Update main.py

main.py

@@ -6,11 +6,7 @@ import asyncio
 from concurrent.futures import ThreadPoolExecutor
 from typing import List
 import numpy as np
-
-app = FastAPI(title="Text Embedding API (Qwen/Qwen3-Embedding-0.6B)")
-
-class TextRequest(BaseModel):
-    text: str = Field(..., min_length=1, description="Text to embed")
+from contextlib import asynccontextmanager
 
 # Globals
 model = None
@@ -19,13 +15,27 @@ model_id = 'Qwen/Qwen3-Embedding-0.6B'
 executor = ThreadPoolExecutor(max_workers=4)
 MAX_TOKENS = 512
 
-@app.on_event("startup")
-async def load_model():
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # Load the model and tokenizer at startup
     global model, tokenizer
     print(f"Loading model: {model_id}...")
     model = SentenceTransformer(model_id)
     tokenizer = model.tokenizer
     print("Model loaded successfully")
+    yield
+    # (Optional) Clean up resources at shutdown
+    print("Cleaning up resources...")
+    model = None
+    tokenizer = None
+
+app = FastAPI(
+    title="Text Embedding API (Qwen/Qwen3-Embedding-0.6B)",
+    lifespan=lifespan
+)
+
+class TextRequest(BaseModel):
+    text: str = Field(..., min_length=1, description="Text to embed")
 
 @app.get("/")
 def home():