DEV Community

Cover image for LLM Development with JavaScript: Is that a thing?
Jacob Orshalick
Jacob Orshalick

Posted on

LLM Development with JavaScript: Is that a thing?

#javascript #node #beginners #openai

This tutorial is a fast track to developing JavaScript apps that talk to LLM models. You'll have a REST service up and talking to an LLM in under 10 minutes. Let the coding magic begin!

This is part 1 from my free e-book:

The Busy Developers Guide to Generative AI

Fig 1: The Busy Developers Guide to Gen AI

All source code is available on GitHub.

ChatGPT vaulted generative AI into mainstream culture. But, it's really just a user interface, powered by the true marvel that lies beneath - the large language model (LLM). 

More precisely, LLMs are very large deep learning models that are pre-trained on vast amounts of data. The keyword there is pre-trained. 

All we have to do to make use of these same models is send them a prompt telling it what we want. We can do that by calling the OpenAI APIs.

Fig 2: Your REST service can call the same APIs used by ChatGPT

1. Install Node

Download and install: https://nodejs.org. Verify the install in your terminal:

~ % node -v
Enter fullscreen mode Exit fullscreen mode

If the installation succeeded, the version will print.

2. Initialize your project

Create a new directory for your project. Navigate to it in your terminal and run the following command:

~/ai-for-devs % npm init -y
Enter fullscreen mode Exit fullscreen mode

This creates a new package.json file, initializing the project.

  1. Install Node modules

The node modules we'll be using:

  • express: which makes server creation quick and easy
  • langchain: which provides a framework for building Apps with LLMs
  • @langchain/openai: which provides OpenAI integrations through their SDK
  • cors: Express middleware to enable CORS

In the same terminal, run the following command:

~/ai-for-devs % npm install express langchain @langchain/openai cors
Enter fullscreen mode Exit fullscreen mode

4. Create the server file

Create a file called server.mjs in the project directory. Open it in a text editor and add the following lines of code:

import express from "express";
import { ChatOpenAI } from "@langchain/openai";
import cors from 'cors';

const app = express();

app.use(cors());

const chatModel = new ChatOpenAI({});

app.get('/', async (req, res) => {
  const response = 
    await chatModel.invoke(
      "Can you simply say 'test'?");

  res.send(response.content);
});

app.listen(3000, () => {
  console.log(`Server is running on port 3000`);
});
Enter fullscreen mode Exit fullscreen mode

5. Create an OpenAI account

Register here: https://platform.openai.com. Obtain an API key:

  • Simply select 'API keys' in the upper left navigation
  • Select '+ Create new secret key'
  • Copy the key somewhere safe for now

Fig 3: The API keys in Open AI's interface

6. Set an environment variable

In the same terminal, run the following command with your key value:

~/ai-for-devs % export OPENAI_API_KEY=<YOUR_KEY_VALUE>
Enter fullscreen mode Exit fullscreen mode

Optionally add this command to your bash profile: ~/.zshrc

7. Launch your server

Back in the terminal, run the following command:

~/node-openai % node server.mjs
Enter fullscreen mode Exit fullscreen mode

Open your web browser and visit: http://localhost:3000

You'll see the response from the OpenAI model: "test"

Congratulations!

You've successfully built a functional REST service. Beyond its ability to prompt an AI and generate responses, it forms the foundation for the remainder of my free to download e-book:

The Busy Developer's Guide to Gen AI

In Part 2, we'll explore the process of streaming longer responses so our users don't have to wait. Part 3 and part 4 will guide you through creating a complete RAG (Retrieval Augmented Generation) implementation.

Download the book to learn more!

Top comments (5)

Collapse
 
joelbonetr profile image
JoelBonetR 🥇 •

Thought you were about to explain Brain JS or something like that at first 😂 either way it hasn't been disappointing, straight to the point and clear, thanks you for sharing! 😁

Collapse
 
jorshali profile image
Jacob Orshalick •

Glad you found it helpful! Maybe I’ll dive into Brain JS for the next one 😉

Collapse
 
joelbonetr profile image
JoelBonetR 🥇 •

That'll be amazing! 😍 Mention me if you do so 😁

Collapse
 
matthewhou profile image
Matthew Hou •

I've switched AI tools three times in the last year and the one thing that saved me was keeping my workflow config in plain markdown files. AGENTS.md, coding conventions, project context — all tool-agnostic. When I moved from Cursor to Claude Code, I just pointed it at the same files. Maybe 10% needed format tweaks. The other 90% just worked. The tool doesn't matter nearly as much as your workflow documentation.

Collapse
 
matthewhou profile image
Matthew Hou •

We had the exact same problem. Our coding standards were in a Confluence page that nobody read — including AI. So we converted the most important rules into ESLint and Ruff configs. Now when AI generates code, it auto-lints on save. Our code review time dropped significantly because all the 'you forgot to follow our pattern' comments disappeared. If your standards aren't executable, they're suggestions.