背景：

      vllm推理框架启动模型不具备api-key验证。需借助fastapi可以实现该功能

代码实现：

rom fastapi import FastAPI, Header, HTTPException, Request,Response
import httpx
import logging# 创建 FastAPI 应用
app = FastAPI()
logging.basicConfig(level=logging.DEBUG)
# 配置 vLLM 的服务地址
VLLM_BASE_URL = "http://localhost:25010"# 定义合法的 API Key 列表（可以根据需要扩展为数据库或配置文件）
VALID_API_KEYS = {"zml_123456789", "zml_1234567890"}# 中间件：验证 API Key
# 验证 API Key
async def verify_api_key(authorization: str = Header(None)):# 打印接收到的 Authorization 字段logging.debug(f"Received Authorization header: {authorization}")# 检查 Authorization 是否存在且以 "Bearer " 开头if not authorization or not isinstance(authorization, str) or not authorization.startswith("Bearer "):raise HTTPException(status_code=403, detail="Invalid Authorization Header")# 提取 API Keytry:api_key = authorization.split(" ")[1]  # 提取 "Bearer " 后的部分except IndexError:raise HTTPException(status_code=403, detail="Malformed Authorization Header")# 验证 API Key 是否合法if api_key not in VALID_API_KEYS:raise HTTPException(status_code=403, detail="Invalid API Key")# 代理路由：转发请求到 vLLM
@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
async def proxy(request: Request, path: str, authorization: str = Header(None)):# 验证 API Keylogging.debug(f"Received request with path: {path}")logging.debug(f"Received headers: {request.headers}")await verify_api_key(authorization)# 构造转发的目标 URLtarget_url = f"{VLLM_BASE_URL}/{path}"# 获取请求体和查询参数body = await request.body()query_params = request.query_params# 使用 httpx 转发请求async with httpx.AsyncClient() as client:# 根据请求方法转发response = await client.request(method=request.method,url=target_url,params=query_params,data=body,headers={key: value for key, value in request.headers.items() if key != "host"})# 返回 vLLM 的响应return Response(content=response.content, status_code=response.status_code, headers=dict(response.headers))

三、启动

uvicorn my_fastapi:app  --host=0.0.0.0 --port=12345
# my_fastapi 为脚本名称

通过访问fastapi提供的12345即可实现改功能