Update handler.py

handler.py

@@ -5,7 +5,7 @@ import torch
 import base64
 import io
 from transformers import BlipForConditionalGeneration, BlipProcessor
-
+import logging
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
 class EndpointHandler():
@@ -15,11 +15,20 @@ class EndpointHandler():
         self.model.eval()
 
     def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
+        logging.debug('------------This is a debug message')
+        logging.info('----------------------This is an info message')
+        logging.warning('--------This is a warning message')
+        logging.error('----------This is an error message')
+        logging.critical('-------------------This is a critical message')
+        print("000000--",type(data))
+        logging.warning('--------This is a warning message')
         print("input data is here------------",data)
         input_data = data.get("inputs", {})
-        print("input data is here-2-----------",input_data)
+        logging.warning('------input_data--This is a warning message', input_data)
+        print("input data is here-2-----------",type(input_data))
         encoded_images = input_data.get("images")
-        print("input encoded_images is here------------",encoded_images)
+        logging.warning('---encoded_images-----This is a warning message',encoded_images)
+        print("input encoded_images is here------------",type(encoded_images))
         if not encoded_images:
             return {"captions": [], "error": "No images provided"} 
 
@@ -37,7 +46,7 @@ class EndpointHandler():
             # Non test code
             dataBytesIO = io.BytesIO(byteImg)
             raw_images =[Image.open(dataBytesIO)]
-            
+            logging.warning('----raw_images----This is a warning message',raw_images)
             # Check if any images were successfully decoded
             if not raw_images:
                 print("No valid images found.")
@@ -48,13 +57,15 @@ class EndpointHandler():
                 "pixel_values": torch.cat([inp["pixel_values"] for inp in processed_inputs], dim=0).to(device),
                 "max_new_tokens":40
             }
-
+            logging.warning('---processed_inputs-----This is a warning message', processed_inputs)
             with torch.no_grad():
                 out = self.model.generate(**processed_inputs)
 
             captions = self.processor.batch_decode(out, skip_special_tokens=True)
+            logging.warning('----captions----This is a warning message',captions)
             print("caption is here-------",captions)
             return {"captions": captions}
         except Exception as e:
             print(f"Error during processing: {str(e)}")
+            logging.error(f"Error during processing: ----------------{str(e)}")
             return {"captions": [], "error": str(e)}