Update app.py

app.py

@@ -51,21 +51,15 @@ def respond(
                 ]
             })
 
-    if text:
-        messages.append({
+    messages.append(
+        {
             "role": "user",
             "content": [
                 { "type": "text", "text": text },
+                *[{"type": "image", "image": image} for image in files]
             ]
-        })
-    
-    for file in files:
-        messages.append({
-            "role": "user",
-            "content": [
-                { "type": "image", "image": file }
-            ]
-        })
+        }
+    )
     
     image_inputs, video_inputs = process_vision_info(messages)
     prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)