89 lines
3.7 KiB
Python
89 lines
3.7 KiB
Python
|
from fastapi import APIRouter, Depends, HTTPException, Query
|
|||
|
|
from sqlalchemy.orm import Session
|
|||
|
|
from pydantic import BaseModel
|
|||
|
|
from openai import OpenAI
|
|||
|
|
|
|||
|
|
from app.core.database import get_db
|
|||
|
|
from app.models.requirement import Requirement
|
|||
|
|
from app.utils.common_util import SuccessData
|
|||
|
|
from app.core.security import get_current_user
|
|||
|
|
|
|||
|
|
client = OpenAI(
|
|||
|
|
api_key="sk-P7bm1Ioe7eovIWkbabAbY8yEON2VFu4RcHqumAFCfoxDVDdi",
|
|||
|
|
base_url="https://api.lkeap.cloud.tencent.com/v1"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
messages = [
|
|||
|
|
# {'role': 'system', 'content': '您现在是一个代码质量审核专家，您的任务是结合业务需求代码进行审核，判断代码是否符合需求'},
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
|
|||
|
|
class WorkScore(BaseModel):
|
|||
|
|
prompt: str
|
|||
|
|
requirement_id: int
|
|||
|
|
|
|||
|
|
|
|||
|
|
router = APIRouter(prefix="/chat", tags=["chat"])
|
|||
|
|
|
|||
|
|
|
|||
|
|
@router.post("/work-score", description="工作内容审核")
|
|||
|
|
async def work_chat(work_score: WorkScore,
|
|||
|
|
db: Session = Depends(get_db),
|
|||
|
|
current_user: str = Depends(get_current_user)):
|
|||
|
|
requirement = db.query(Requirement).filter(Requirement.id == work_score.requirement_id).first()
|
|||
|
|
if not requirement:
|
|||
|
|
raise HTTPException(status_code=400, detail="需求不存在")
|
|||
|
|
|
|||
|
|
prompt = f"""
|
|||
|
|
接下来，需要您根据提供的需求，对以下代码进行审核，有如下要求：
|
|||
|
|
1.判断代码是否符合需求，尽量详细地给出判断依据
|
|||
|
|
2.对代码的整体质量进行打分，满分为 100 分，打分时可以从代码的结构、性能等方面综合考量
|
|||
|
|
3..对代码的完成度进行打分，满分为 100 分，主要看代码是否实现了需求中的主要功能
|
|||
|
|
4.对代码的可读性进行打分，满分为 100 分，依据代码的注释、变量命名等是否规范易懂来评判
|
|||
|
|
5.对代码的可维护性进行打分，满分为 100 分，可从代码是否模块化、是否易于修改等方面考虑
|
|||
|
|
6.对代码的可扩展性进行打分，满分为 100 分，评估代码是否方便增加新功能或修改现有功能
|
|||
|
|
7.对代码是否符合需求业务进行打分，满分为 100 分，判断代码是否契合业务逻辑和目标
|
|||
|
|
8.综合结合 2-7 的分数，整体打分，满分为 100 分，给出一个综合的评判分数
|
|||
|
|
9.最终以 markdown 表格格式输出，尽量让表格呈现清晰、易读
|
|||
|
|
需求：```
|
|||
|
|
{requirement.description}
|
|||
|
|
```
|
|||
|
|
代码：```
|
|||
|
|
{work_score.prompt}
|
|||
|
|
```
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
print(">>> prompt: \n%s" % prompt)
|
|||
|
|
messages.append({'role': 'system', 'content': prompt})
|
|||
|
|
stream = client.chat.completions.create(
|
|||
|
|
model="deepseek-r1",
|
|||
|
|
messages=messages,
|
|||
|
|
stream=True
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
reasoning_content = "" # 定义完整思考过程
|
|||
|
|
answer_content = "" # 定义完整回复
|
|||
|
|
is_answering = False # 判断是否结束思考过程并开始回复
|
|||
|
|
for chunk in stream:
|
|||
|
|
if not getattr(chunk, 'choices', None):
|
|||
|
|
print("\n" + "=" * 20 + "Token 使用情况" + "=" * 20 + "\n")
|
|||
|
|
print(chunk.usage)
|
|||
|
|
continue
|
|||
|
|
delta = chunk.choices[0].delta
|
|||
|
|
# 处理空内容情况
|
|||
|
|
if not getattr(delta, 'reasoning_content', None) and not getattr(delta, 'content', None):
|
|||
|
|
continue
|
|||
|
|
# 处理开始回答的情况
|
|||
|
|
if not getattr(delta, 'reasoning_content', None) and not is_answering:
|
|||
|
|
print("\n" + "=" * 20 + "完整回复" + "=" * 20 + "\n")
|
|||
|
|
is_answering = True
|
|||
|
|
# 处理思考过程
|
|||
|
|
if getattr(delta, 'reasoning_content', None):
|
|||
|
|
print(delta.reasoning_content, end='', flush=True)
|
|||
|
|
reasoning_content += delta.reasoning_content
|
|||
|
|
# 处理回复内容
|
|||
|
|
elif getattr(delta, 'content', None):
|
|||
|
|
print(delta.content, end='', flush=True)
|
|||
|
|
answer_content += delta.content
|
|||
|
|
return SuccessData(answer_content)
|