added VQA ability in handler

handler.py

@@ -16,11 +16,12 @@ class EndpointHandler():
 
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
         image_encoded = data.pop("inputs", data)
+        text = data["text"]
 
         # image = Image.open(image_path)
         image = self.decode_base64_image(image_encoded)
 
-        processed = self.processor(images=image, return_tensors="pt").to(self.device)
+        processed = self.processor(images=image, text=text, return_tensors="pt").to(self.device)
 
         out = self.model.generate(**processed)