Update app.py

app.py

@@ -35,14 +35,20 @@ def model_inference(input_dict, history):
     if text == "" and images:
         gr.Error("Please input a text query along with the image(s).")
         return
-
+    system_message = "You are a helpful assistant good at solving problems with step-by-step reasoning. You should first think about the reasoning process in the mind and then provide the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags."
+    question_text = "In which country and within which first-level administrative region of that country was this picture taken? Please answer in the format of <answer>$country,administrative_area_level_1$</answer>?"
     # Prepare messages for the model
     messages = [
+        {
+            "role": "system",
+            "content": system_message
+            
+        },
         {
             "role": "user",
             "content": [
                 *[{"type": "image", "image": image} for image in images],
-                {"type": "text", "text": text},
+                {"type": "text", "text": question_text},
             ],
         }
     ]
@@ -79,7 +85,7 @@ examples = [
 
 demo = gr.ChatInterface(
     fn=model_inference,
-    description="# **Qwen2.5-VL-3B-Instruct**",
+    description="# **SeekWorld**",
     examples=examples,
     textbox=gr.MultimodalTextbox(label="Query Input", file_types=["image"], file_count="multiple"),
     stop_btn="Stop Generation",