DEV Community: Apu Chakraborty

The Ultimate Guide to Running n8n with Ollama LLM Locally Using Docker

Apu Chakraborty — Tue, 10 Jun 2025 14:24:10 +0000

Would you like to automate tasks using AI locally—without relying on the cloud, incurring API costs, or risking data leakage?

This guide will demonstrate how to operate n8n, a robust open-source workflow automation tool, in conjunction with Ollama, a high-speed local LLM runtime (similar to LLaMA, Mistral, or others)—all facilitated through Docker on your personal computer.

Indeed, it is possible to establish a completely local AI automation system at no cost whatsoever.
Let us explore this further.

📁 1. Create a folder structure

mkdir n8n-ollama
cd n8n-ollama
touch docker-compose.yml

🧾 2. Create `docker-compose.yml`

Create a file named docker-compose.yml with:


services:
  ollama:
    image: ollama/ollama
    ports:
      - "11434:11434"
    container_name: ollama
    networks:
      - n8n-network
    volumes:
      - ollama_data:/root/.ollama

  n8n:
    image: n8nio/n8n
    container_name: n8n
    ports:
      - "5678:5678"
    networks:
      - n8n-network
    environment:
      - N8N_HOST=localhost
      - N8N_PORT=5678
      - N8N_EDITOR_BASE_URL=http://localhost:5678
      - WEBHOOK_URL=http://localhost:5678
      - NODE_FUNCTION_ALLOW_EXTERNAL=*
    volumes:
      - n8n_data:/home/node/.n8n

networks:
  n8n-network:

volumes:
  ollama_data:
  n8n_data:

This puts both containers in the same Docker network so n8n can reach ollama using the hostname ollama.

▶️ 3. Start both services

docker-compose up -d

you will get response like this -

[+] Running 2/2
 ✔ Container ollama  Started                                                                                        0.6s 
 ✔ Container n8n     Started

✅ Verify container

#verify containers
docker ps

CONTAINER ID   IMAGE           COMMAND                  CREATED      STATUS         PORTS                                           NAMES
0d99d7a06ff9   n8nio/n8n       "tini -- /docker-ent…"   3 days ago   Up 2 minutes   0.0.0.0:5678->5678/tcp, :::5678->5678/tcp       n8n
c5eabfa39b70   ollama/ollama   "/bin/ollama serve"      3 days ago   Up 2 minutes   0.0.0.0:11434->11434/tcp, :::11434->11434/tcp   ollama

You should see both ollama and n8n containers running.
n8n - http://localhost:5678
ollama - http://localhost:11434

🎉 Great! That means n8n successfully connected to Ollama, and now the only issue is:

⛓️ Pull the correct model inside the Ollama container

Open a terminal inside the Ollama container:

docker exec -it ollama bash

You're now inside the container.

Pull a valid model (e.g., `llama3`):

ollama pull llama3
# ---
ollama pull llama3.2
# ---
ollama pull deepseek-r1:1.5b

root@c5eabfa39b70:/# ollama list
NAME                ID              SIZE      MODIFIED   
deepseek-r1:1.5b    e0979632db5a    1.1 GB    3 days ago    
llama3.2:latest     a80c4f17acd5    2.0 GB    3 days ago    
llama3:latest       365c0bd3c000    4.7 GB    3 days ago

⭐ This will download the official llama3 model.

Exit the container:

exit

In n8n, update your model name:

When setting up the Ollama node in n8n, use:

llama3

✌🏻 This matches the model you pulled.

curl http://localhost:11434/api/generate \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2",
    "prompt": "5+5 ?",
    "stream": false
}'

From outside, run:

docker exec -it ollama ollama list

🛑 stop the container:

docker-compose down

You Did It! Now Build AI Agents Locally—Fast & Free.

With Ollama + n8n, you can:

Run AI like Llama offline (no APIs, no costs)
Automate content, support, or data tasks in minutes
Own your AI workflow (no limits, no middlemen)

Your turn—launch a workflow and see the magic happen. 🚀

How to add Ckeditor5 in your Next JS, react App

Apu Chakraborty — Sun, 06 Jun 2021 11:08:43 +0000

I am creating a fresh CRA & here is my project directory

Before we going started, you need to add this npm package first, to install please paste the below code into your terminal.

npm i @ckeditor/ckeditor5-react
npm i @ckeditor/ckeditor5-build-classic

create a components folder under src folder and create a Editor component under components/Editor.js & use this code

import React, { useEffect, useRef } from "react";

function Editor({ onChange, editorLoaded, name, value }) {
  const editorRef = useRef();
  const { CKEditor, ClassicEditor } = editorRef.current || {};

  useEffect(() => {
    editorRef.current = {
      CKEditor: require("@ckeditor/ckeditor5-react").CKEditor, // v3+
      ClassicEditor: require("@ckeditor/ckeditor5-build-classic")
    };
  }, []);

  return (
    <div>
      {editorLoaded ? (
        <CKEditor
          type=""
          name={name}
          editor={ClassicEditor}
          data={value}
          onChange={(event, editor) => {
            const data = editor.getData();
            // console.log({ event, editor, data })
            onChange(data);
          }}
        />
      ) : (
        <div>Editor loading</div>
      )}
    </div>
  );
}

export default Editor;

Now go to your app.js or wherever you want to use this editor just import Editor Component and use this

import React, { useState, useEffect } from "react";
import "./styles.css";
import Editor from "./Editor";

export default function App() {
  const [editorLoaded, setEditorLoaded] = useState(false);
  const [data, setData] = useState("");

  useEffect(() => {
    setEditorLoaded(true);
  }, []);

  return (
    <div className="App">
      <h1>ckEditor 5</h1>

      <Editor
        name="description"
        onChange={(data) => {
          setData(data);
        }}
        editorLoaded={editorLoaded}
      />

      {JSON.stringify(data)}
    </div>
  );
}

visit ckEditor5 documentation to add more features - https://ckeditor.com/docs/ckeditor5/latest/examples/builds/classic-editor.html

you can clone repo

apuchakraborty / ckEditor5-implement

Created with CodeSandbox

ckEditor5-implement

Created with CodeSandbox

go to - cd /projectdir

npm install & npm start to run

View on GitHub

You can use this code in codesSandbox
Here is your editor -

Laravel 7 API authentication for beginners

Apu Chakraborty — Tue, 25 Aug 2020 15:22:02 +0000

Nowadays, API is becoming the most essentials for modern applications. In this article, we will see how can we create APIs using Laravel 7 easily.
We are not going to cover what API is and why we should use it. So if you don't know What API is? then google it first and then come here.

Let's come to the Point

First of all, let's create a fresh Laravel project

composer create-project --prefer-dist laravel/laravel laravelApi

We are going to use Laravel sanctum to get token so, let's install sanctum

composer require laravel/sanctum

Now publish the configuration files and migrations

php artisan vendor:publish --provider="Laravel\Sanctum\SanctumServiceProvider"

Now, it's time to add EnsureFrontendRequestsAreStateful middleware to your API middleware group in your app/Http/Kernel.php file

use Laravel\Sanctum\Http\Middleware\EnsureFrontendRequestsAreStateful;

'api' => [
    EnsureFrontendRequestsAreStateful::class,
    'throttle:60,1',
    \Illuminate\Routing\Middleware\SubstituteBindings::class,
],

Configure your database in .env file

DB_CONNECTION=mysql
DB_HOST=127.0.0.1
DB_PORT=3306
DB_DATABASE=yourdatabasename
DB_USERNAME=username
DB_PASSWORD=password

let's migrate

php artisan migrate

it is responsible for creating the user table in your application.

Next, go to User Model in App/User.php and add this code

use Laravel\Sanctum\HasApiTokens;

class User extends Authenticatable
{
    use HasApiTokens, Notifiable;
}

Next, go to the routes folder and open api.php
and add this line of routes

Route::post('/register', 'RegisterController@register');
Route::post('/login', 'LoginController@login');

and change the default middleware to sanctum

Route::middleware('auth:sanctum')->get('/user', function (Request $request) {
    return $request->user();
});

Now create two controller RegisterController and LoginController

php artisan make:controller LoginController

<?php

namespace App\Http\Controllers;

use App\User;
use Illuminate\Http\Request;
use Illuminate\Support\Facades\Auth;
use Illuminate\Support\Facades\Hash;
use Illuminate\Validation\ValidationException;

class LoginController extends Controller
{
    public function login(Request $request)
    {
        $request->validate([
            'email' => 'required|email',
            'password' => 'required',
        ]);

        $user = User::where('email', $request->email)->first();

        if (!$user || !Hash::check($request->password, $user->password)) {
            throw ValidationException::withMessages([
                'email' => ['The provided credentials are incorrect.'],
            ]);
        }

        return $user->createToken('x-key')->plainTextToken;
    }

}

php artisan make:controller RegisterController

<?php

namespace App\Http\Controllers;

use App\User;
use Illuminate\Http\Request;
use Illuminate\Support\Facades\Hash;

class RegisterController extends Controller
{
    public function register(Request $request)
    {
        $request->validate([
            'name' => ['required'],
            'email' => ['required', 'email', 'unique:users'],
            'password' => ['required', 'min:8', 'confirmed']
        ]);

        User::create([
            'name' => $request->name,
            'email' => $request->email,
            'password' => Hash::make($request->password)
        ]);
    }
}

let's register a user using postman

and try to login

You are ready to go, cheers.

DEV Community: Apu Chakraborty

The Ultimate Guide to Running n8n with Ollama LLM Locally Using Docker

Would you like to automate tasks using AI locally—without relying on the cloud, incurring API costs, or risking data leakage?

📁 1. Create a folder structure

🧾 2. Create docker-compose.yml

▶️ 3. Start both services

✅ Verify container

⛓️ Pull the correct model inside the Ollama container

Open a terminal inside the Ollama container:

Pull a valid model (e.g., llama3):

Exit the container:

In n8n, update your model name:

🛑 stop the container:

How to add Ckeditor5 in your Next JS, react App

apuchakraborty / ckEditor5-implement

Created with CodeSandbox

ckEditor5-implement

Laravel 7 API authentication for beginners

🧾 2. Create `docker-compose.yml`

Pull a valid model (e.g., `llama3`):