How to Use AutoGen & GPT-4 to Create Multiple AI Agents

In this AutoGen tutorial for beginners, you'll learn how to build a team of autonomous AI Agents powered by OpenAI's GPT-4. AutoGen is the cutting-edge framework for creating AI multi-agent Assistants, leaving behind its competitors such as MetaGPT or ChatDev. 🤝 Connect with me 🤝 LinkedIn: https://www.linkedin.com/in/kris-ograbek/ Medium: https://medium.com/@kris-ograbek +++ Useful Resources +++ Code: https://colab.research.google.com/drive/11HiXpnPNIN3WIJK76TG-tsraix_lhb0M?usp=sharing +++ Sources for Autogen +++ Docs: https://microsoft.github.io/autogen/docs/Examples/AutoGen-AgentChat GitHub: https://github.com/microsoft/autogen/tree/main Official Paper: https://arxiv.org/abs/2308.08155 Multi-agent Conversation Framework: https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat/ SDK: https://microsoft.github.io/autogen/docs/reference/agentchat/conversable_agent/ Chapters: 0:00 Intro 1:24 Feature 1: Complete flexibility 2:39 Feature 2: Human participation 4:04 Feature 3: Multi-agent conversations 5:06 Feature 4: Flexible autonomy 5:50 User Proxy Agent autonomy explained 6:56 Assistant Agents explained 7:21 Group Chat Managers explained 9:06 AutoGen example project in Colab 11:21 GPT-4 prices :( 12:33 User Proxy Agent creation 13:40 Analyzing AutoGen results 16:35 AutoGen fixes the first bug 17:22 AutoGen fixes the second bug 18:12 Excitement about the results 20:45 Followup the conversation with User Proxy 24:15 AutoGen on your computer (+ function calling) 2023-10-26T13:28:27Z1280 https://www.youtube.com/embed/nnbjOJkQ7sg