Skip to content

A programming framework for agentic AI

Add blog post for open ai assistants (#638)

gagb08145bfbce80
diff --git a/website/blog/2023-11-13-OAI-assistants/img/teaser.jpg b/website/blog/2023-11-13-OAI-assistants/img/teaser.jpg
new file mode 100644
index 000000000..ac22cd3c0
Binary files /dev/null and b/website/blog/2023-11-13-OAI-assistants/img/teaser.jpg differ
diff --git a/website/blog/2023-11-13-OAI-assistants/index.mdx b/website/blog/2023-11-13-OAI-assistants/index.mdx
new file mode 100644
index 000000000..7c1ff13e0
--- /dev/null
+++ b/website/blog/2023-11-13-OAI-assistants/index.mdx
@@ -0,0 +1,117 @@
+---
+title: AutoGen Meets GPTs
+authors: gagb
+tags: [openai-assistant]
+---
+
+![OpenAI Assistant](img/teaser.jpg)
+<p align="center"><em>AutoGen enables collaboration among multiple ChatGPTs for complex tasks.</em></p>
+
+
+## TLDR
+OpenAI assistants are now integrated into AutoGen via [`GPTAssistantAgent`](https://github.com/microsoft/autogen/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/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_twoagents_basic.ipynb)
+* [Code interpreter](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_code_interpreter.ipynb)
+* [Function calls](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_function_call.ipynb)
+
+
+## Introduction
+Earlier last week, OpenAI introduced [GPTs](https://openai.com/blog/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://aka.ms/autogen-pdf) since earlier this year, and now (starting with version 0.2.0b5) we are introducing compatibility with the [Assistant API](https://openai.com/blog/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
+pip install pyautogen
+```
+
+## 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
+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
+# 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 existsing 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
+# 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/microsoft/autogen/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://leoljl.github.io),
+[Yiran Wu](https://github.com/kevin666aa),
+[Qingyun Wu](https://qingyun-wu.github.io/),
+[Chi Wang](https://www.microsoft.com/en-us/research/people/chiw/), and many other AutoGen maintainers.
diff --git a/website/blog/authors.yml b/website/blog/authors.yml
index cf77c02e3..f660a25f4 100644
--- a/website/blog/authors.yml
+++ b/website/blog/authors.yml
@@ -40,6 +40,12 @@ beibinli:
url: https://github.com/beibinli
image_url: https://github.com/beibinli.png
+gagb:
+ name: Gagan Bansal
+ title: Senior Researcher at Microsoft Research AI Frontier
+ url: https://www.linkedin.com/in/gagan-bansal/
+ image_url: https://github.com/gagb.png
+
jieyuz2:
name: Jieyu Zhang
title: PhD student at University of Washington