Gagan Bansal
Senior Researcher at Microsoft Research
AutoGen enables collaboration among multiple ChatGPTs for complex tasks.
## TL;DR OpenAI assistants are now integrated into AutoGen via [`GPTAssistantAgent`](https://github.com/ag2ai/ag2/blob/main/autogen/agentchat/contrib/gpt_assistant_agent.py). This enables multiple OpenAI assistants, which form the backend of the now popular GPTs, to collaborate and tackle complex tasks. Checkout example notebooks for reference: * [Basic example](https://github.com/ag2ai/ag2/blob/main/notebook/agentchat_oai_assistant_twoagents_basic.ipynb) * [Code interpreter](https://github.com/ag2ai/ag2/blob/main/notebook/agentchat_oai_code_interpreter.ipynb) * [Function calls](https://github.com/ag2ai/ag2/blob/main/notebook/agentchat_oai_assistant_function_call.ipynb) ## Introduction Earlier last week, OpenAI introduced [GPTs](https://openai.com/index/introducing-gpts), giving users ability to create custom ChatGPTs tailored for them. *But what if these individual GPTs could collaborate to do even more?* Fortunately, because of AutoGen, this is now a reality! AutoGen has been pioneering agents and supporting [multi-agent workflows](https://openreview.net/pdf?id=BAakY1hNKS) since earlier this year, and now (starting with version 0.2.0b5) we are introducing compatibility with the [Assistant API](https://openai.com/index/introducing-gpts), which is currently in beta preview. To accomplish this, we've added a new (experimental) agent called the `GPTAssistantAgent` that lets you seamlessly add these new OpenAI assistants into AutoGen-based multi-agent workflows. This integration shows great potential and synergy, and we plan to continue enhancing it. ## Installation ```bash theme={null} pip install autogen[openai] ``` ## Basic Example Here's a basic example that uses a `UserProxyAgent` to allow an interface with the `GPTAssistantAgent`. First, import the new agent and setup `config_list`: ```python theme={null} from autogen import config_list_from_json from autogen.agentchat.contrib.gpt_assistant_agent import GPTAssistantAgent from autogen import UserProxyAgent config_list = config_list_from_json("OAI_CONFIG_LIST") ``` Then simply define the OpenAI assistant agent and give it the task! ```python theme={null} # creates new assistant using Assistant API gpt_assistant = GPTAssistantAgent( name="assistant", llm_config={ "config_list": config_list, "assistant_id": None }) user_proxy = UserProxyAgent(name="user_proxy", code_execution_config={ "work_dir": "coding" }, human_input_mode="NEVER") user_proxy.initiate_chat(gpt_assistant, message="Print hello world") ``` `GPTAssistantAgent` supports both creating new OpenAI assistants or reusing existing assistants (e.g, by providing an `assistant_id`). ## Code Interpreter Example `GPTAssistantAgent` allows you to specify an OpenAI tools (e.g., function calls, code interpreter, etc). The example below enables an assistant that can use OpenAI code interpreter to solve tasks. ```python theme={null} # creates new assistant using Assistant API gpt_assistant = GPTAssistantAgent( name="assistant", llm_config={ "config_list": config_list, "assistant_id": None, "tools": [ { "type": "code_interpreter" } ], }) user_proxy = UserProxyAgent(name="user_proxy", code_execution_config={ "work_dir": "coding" }, human_input_mode="NEVER") user_proxy.initiate_chat(gpt_assistant, message="Print hello world") ``` Checkout more examples [here](https://github.com/ag2ai/ag2/tree/main/notebook). ## Limitations and Future Work * Group chat managers using GPT assistant are pending. * GPT assistants with multimodal capabilities haven't been released yet but we are committed to support them. ## Acknowledgements `GPTAssistantAgent` was made possible through collaboration with [@IANTHEREAL](https://github.com/IANTHEREAL), [Jiale Liu](https://github.com/LeoLjl), [Yiran Wu](https://github.com/yiranwu0), [Qingyun Wu](https://qingyun-wu.github.io/), [Chi Wang](https://github.com/sonichi), and many other AutoGen maintainers.