From dfa4197b04c81b5f978d448563be777b52179890 Mon Sep 17 00:00:00 2001 From: Kye Date: Fri, 24 Nov 2023 17:35:47 -0800 Subject: [PATCH] GPT4Vision + multimodal --- .../multi_modal_auto_agent.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent.py diff --git a/playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent.py b/playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent.py new file mode 100644 index 00000000..f5462847 --- /dev/null +++ b/playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent.py @@ -0,0 +1,17 @@ +from swarms.structs import Flow +from swarms.models.gpt4_vision_api import GPT4VisionAPI + + +llm = GPT4VisionAPI() + +task = "What is the color of the object?" +img = "images/swarms.jpeg" + +## Initialize the workflow +flow = Flow( + llm=llm, + max_loops="auto", + dashboard=True, +) + +flow.run(task=task, img=img)