Update app.py

app.py

@@ -18,7 +18,7 @@ from qwen_vl_utils import process_vision_info
 
 # Constants for text generation
 MAX_MAX_NEW_TOKENS = 4096
-DEFAULT_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 3000
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
@@ -312,4 +312,4 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                        outputs=[output, markdown_output])
 
 if __name__ == "__main__":
-    demo.queue(max_size=30).launch(share=True, ssr_mode=False, show_error=True)
+    demo.queue(max_size=30).launch(share=True, mcp_server=True, ssr_mode=False, show_error=True)