Merge pull request #3 from stardrophere/backend_optimize

Backend optimize

.gitignore

@@ -37,9 +37,6 @@ MANIFEST
 *.manifest
 *.spec
 
-# uv
-*.lock
-
 # Installer logs
 pip-log.txt
 pip-delete-this-directory.txt
@@ -192,4 +189,6 @@ cython_debug/
 
 **/data/*
 **/docker/*
-backend/app/static/*
+backend/app/static/*
+
+test*.*

backend/app/crud/crud_source.py

@@ -24,6 +24,10 @@ def get_multi(db: Session, skip: int = 0, limit: int = 100) -> List[InfoSource]:
 def create(db: Session, obj_in: InfoSourceCreate) -> InfoSource:
     """创建新的信息源"""
     db_obj = InfoSource(**obj_in.model_dump())
+    exits =db.query(InfoSource).filter(InfoSource.source_name == db_obj.source_name).first()
+    if exits:
+        db.close()
+        return db_obj
     try:
         db.add(db_obj)
         db.commit()

backend/app/main.py

@@ -1,10 +1,11 @@
 # app/main.py
 import logging
 import os
-from fastapi.responses import FileResponse
+from pathlib import Path
+from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
 import httpx
 from contextlib import asynccontextmanager
-from fastapi import FastAPI, staticfiles
+from fastapi import FastAPI, HTTPException, Request, staticfiles
 from fastapi.middleware.cors import CORSMiddleware
 from dotenv import load_dotenv
 
@@ -112,14 +113,25 @@ app.add_middleware(
 # 版本控制
 app.include_router(api_router, prefix="/api/v1")
 
-# 把目录改成static对应我们放dist内容的路径就可以
-app.mount("/", staticfiles.StaticFiles(directory="app/static", html=True), name="static")
-
 # 只需要保留API的优先匹配，catch_all可以简化成这样
 @app.get("/api/{full_path:path}")
 async def api_not_found(full_path: str):
     return {"detail": "API Not Found"}
 
+staticPath = staticfiles.StaticFiles(directory="app/static", html=True)
+
+# 把目录改成static对应我们放dist内容的路径就可以
+app.mount("/", staticPath, name="static")
+
+INDEX_HTML = Path("app/static/index.html").read_text(encoding="utf-8")
+
+@app.exception_handler(404)
+async def not_found_handler(request: Request, exc: HTTPException):
+    # 如果是API路径才返回404，前端路径走catch-all不会进这里
+    if request.url.path.startswith("/api/"):
+        return JSONResponse({"detail": "Not Found"}, status_code=404)
+    return HTMLResponse(INDEX_HTML)
+
 # 健康检查
 @app.get("/", tags=["健康检查"])
 async def root():

backend/app/services/fetcher_service.py

@@ -26,9 +26,9 @@ SIMILARITY_THRESHOLD = float(os.getenv("SIMILARITY_THRESHOLD", 0.72))
 API_BASE_URL = os.getenv("API_BASE_URL", "https://newsnow.busiyi.world/api/s")
 EMBEDDING_MODEL_PATH = os.getenv("EMBEDDING_MODEL_PATH", "")
 
-print("正在加载 BAAI/bge-m3 向量模型...")
+print("正在加载模型...")
 # 全局单例
-embedder_model = SentenceTransformer(EMBEDDING_MODEL_PATH, local_files_only=True, device="cuda")
+embedder_model = SentenceTransformer(EMBEDDING_MODEL_PATH, local_files_only=True)
 print("模型加载完成。")
 
 

backend/pyproject.toml

@@ -49,7 +49,6 @@ dependencies = [
     "safetensors==0.7.0",
     "scikit-learn==1.8.0",
     "scipy==1.17.1",
-    "sentence-transformers==5.2.3",
     "shellingham==1.5.4",
     "sniffio==1.3.1",
     "sqlalchemy==2.0.48",
@@ -57,8 +56,6 @@ dependencies = [
     "sympy==1.14.0",
     "threadpoolctl==3.6.0",
     "tokenizers==0.22.2",
-    "torch==2.10.0",
-    "torchvision==0.25.0",
     "tqdm==4.67.3",
     "transformers==5.3.0",
     "typer==0.24.1",
@@ -68,4 +65,16 @@ dependencies = [
     "tzlocal==5.3.1",
     "urllib3==2.6.3",
     "uvicorn==0.41.0",
+    "torch==2.11.0+cpu",
+    "torchvision==0.26.0+cpu",
+    "torchaudio==2.11.0+cpu",
+    "sentence-transformers>=5.3.0",
 ]
+
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+default = false
+
+[tool.uv]
+index-strategy = "unsafe-best-match"

dockerfile

@@ -20,7 +20,7 @@ WORKDIR /backend
 COPY backend/pyproject.toml backend/uv.lock ./
 RUN --mount=type=cache,target=/root/.cache/uv \
     pip install --no-cache-dir uv && \
-    uv sync --frozen --no-dev
+    uv sync --frozen --no-dev --index https://pypi.tuna.tsinghua.edu.cn/simple/
 
 # 复制后端代码
 COPY backend/app ./app