Using LangChain and LangGraph with local models

DanielJuly 1, 2025October 3, 2025

In this video, I'll walk you through setting up and using local models with LangChain, making AI development more private, cost-effective, and flexible. We'll start by installing Ollama, a tool that simplifies running local language models, and then set up a local LLM using Llama 3.2. Once the model is running, I'll show you how to interact with it and even turn off your Wi-Fi to demonstrate its true offline capabilities.

Next, we'll dive into integrating this local model with LangChain and LangGraph, making it easy to build AI-powered applications without relying on cloud-based APIs. I'll guide you through serving the model on localhost and writing a simple script to interact with it using LangChain. By the end of this tutorial, you'll have a fully functional local AI setup that you can extend further—whether by connecting it to an AI agent, using retrieval-augmented generation (RAG), or building more advanced workflows.

Plus, you’ll enjoy the benefits of full data privacy and reduced costs.

👨‍💻Full code here: https://github.com/daniel-jscraft/Javascript-CSS-demos/tree/main/demos/%F0%9F%A6%9C_langchain/23-local-llm