LangGraph and OpenGPTs
In January, LangChain officially launched LangChain v0.1, LangGraph, and OpenGPTs! LangChain v0.1’s release included LangGraph, which powers OpenGPTs.
LangGraph was purpose-built to solve the problem of adding cycles into applications built on (Lang)Chains. Cycles are important in agentic Reasoning-Action (ReAct) frameworks because reasoning is followed by an action, which is followed by more reasoning, followed by another action, and so on…. This means that LLMs are essentially running in a loop, in other words, in a cycle. In short, LangGraph is all about building agents as graphs.
OpenGPTs run on MessageGraph, a particular type of graph in LangGraph. It simply takes in a list of messages and returns a message to append to the list, similar to OpenAI’s Chat Completions Model used within the OpenAI API and the OpenAI Assistants API.
In this event, as always, we’ll break down the details you need to know to build, ship, and share OpenGPTs of your own! We’ll start by walking through the main types of OpenGPTs that you can create: Chatbots, RAGBots, and Assistants. We will demonstrate how each of these work, in order of increasing complexity. Then we’ll dig into what powers OpenGPTs under the hood, including what you should know about LangGraph and MessageGraph. Finally, we’ll build a complex agentic Assistant for our live code demo and walkthrough!
Who should attend the event?
Learners who want to build their OpenGPTs using LangChain.
AI Engineers who are looking for a high-level intro to LangGraph.
Practitioners who are interested in building at the open-source edge of LLMs!
Speakers:
Dr. Greg Loughnane is the Co-Founder & CEO of AI Makerspace, where he serves as an instructor for their AI Engineering Bootcamp. Since 2021 he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris Alexiuk is the Co-Founder & CTO at AI Makerspace, where he serves as an instructor for their AI Engineering Bootcamp. Previously, he’s held roles as a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn & YouTube to stay updated with workshops, new courses, and opportunities for corporate training.