Update app.py

app.py

@@ -164,16 +164,14 @@ def prepare_test_messages(image, prompt):
     image.save(buffered, format="JPEG")
     img_base64 = base64.b64encode(buffered.getvalue()).decode('utf-8')
 
-    if "segment" in prompt or "mask" in prompt:
-        SYSTEM_PROMPT = (
-            "A conversation between User and Assistant. The user asks a question, and the Assistant solves it. The assistant "
-            "first thinks about the reasoning process in the mind and then provides the user with the answer. The reasoning "
-            "process should enclosed within <think> </think> tags, and the bounding box, points and points labels should be enclosed within <bbox></bbox>, <points></points>, and <labels></labels>, respectively. i.e., "
-            "<think> reasoning process here </think> <bbox>[x1,y1,x2,y2]</bbox>, <points>[[x3,y3],[x4,y4],...]</points>, <labels>[1,0,...]</labels>"
-            "Where 1 indicates a foreground (object) point, and 0 indicates a background point."
-        )
-    else:
-        SYSTEM_PROMPT = "You're a helpful visual assistant."
+    SYSTEM_PROMPT = (
+        "A conversation between User and Assistant. The user asks a question, and the Assistant solves it. The assistant "
+        "first thinks about the reasoning process in the mind and then provides the user with the answer. The reasoning "
+        "process should enclosed within <think> </think> tags, and the bounding box, points and points labels should be enclosed within <bbox></bbox>, <points></points>, and <labels></labels>, respectively. i.e., "
+        "<think> reasoning process here </think> <bbox>[x1,y1,x2,y2]</bbox>, <points>[[x3,y3],[x4,y4],...]</points>, <labels>[1,0,...]</labels>"
+        "Where 1 indicates a foreground (object) point, and 0 indicates a background point."
+    )
+
 
     messages = [
         {"role": "system", "content": [{"type": "text", "text": SYSTEM_PROMPT}]},