Update app.py

app.py

@@ -11,7 +11,7 @@ ckpt = "meta-llama/Llama-3.2-11B-Vision-Instruct"
 model = MllamaForConditionalGeneration.from_pretrained(ckpt,
     torch_dtype=torch.bfloat16).to("cuda")
 processor = AutoProcessor.from_pretrained(ckpt)
-
+import requests
 
 @spaces.GPU
 def bot_streaming(message, history, max_new_tokens=250):
@@ -25,31 +25,39 @@ def bot_streaming(message, history, max_new_tokens=250):
     images = []
     
 
-    for i, msg in enumerate(history): 
-        if isinstance(msg[0], tuple):
-            messages.append({"role": "user", "content": [{"type": "text", "text": history[i+1][0]}, {"type": "image"}]})
-            messages.append({"role": "assistant", "content": [{"type": "text", "text": history[i+1][1]}]})
-            images.append(Image.open(msg[0][0]).convert("RGB"))
-        elif isinstance(history[i-1], tuple) and isinstance(msg[0], str):
-            # messages are already handled
-            pass
-        elif isinstance(history[i-1][0], str) and isinstance(msg[0], str): # text only turn
-            messages.append({"role": "user", "content": [{"type": "text", "text": msg[0]}]})
-            messages.append({"role": "assistant", "content": [{"type": "text", "text": msg[1]}]})
+    # for i, msg in enumerate(history): 
+    #     if isinstance(msg[0], tuple):
+    #         messages.append({"role": "user", "content": [{"type": "text", "text": history[i+1][0]}, {"type": "image"}]})
+    #         messages.append({"role": "assistant", "content": [{"type": "text", "text": history[i+1][1]}]})
+    #         images.append(Image.open(msg[0][0]).convert("RGB"))
+    #     elif isinstance(history[i-1], tuple) and isinstance(msg[0], str):
+    #         # messages are already handled
+    #         pass
+    #     elif isinstance(history[i-1][0], str) and isinstance(msg[0], str): # text only turn
+    #         messages.append({"role": "user", "content": [{"type": "text", "text": msg[0]}]})
+    #         messages.append({"role": "assistant", "content": [{"type": "text", "text": msg[1]}]})
 
-    # add current message
-    if len(message["files"]) == 1:
+    # # add current message
+    # if len(message["files"]) == 1:
         
-        if isinstance(message["files"][0], str): # examples
-            image = Image.open(message["files"][0]).convert("RGB")
-        else: # regular input
-            image = Image.open(message["files"][0]["path"]).convert("RGB")
-        images.append(image)
-        messages.append({"role": "user", "content": [{"type": "text", "text": txt}, {"type": "image"}]})
-    else:
-        messages.append({"role": "user", "content": [{"type": "text", "text": txt}]})
+    #     if isinstance(message["files"][0], str): # examples
+    #         image = Image.open(message["files"][0]).convert("RGB")
+    #     else: # regular input
+    #         image = Image.open(message["files"][0]["path"]).convert("RGB")
+    #     images.append(image)
+    #     messages.append({"role": "user", "content": [{"type": "text", "text": txt}, {"type": "image"}]})
+    # else:
+    #     messages.append({"role": "user", "content": [{"type": "text", "text": txt}]})
 
 
+    messages= message['messages']
+    files = message['images']
+    for url in files:
+        response = requests.get(url)
+        img = Image.open(BytesIO(response.content)).convert("RGB")
+        images.append(img)
+    
+
     print("\n\nfinal messages        ", messages)
 
     texts = processor.apply_chat_template(messages, add_generation_prompt=True)