Building Agentic and Multi-Agent Systems with LangGraph

Abstract: 

People and companies in 2024 aim to build ever more complex and performant LLM applications. Leveraging context (e.g., Retrieval Augmented Generation, or RAG), reasoning, and access to external tools or functions (Agents), are front and center. For applications to leverage context well, they must provide useful input to the context window (e.g., [in-context learning](https://openai.com/index/language-models-are-few-shot-learners/)), through direct prompting (Prompt Engineering) or search and retrieval (RAG). To leverage reasoning is to leverage the Reasoning-Action ([ReAct](https://arxiv.org/abs/2210.03629)) pattern, and to be “agentic” or “agent-like.” Another way to think about agents is that they enhance search and retrieval through the intelligent use of tools or services.

The best practice orchestration tooling in the industry for building context-aware, reasoning applications with LLMs is LangChain. To build with Agents, LangGraph leverages a graph-based approach to add cyclical reasoning loops to our application logic. Once we introduce agentic cycles, adding agents (e.g., multi-agents) to our graph becomes trivial.

In this session, we'll break down all the concepts and code you need to understand and build the industry-standard agentic and multi-agent systems, from soup to nuts, with LangChain.

## **👨‍🏫 Concepts**

We’ll cover:

- A review of the basic prototyping patterns of GenAI, including Prompt Engineering, RAG, Fine-Tuning, and Agents
- LangChain and LangGraph core constructs for building agentic and multi-agent applications

## ⌨️ **Code**

You’ll learn how to:

- 🏗️ Build RAG applications with LangChain
- ⛓️ Build agentic RAG applications with LangGraph
- 🤖 Develop multi-agent workflows with LangGraph

Session Outline:

1. **🧑‍🏫 Concepts**: Introduction to Patterns of GenAI: Prompt Engineering, Retrieval Augmented Generation, Fine-Tuning, and Agents
2. **🧑‍🏫 Concepts**: LangChain: Core Constructs | **🧑‍💻 Code**: LangChain RAG Demo
3. **🧑‍🏫 Concepts**: LangGraph: Core Constructs | **🧑‍💻 Code**: LangGraph Agent Demo
4. **🧑‍🏫 Concepts**: LangGraph Studio: The Agent IDE | **🧑‍💻 Code**: LangGraph & LangGraph Studio Multi-Agent Agent Demo

Bio: 

Dr. Greg Loughnane is the Co-Founder & CEO of AI Makerspace, where he is 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.

Open Data Science

 

 

 

Open Data Science
One Broadway
Cambridge, MA 02142
info@odsc.com

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from - Youtube
Vimeo
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google