update sth. at 2025-03-03 19:46:42

app.py

@@ -5,6 +5,7 @@ import torch
 import gradio as gr
 from fastapi import FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from pydantic import BaseModel, Field, model_validator
 from typing import List, Dict, Optional
 
@@ -105,6 +106,8 @@ app.add_middleware(
     allow_methods=["*"],
     allow_headers=["*"],
 )
+security = HTTPBearer()
+
 @app.post("/embed", response_model=EmbeddingResponse)
 @app.post("/api/embeddings", response_model=EmbeddingResponse)
 @app.post("/api/embed", response_model=EmbeddingResponse)
@@ -114,7 +117,7 @@ app.add_middleware(
 @app.post("/hf/v1/embeddings", response_model=EmbeddingResponse)
 @app.post("/api/v1/chat/completions", response_model=EmbeddingResponse)
 @app.post("/hf/v1/chat/completions", response_model=EmbeddingResponse)
-async def generate_embeddings(request: EmbeddingRequest):
+async def generate_embeddings(request: EmbeddingRequest, credentials: HTTPAuthorizationCredentials = Depends(security)):
     try:
         # 计算token数量
         token_count = len(embedding_service.tokenizer.encode(request.inputs))
@@ -183,4 +186,4 @@ async def startup_event():
 if __name__ == "__main__":
     asyncio.run(embedding_service.initialize())
     gr.mount_gradio_app(app, iface, path="/ui")
-    uvicorn.run(app, host="0.0.0.0", port=7860, workers=2)
+    uvicorn.run("app:app", host="0.0.0.0", port=7860)