Update app.py

app.py

@@ -8,8 +8,7 @@ import uvicorn
 app = FastAPI()
 
 # Initialize tokenizer
-tokenizer = AutoTokenizer.from_pretrained(
-    "Xenova/multi-qa-mpnet-base-dot-v1")
+tokenizer = AutoTokenizer.from_pretrained("Xenova/multi-qa-mpnet-base-dot-v1")
 
 # Load ONNX model
 session = InferenceSession("model.onnx")
@@ -36,13 +35,7 @@ async def predict(request: Request):
             raise HTTPException(status_code=400, detail="No text provided")
         
         # Tokenize input
-        inputs = tokenizer(
-            text,
-            return_tensors="np",
-            padding=False,  # Disable padding
-            truncation=False,  # Disable truncation
-            add_special_tokens=True  # Ensure CLS/SEP tokens
-        )
+        inputs = tokenizer(text)
         
         # Run model
         outputs = session.run(None, {