response updated

app.py

@@ -67,11 +67,14 @@ processor = AutoProcessor.from_pretrained(model_name, use_auth_token=HF_TOKEN)
 def predict_image(image_url, text):
     try:
         # Download the image from the URL
+        # response = requests.get(image_url)
+        # response.raise_for_status()  # Raise an error for invalid responses
+        # image = Image.open(io.BytesIO(response.content)).convert("RGB")
+
         response = requests.get(image_url)
         response.raise_for_status()  # Raise an error for invalid responses
         image = Image.open(io.BytesIO(response.content)).convert("RGB")
-
-        # Prepare the input messages
+        
         messages = [
             {"role": "user", "content": [
                 {"type": "image"},  # Specify that an image is provided
@@ -83,7 +86,26 @@ def predict_image(image_url, text):
         input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
         
         # Process the inputs and move to the appropriate device
-        inputs = processor(image=image, text=input_text, return_tensors="pt").to("cuda")
+        inputs = processor(image, input_text, return_tensors="pt").to(device)
+
+        outputs = model.generate(**inputs, max_new_tokens=100)
+    
+        # Decode the output to return the final response
+        response = processor.decode(outputs[0], skip_special_tokens=True)
+        
+        # # Prepare the input messages
+        # messages = [
+        #     {"role": "user", "content": [
+        #         {"type": "image"},  # Specify that an image is provided
+        #         {"type": "text", "text": text}  # Add the user-provided text input
+        #     ]}
+        # ]
+        
+        # # Create the input text using the processor's chat template
+        # input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
+        
+        # # Process the inputs and move to the appropriate device
+        # inputs = processor(image=image, text=input_text, return_tensors="pt").to("cuda")
         
         # Generate a response from the model
         # outputs = model.generate(**inputs, max_new_tokens=100)
@@ -91,23 +113,23 @@ def predict_image(image_url, text):
         # # Decode the output to return the final response
         # response = processor.decode(outputs[0], skip_special_tokens=True)
 
-        streamer = TextIteratorStreamer(processor, skip_special_tokens=True, skip_prompt=True)
+        # streamer = TextIteratorStreamer(processor, skip_special_tokens=True, skip_prompt=True)
 
-        generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=2048)
-        generated_text = ""
+        # generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=2048)
+        # generated_text = ""
         
-        thread = Thread(target=model.generate, kwargs=generation_kwargs)
-        thread.start()
-        buffer = ""
-    
-        for new_text in streamer:
-            buffer += new_text
-            # generated_text_without_prompt = buffer
-            # # time.sleep(0.01)
-            # yield buffer
+        # thread = Thread(target=model.generate, kwargs=generation_kwargs)
+        # thread.start()
+        # buffer = ""
+    
+        # for new_text in streamer:
+        #     buffer += new_text
+        #     # generated_text_without_prompt = buffer
+        #     # # time.sleep(0.01)
+        #     # yield buffer
         
-        return buffer
-        # return response
+        # return buffer
+        return response
     
     except Exception as e:
         raise ValueError(f"Error during prediction: {str(e)}")