色：用户编辑后的文本做专业润色
POLISH = LLM.DEEPSEEK_V4_FLASH.create(temperature=0.3)
class BrowserPlugModel:
app/ai/resume_diagnoser/diagnoser.py
+1 -40
View File
@@ -7,7 +7,7 @@ from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from app.ai.model_config import DiagnoserModel
from app.ai.resume_diagnoser.prompts import DIAGNOSE_MODULE_PROMPT, SUMMARY_PROMPT, POLISH_PROMPT
from app.ai.resume_diagnoser.prompts import DIAGNOSE_MODULE_PROMPT, SUMMARY_PROMPT
from app.core.logger import log
from app.tool.json_helper import parse_llm_json
@@ -54,45 +54,6 @@ async def generate_summary(grade: str, urgent_total: int, important_total: int,
return "简历诊断已完成，请查看各模块的详细诊断结果。"
_polish_chain = (
ChatPromptTemplate.from_messages([("system", POLISH_PROMPT), ("human", "请开始优化。")])
| DiagnoserModel.POLISH
| StrOutputParser()
)
async def polish_content(module_type: str, reference_content: list[dict] | str | None,
user_content: list[str], is_summary: bool) -> list[str]:
"""润色用户编辑后的文本"""
ref_text = ""
if reference_content:
if isinstance(reference_content, list):
ref_text = "\n".join(
item.get("text", "") if isinstance(item, dict) else str(item)
for item in reference_content
)
else:
ref_text = str(reference_content)
if not ref_text:
ref_text = "无"
inp = {
"module_type": module_type,
"reference_content": ref_text,
"user_content": "\n".join(user_content),
"summary_constraint": "- 注意：此模块只能输出一个段落，数组只能有一个元素" if is_summary else "",
}
try:
raw = await _polish_chain.ainvoke(inp)
result = parse_llm_json(raw)
if isinstance(result, list):
return [str(item) for item in result]
return [str(result)]
except Exception as e:
log.warning(f"AI润色失败: {e}")
return user_content
async def _safe_invoke(task: dict) -> dict:
"""单条记录诊断，失败返回空结果"""
module_type = task.get("module_type", "unknown")
app/ai/resume_diagnoser/prompts.py
-23
View File
@@ -82,26 +82,3 @@ SUMMARY_PROMPT = """你是一位资深简历顾问。请根据以下简历诊断
4. 一句鼓励或行动建议
直接输出评价文本，不要输出JSON或其他格式标记。控制在200字以内。"""
POLISH_PROMPT = """你是一位资深简历顾问。请对用户提供的简历描述文本进行润色优化，让语言更精练、更专业。
## 模块类型
{module_type}
## AI 之前的优化版本（仅供参考）
{reference_content}
## 用户提交的文本（以此为主进行优化）
{user_content}
## 优化要求
- 以用户提交的文本为主体进行润色，AI之前的版本仅作参考
- 让语言更精练、更专业，去除冗余表达
- 尽量使用数据量化成果
- 保持原意不变，不凭空捏造内容
- 输出为 JSON 数组格式，每个元素是一个段落的纯文本
{summary_constraint}
## 输出格式
严格输出 JSON 数组，不要输出其他内容：
["优化后的段落1", "优化后的段落2"]"""
app/ai/resume_polisher/__init__.py
View File
app/ai/resume_polisher/polisher.py
+36
View File
@@ -0,0 +1,36 @@
"""简历段落润色 AI 引擎：仅做格式/错字/表达层面的优化"""
import json
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from app.ai.model_config import ResumePolisherModel
from app.ai.resume_polisher.prompts import POLISH_PROMPT
from app.core.logger import log
from app.tool.json_helper import parse_llm_json
# 润色链（StrOutputParser 拿原始文本，再手动解析 JSON，避免 markdown 代码块导致解析失败）
_polish_chain = (
ChatPromptTemplate.from_messages([("system", POLISH_PROMPT), ("human", "请开始润色。")])
| ResumePolisherModel.POLISH
| StrOutputParser()
)
async def polish_paragraphs(content: list[str]) -> list[str]:
"""对段落数组做表达层面的润色，返回与输入等长的数组；失败兜底原样返回"""
if not content:
return []
inp = {"content": json.dumps(content, ensure_ascii=False)}
try:
raw = await _polish_chain.ainvoke(inp)
result = parse_llm_json(raw)
if isinstance(result, list) and len(result) == len(content):
return [str(item) for item in result]
log.warning(f"AI润色返回结果不符合预期, 原样返回: {result}")
return content
except Exception as e:
log.warning(f"AI润色失败: {e}")
return content
app/ai/resume_polisher/prompts.py
+21
View File
@@ -0,0 +1,21 @@
"""简历段落润色 Prompt 模板"""
POLISH_PROMPT = """你是一位严谨的简历文字校对助手。请对用户提交的简历段落进行"表面润色"，只做表达层面的优化。
## 优化范围（只允许做这些）
- 修正错别字、标点、语法错误
- 优化文本格式与排版（如多余空格、断句、全半角混用）
- 让表达更通顺、专业，去除明显口语化和冗余措辞
## 严格禁止（绝对不能做）
- 不得改变原意，不得增加或删除任何信息点
- 不得编造、补充任何内容（尤其禁止凭空添加数字、量化成果、技能、成就）
- 不得改变段落的数量和顺序
## 输入
用户提交的段落数组（每个元素是一个段落）：
{content}
## 输出格式
严格输出 JSON 数组，元素个数和顺序必须与输入完全一致，不要输出其他任何内容：
["润色后的段落1", "润色后的段落2"]"""
app/api/resume.py
+15 -2
View File
@@ -1,10 +1,11 @@
"""简历上传解析接口"""
from fastapi import APIRouter, UploadFile, File
from pydantic import BaseModel, Field
from app.core.context import RequestContext
from app.core.database import get_db
from app.services.resume_parse_service import ResumeParseService
from app.services.resume_service import ResumeService
router = APIRouter(prefix="/resume", tags=["简历"])
@@ -15,7 +16,7 @@ async def upload_resume(file: UploadFile = File(...)):
user_id = RequestContext.user_id.get()
content = await file.read()
service = ResumeParseService()
service = ResumeService()
# 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
@@ -23,3 +24,15 @@ async def upload_resume(file: UploadFile = File(...)):
async for session in get_db():
resume_id = await service.save_resume(session, user_id, file.filename, parsed)
return {"resumeId": resume_id}
class PolishParam(BaseModel):
content: list[str] = Field(..., description="待润色的简历段落文本数组")
@router.post("/polish", summary="AI润色简历段落")
async def polish_resume(param: PolishParam):
"""对前端提交的简历段落做表达层面的润色（格式/错字/表达），不改内容，返回等长数组"""
service = ResumeService()
result = await service.polish_paragraphs(param.content)
return {"content": result}
app/api/resume_diagnose.py
+1 -23
View File
@@ -5,7 +5,7 @@ import time
from fastapi import APIRouter, Depends
from pydantic import BaseModel, Field
from app.ai.resume_diagnoser.diagnoser import diagnose_all, generate_summary, polish_content
from app.ai.resume_diagnoser.diagnoser import diagnose_all, generate_summary
from app.core.auth import func_permission
from app.core.context import RequestContext
from app.core.database import get_db
@@ -98,25 +98,3 @@ async def feedback_issue(issue_id: int, param: FeedbackParam):
async for session in get_db():
service = ResumeDiagnoseService(session)
await service.update_feedback(issue_id, user_id, param.user_feedback)
class PolishParam(BaseModel):
content: list[str] = Field(..., description="用户编辑后的文本段落数组")
@router.post("/issue/{issue_id}/polish", summary="AI润色用户编辑的文本")
async def polish_issue_content(issue_id: int, param: PolishParam):
"""基于诊断问题上下文，AI润色用户编辑后的文本"""
user_id = RequestContext.user_id.get()
async for session in get_db():
service = ResumeDiagnoseService(session)
ctx = await service.get_issue_for_polish(issue_id, user_id)
result = await polish_content(
module_type=ctx["module_label"],
reference_content=ctx["optimized_content"],
user_content=param.content,
is_summary=ctx["is_summary"],
)
return {"content": result}
app/services/resume_diagnose_service.py
-15
View File
@@ -153,21 +153,6 @@ class ResumeDiagnoseService:
issue.user_feedback = user_feedback
await self.session.flush()
async def get_issue_for_polish(self, issue_id: int, user_id: int) -> dict:
"""获取 issue 润色所需的上下文信息"""
result = await self.session.execute(
select(ResumeDiagnosisIssue).where(
ResumeDiagnosisIssue.id == issue_id, ResumeDiagnosisIssue.user_id == user_id))
issue = result.scalar_one_or_none()
if issue is None:
raise ValueError("诊断问题不存在")
return {
"module_type": issue.module_type,
"module_label": _MODULE_LABELS.get(issue.module_type, issue.module_type),
"optimized_content": issue.optimized_content,
"is_summary": issue.module_type == "summary",
}
# ===== 工具函数 =====
app/services/resume_parse_service.py → app/services/resume_service.py
+10 -2
View File
@@ -1,4 +1,4 @@
"""简历解析 Service
"""简历 Service
上传简历文件 → 解析为纯文本 → AI 两阶段并行结构化 → 写入数据库。
依赖：file_parser（文件解析工具）、resume_extractor（AI两阶段并行提取）
@@ -11,6 +11,7 @@ import shortuuid
from sqlalchemy.ext.asyncio import AsyncSession
from app.ai.resume_extractor.extractor import extract_all
from app.ai.resume_polisher.polisher import polish_paragraphs
from app.core.logger import log
from app.models.user_resume import UserResume
from app.models.user_resume_competition import UserResumeCompetition
@@ -22,7 +23,7 @@ from app.tool.file_parser import parse_to_text
from app.tool.snowflake import next_id
class ResumeParseService:
class ResumeService:
async def parse_and_extract(self, filename: str, content: bytes) -> dict:
"""文件解析 + AI 两阶段并行结构化，不涉及数据库操作"""
@@ -37,6 +38,13 @@ class ResumeParseService:
log.info("AI两阶段并行结构化提取完成")
return parsed
async def polish_paragraphs(self, content: list[str]) -> list[str]:
"""对简历段落做表达层面的润色（格式/错字/表达），不涉及数据库操作"""
log.info(f"开始简历段落润色, 段落数={len(content)}")
result = await polish_paragraphs(content)
log.info("简历段落润色完成")
return result
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()