DEV Community: James Murdza

Making an Alexa chatbot with Tambo+Deezer 🎶

James Murdza — Fri, 29 Aug 2025 18:40:51 +0000

Today we're going to see how to start with a basic AI chatbot and add in tools and custom UI components. For this tutorial we'll add a "music search tool" and a "music miniplayer" to give a chatbot musical abilities in about ten minutes.

But first, here's quick demo:

(Link to the code: jamesmurdza/my-music-player)

1. Create a New Tambo App

We'll start by creating a new Tambo app (Tambo is an open source generative UI framework):

npx tambo create-app my-music-player
cd my-music-player
npx tambo init

Once you have your Tambo project set up, you can delete a few of the template files from the example:

rm src/components/ui/card-data.tsx src/services/population-stats.ts

2. Define Music Types

We'll be using the Deezer API to search for music, so let's define a few types which we'll use later.

Put these into src/lib/types.ts:

import { z } from "zod";

// This schema is used both the server function output and the props of the music card component:
export const songSchema = z.object({
    artist: z.string().describe("Artist name"),
    title : z.string().describe("Title"),
    album: z.string().describe("Album name"),
    duration: z.number().describe("Duration in seconds"),
    preview: z.string().describe("Preview URL (30 seconds)"),
    link: z.string().describe("Full song link"),
    albumCover: z.string().optional().describe("Album cover URL"),
  });

export type Song = z.infer<typeof songSchema>;

// This schema defines the server function input 
export const searchMusicInputSchema = z.object({
  query: z
    .string()
    .describe("Music search query (song title, artist name, or genre)"),
});
export type SearchMusicInput = z.infer<typeof searchMusicInputSchema>;

// This schema defines the server function input and output
export const searchMusicSchema = z.function().args(searchMusicInputSchema).returns(z.array(songSchema));

3. Create a Music Search Service

Now, let's define a NextJS server function to query the Deezer API. We'll use this later as a tool for the chatbot.

Save this to src/services/music-search.ts:

"use server";

import { SearchMusicInput, Song } from "@/lib/types";

export async function searchMusic({ query }: SearchMusicInput): Promise<Song[]> {
  const response = await fetch(
    `https://api.deezer.com/search?q=${encodeURIComponent(query)}&limit=10`
  );
  const data = await response.json();
  if (data.error) throw new Error(data.error);
  // Map Deezer API results to MusicSearchResult type
  return (data.data || []).map((item: any) => ({
    ...item,
    artist: item.artist?.name || "",
    album: item.album?.title || "",
    albumCover: item.album?.cover || ""
  }));
}

Note that we are using the same types which we defined in step 2.

4. Build the Music Miniplayer Component

For the next step, we'll design a music miniplayer React Component that looks something like this:

Put this in src/components/ui/music-card.tsx:

import { z } from "zod";
import { useState, useEffect, useRef } from "react";

import { songSchema } from "@/lib/types";
export type MusicCardProps = z.infer<typeof songSchema>;

export function MusicCard({
  title,
  artist,
  album,
  preview,
  link,
  albumCover,
}: MusicCardProps) {
  // ...
}

You can find the full code for this component here. Note that again, we are using the types from step 2.

5. Register Tools and Components with Tambo

The final step is to integrate both our music search tool and our miniplayer component into the AI chat template. That can be done simply by registering these elements (and their type definitions) with Tambo.

To do that, replace the entire contents of src/lib/tambo.ts with this code:

"use client";

// Central configuration file for Tambo components and tools
// Read more about Tambo at https://tambo.co/docs

import { TamboComponent, TamboTool } from "@tambo-ai/react";

import { MusicCard } from "@/components/ui/music-card";
import { searchMusic } from "@/services/music-search";
import { songSchema, searchMusicSchema } from "@/lib/types";

// Tambo tools registered for AI use.
export const tools: TamboTool[] = [
  {
    name: "searchMusic",
    description:
      "Searches for music by song title, artist name, or any music-related query.",
    tool: searchMusic,
    toolSchema: searchMusicSchema,
  },
];

// Tambo components registered for AI use.
export const components: TamboComponent[] = [
  {
    name: "MusicCard",
    description: "A component that plays a song from Deezer.",
    component: MusicCard,
    propsSchema: songSchema,
  },
];

Conclusion

That's it! Your app should work now (or let me know 😉). There's a lot more that can be added, such as a loading state for the miniplayer component and any additional tools or components you can think of.

Join the Tambo Discord to see more projects you can build with Tambo!

How to extend the disk space of an AWS EC2 instance

James Murdza — Mon, 19 Aug 2024 22:55:12 +0000

This works for instances running Amazon Linux:

0. If you need to free up space quickly

Delete some journals:

sudo journalctl --vacuum-size=100M

1. Add space in the AWS console

Go to EC2, and select your instance.
Scroll to the horizontal tab bar, and click storage.
Click on the volume ID.
Select the volume, and under actions, click "Modify Volume". If this is grayed out, you have to wait.
Enter the new disk size and click modify.

2. Grow the partition

Determine the partition you want to grow:
```
sudo lsblk
```
Use growpart to grow the partition, changing xvda to the name of the partition you just determined:
```
sudo growpart /dev/xvda 1
```
Extend the filesystem to use the additional space:
```
sudo resize2fs /dev/root
```

Host your own PaaS (platform as a service) on Amazon Web Services

James Murdza — Sun, 14 Jul 2024 22:30:42 +0000

Dokku is an open-source PaaS that allows you to deploy and host multiple applications on a single server. Its functionality is similar to the backend of a service like Heroku, managing tasks such as scaling, load balancing, and database management.

Here's how you can set up Dokku from scratch on AWS:

Deployment

1. Launch the server

In the AWS control panel, create a new EC2 instance.

Select Ubuntu 12
Create a new SSH key pair
Allow public SSH, HTTP, and HTTPS access to the server

2. Configure DNS

Let's assume your domain is mydomain.com, and you want to host applications as appname.mydomain.com.

In your DNS control panel, create two records:

A Record pointing @ to the EC2 instance's public IP address
A Record pointing * to the EC2 instance's public IP address

3. Setup the server

SSH into the EC2 instance and install Dokku:

wget -NP . https://dokku.com/bootstrap.sh
sudo DOKKU_TAG=v0.34.6 bash bootstrap.sh
dokku domains:set-global mydomain.com
cat ~/.ssh/authorized_keys | dokku ssh-keys:add admin

Your Dokku server should now be up and running! If you want, you can use the following steps to test your installation and see how Dokku works.

Testing that it works

1. Create a test application

On the same EC2 instance, run:

dokku apps:create myapp
sudo dokku plugin:install https://github.com/dokku/dokku-postgres.git
dokku postgres:create railsdatabase
dokku postgres:link railsdatabase ruby-getting-started

2. Set up SSH authentication

On your local machine, add the following to .ssh/config:

Host mydomain.com
    HostName mydomain.com
    User dokku
    IdentityFile ~/ServerKey.pem

3. Deploy a test application

Then, on your local machine, run these commands to deploy a test application:

git clone https://github.com/heroku/ruby-getting-started
cd ruby-getting-started
git remote add dokku dokku@example.com:myapp
git push

🧑‍💻 12 Discord Communities for Learning to Code

James Murdza — Sat, 13 Jul 2024 15:11:23 +0000

When you're learning to code, having a strong community can make all the difference in your learning journey! If you have no community around you, you can quickly find some like-minded learners on Discord. Here's a curated list of Discord server that an aspiring coder should consider joining:

Certainly! Here's the revised list in the requested format:

1. The Odin Project

🟢 Members Online: 17k

The Odin Project is a supportive community focused on web development, offering a comprehensive curriculum and discussions for all levels.

🔗 Join link: Join The Odin Project Discord Server

2. The Coding Den

🟢 Members Online: 23k

The Coding Den is a welcoming space for coders of all levels, providing resources, coding help, and general programming discussions.

🔗 Join link: Join The Coding Den Discord Server

3. The Programmer's Hangout

🟢 Members Online: 22k

The Programmer's Hangout is a friendly community for discussing various programming topics, sharing knowledge, and getting coding help.

🔗 Join link: Join The Programmer's Hangout Discord Server

4. Harvard CS50

🟢 Members Online: 23k

Harvard CS50's official Discord offers resources, peer support, and guidance for course participants.

🔗 Join link: Join Harvard CS50 Discord Server

5. Codecademy

🟢 Members Online: 8k

Codecademy's official community provides support, project sharing, and discussions for learners.

🔗 Join link: Join Codecademy Discord Server

6. JavaScript Mastery

🟢 Members Online: 4k

JavaScript Mastery is a focused community for JavaScript enthusiasts, offering resources, project collaborations, and coding help.

🔗 Join link: Join JavaScript Mastery Discord Server

7. Python

🟢 Members Online: 46k

Python's community is one of the largest for Python learners, providing resources, coding help, and discussions on Python topics.

🔗 Join link: Join Python Discord Server

8. Devcord

🟢 Members Online: 4k

Devcord is a community for web developers, offering support, resources, and discussions on front-end and back-end development.

🔗 Join link: Join Devcord Discord Server

9. Free Code Camp

🟢 Members Online: 4k

Free Code Camp's official Discord provides support, resources, and collaboration opportunities for learners.

🔗 Join link: Join Free Code Camp Discord Server

10. CodeSupport

🟢 Members Online: 3k

CodeSupport is a helpful community offering coding help, resources, and discussions on various programming topics.

🔗 Join link: Join CodeSupport Discord Server

11. Devpost

🟢 Members Online: 1k

Devpost's official Discord offers support and collaboration opportunities for hackathon enthusiasts.

🔗 Join link: Join Devpost Discord Server

12. DonTheDeveloper

🟢 Members Online: 230

DonTheDeveloper is a smaller community offering personalized support, career advice, and discussions.

🔗 Join link: Join DonTheDeveloper Discord Server

Know a great server that I missed? Leave a comment below!

Host your own web-based collaborative IDE

James Murdza — Sat, 01 Jun 2024 00:49:59 +0000

Intro

I recently got to try Ishaan Dey's Sandbox, (ishaan1013/sandbox) which is an open source web-based editor similar to Replit that lets you write and run code in your browser.

In this post I write down the steps I followed to get the project running locally.

Quick note—in some of the text below you may see the use of emojis like 🍎 in example code. It should be very obvious what you need to put in place of the emojis—if not, leave a comment!

0. Requirements

The application uses NodeJS and can be run with Docker.

Needed accounts to set up:

Clerk: Used for user authentication.
Liveblocks: Used for collaborative editing.
E2B: Used for the terminals and live preview.
Cloudflare: Used for relational data storage (D2) and file storage (R2).

A quick overview of the tech before we start: The deployment uses a NextJS app for the frontend and an ExpressJS server on the backend. Presumably that's because NextJS integrates well with Clerk middleware but not with Socket.io.

1. Initial setup

No surprise in the first step:

git clone https://github.com/jamesmurdza/sandbox
cd sandbox

Run npm install in:

/frontend
/backend/database
/backend/storage
/backend/server
/backend/ai

2. Adding Clerk

Setup the Clerk account.
Get the API keys from Clerk.

Update /frontend/.env:

NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY='🔑'
CLERK_SECRET_KEY='🔑'

3. Deploying the storage bucket

Go to Cloudflare.
Create and name an R2 storage bucket in the control panel.
Copy the account ID of one domain.

Update /backend/storage/src/wrangler.toml:

account_id = '🔑'
bucket_name = '🔑'
key = 'SUPERDUPERSECRET'

In the /backend/storage/src directory:

npx wrangler deploy

4. Deploying the database

Create a database:

npx wrangler d1 create sandbox-database

Use the output for the next setp.

Update /backend/database/src/wrangler.toml:

database_name = '🔑'
database_id = '🔑'
KEY = 'SUPERDUPERSECRET'
STORAGE_WORKER_URL = 'https://storage.🍎.workers.dev'

In the /backend/database/src directory:

npx wrangler deploy

5. Applying the database schema

Delete the /backend/database/drizzle/meta directory.

In the /backend/database/ directory:

npm run generate
npx wrangler d1 execute sandbox-database --remote --file=./drizzle/0000_🍏_🍐.sql

6. Configuring the server

Update /backend/server/.env:

DATABASE_WORKER_URL='https://database.🍎.workers.dev'
STORAGE_WORKER_URL='https://storage.🍎.workers.dev'
WORKERS_KEY='SUPERDUPERSECRET'

7. Adding Liveblocks

Setup the Liveblocks account.

Update /frontend/.env:

NEXT_PUBLIC_LIVEBLOCKS_PUBLIC_KEY='🔑'
LIVEBLOCKS_SECRET_KEY='🔑'

8. Adding E2B

Setup the E2B account.

Update /backend/server/.env:

E2B_API_KEY='🔑'

9. Adding AI code generation

In the /backend/ai directory:

npx wrangler deploy

Update /backend/server/.env:

AI_WORKER_URL='https://ai.🍎.workers.dev'

10. Configuring the frontend

Update /frontend/.env:

NEXT_PUBLIC_DATABASE_WORKER_URL='https://database.🍎.workers.dev'
NEXT_PUBLIC_STORAGE_WORKER_URL='https://storage.🍎.workers.dev'
NEXT_PUBLIC_WORKERS_KEY='SUPERDUPERSECRET'

11. Running the IDE

Run npm run dev simultaneously in:

/frontend
/backend/server

The halting problem in computer science...actually explained

James Murdza — Fri, 24 May 2024 13:33:10 +0000

In the next five minutes you will learn— 1) What is the halting problem and why it is important 2) Some examples of halting and non-halting programs 3) Alan Turing's formal proof

Often, computers hang...
Progress bars stop or go backwards...
Or you get the dreaded spinning beach ball of death. ☠️

Does this mean that some programmer just get sloppy somewhere, or is it an unavoidable fact of life?

Actually, according to computer science, this is just life!

And that’s because fundamentally—for an arbitrary program—there’s no way to predict how long a program will take to run without running it.

This was proven by the mathematician Alan Turing in 1936.

Now, you're probably thinking, if I have a simple program like this:

def table(a, b):
    for i in range(1, a):
        for j in range(1, b):
            print(i, j)

Of course I can calculate how long it takes to run.

(A iterations x B iterations = A x B print statements)

But that required us reading the code of the program and visualizing the possible paths through the program.

(This is called static analysis, by the way—analyzing a program without actually running it.)

And as a program becomes more complex, this becomes increasingly painful to do. And actually, there's no general way to do this for any program.

This is where the halting problem comes in.

Formulated by Turing, the problem asks:

Given a program and an input, can we determine if the program will eventually halt (finish running) or if it will run forever?

Let’s look at one more slightly better example before trying to solve the halting problem:

def fibonacci(n):
    if n == 0:
        return 0
    elif n == 1:
        return 1
    else:
        return fibonacci(n - 1) + fibonacci(n - 2)

This program will halt if n is a non-negative integer. Otherwise, it will run forever!

We figured this out because we are smart human beings, who can read the code and work backwards.

But now, look at Alan Turing's challenge—Can we write a computer program that will figure this out for us, regardless of the program?

Spoiler alert: No program can do this.

And this is what he said: If it were possible, that means you should be able to make a program like this:

def will_halt(program):
    if blah blah blah:
        return true
    else:
        return false

Which can clearly never be written!

To see why, we can write another mischievous program:

def tricky_program():
    if will_halt(tricky_program):
        while True:
            pass
    else:
        return

This program references the will_halt program to check what will_halt expects it to do, and does the opposite.

Wait, the program passed to will_halt can also use will_halt itself? Isn’t that cheating?

Well no—if the program will_halt can be written, then then there's no reason the same logic couldn’t be used within tricky_program. It's just code.

While this may seem like a depressing outcome for software development everywhere, this is actually just the beginning of what makes computer programming a lot of fun. Just ask Alan Turing—he was having fun with this 40 years before the first personal computer was invented!

P.S. Of course, in the year 2024, you certainly have one thought after reading this. "OK, so we can't write a program that solves the halting problem, but we can train an AI to do it!" Well, the answer is still technically no, but that's a post for another day...

Seven Sites to Find Free Low-Code App Templates

James Murdza — Sun, 14 Jan 2024 21:33:28 +0000

Starting with low-code or with a template can make your prototyping process faster, and take the risk out of launching your ideas. Why not try a low-code template? The hardest thing about using a template is finding the right one, and that's where this list can help:

1. Bubble

Marketplace Link: Bubble Templates
Description: Bubble offers a vast marketplace of both free and paid templates, covering a wide range of categories, including games, marketplaces, and social networks. It's a go-to platform for quickly prototyping apps with low-code development.

2. Flutter Flow

Marketplace Link: Flutter Flow Templates
Description: Flutter Flow specializes in mobile app development and provides templates for various apps, such as chat GPT clones and Spotify-like music streaming apps. It's a powerful tool for creating mobile apps effortlessly.

3. Adalo

Marketplace Link: Adalo Templates
Description: Adalo offers UI component examples and some full-featured apps, including an app similar to Goodreads. It's a great choice for those looking to build apps with a focus on user interface and experience.

4. Glide

Marketplace Link: Glide Templates
Description: Glide is ideal for data-heavy applications like inventory management or trackers. It simplifies database app development and provides templates to get you started quickly.

5. Voice Flow

Marketplace Link: Voice Flow Templates
Description: Voice Flow is a specialized platform for creating chatbots and integrates seamlessly with popular messaging apps like WhatsApp, Discord, and Slack. It's perfect for automating conversations and interactions.

6. BuildShip

Marketplace Link: BuildShip Templates
Description: Build Ship is a low-code backend platform that offers templates for building fully-featured apps, including bots. It's a valuable resource for developers looking to streamline backend development.

7. Share Tribe

Marketplace Link: Share Tribe Examples
Description: Share Tribe allows users to create community-based websites for buying, selling, or renting. It provides a gallery of examples showcasing websites built with Share Tribe for inspiration, making it easy to kickstart community-driven projects.

8. Softr

Marketplace Link: Softr Templates
Description: Like Glide, Softr excels in managing data-heavy tasks like inventory and trackers, simplifying app development with its templates and user-friendly interface.

Five APIs for AI text-to-speech 🗣️

James Murdza — Tue, 02 Jan 2024 18:02:03 +0000

If you need to narrate text to audio, there are a number of great sounding services which provide APIs. Many have generous free tiers! See below for a comparison:

Summary

Service & Quality	Cost to Narrate The Sorcerer's Stone	Cost to Narrate the Harry Potter Series	Sample
OpenAI (Standard)	$6.75	$100.50
OpenAI (HD)	$13.50	$201.00	Audio
ElevenLabs (HD)	$13.20	$200.70	Audio
Google Cloud (Standard)	Free	$10.80
Google Cloud (Neural)	Free	$91.20	Audio
Google Cloud (Studio)	$56.00	$1,056.00	Audio
Amazon Polly (Standard)	Free	$2.28	Audio
Amazon Polly (Neural)	Free	$9.12	Audio
Amazon Polly (Long-form)	Free	$62.00	Audio

The Sorcerer's Stone is 450,000 characters and the Harry Potter series is 6,700,000 characters.

Pricing plans per service

OpenAI

Standard: $0.015 / 1K characters
HD: $0.030 / 1K characters
https://openai.com/pricing

ElevenLabs

HD: $.030 / 1K characters (first 10,000 are free)
Note: Pricing scales down to $.017 in higher tiers.
https://elevenlabs.io/pricing

Google Cloud

Standard: $0.004 / 1K characters (first 4,000,000 are free)
Neural: $0.016 / 1K characters (first 1,000,000 are free)
Long-form: $0.16 / 1K characters (first 100,000 are free)
https://cloud.google.com/text-to-speech/pricing

Amazon Polly

Standard: $0.0004 / 1K characters (first 5,000,000 are free)
Neural: $0.0016 / 1K characters (first 1,000,000 are free)
Long-form: $0.01 / 1K characters (first 500,000 are free)
https://aws.amazon.com/polly/pricing/

The 20 most used React libraries

James Murdza — Fri, 29 Dec 2023 07:40:49 +0000

The libraries in this list cater to a wide array of needs from user interface design to data management and animations. If you're a front-end developer using React, you will run into these eventually, so might as well get familiar with them now!

react-router-dom: Simplifies client-side routing for multi-page web apps. Learn more
axios: The go-to choice for hassle-free HTTP requests and API calls. Learn more
react-redux: A powerhouse for efficient state management and data flow control. Learn more
react-bootstrap: Speeds up UI development with pre-designed responsive components. Learn more
styled-components: Allows for maintainable styling with CSS-in-JS. Learn more
@material-ui: Offers Material Design-inspired UI components for modern aesthetics. Learn more
moment: Handles date and time manipulations with ease. Learn more
react-icons: Quickly integrate a variety of icons into your React app. Learn more
@emotion/react: Elevates your styling game with CSS-in-JS capabilities. Learn more
lodash: Provides a wealth of utility functions for data manipulation. Learn more
classnames: Makes dynamic CSS class application a breeze. Learn more
@fortawesome/react-fontawesome: Access Font Awesome icons with customization options. Learn more
firebase: Simplifies serverless functionality integration into your app. Learn more
react-toastify: Enhance user experience with customizable toast notifications. Learn more
antd: Empowers you with enterprise-level UI components and layouts. Learn more
uuid: Generates universally unique identifiers for various purposes. Learn more
date-fns: Simplifies date and time operations with a robust library. Learn more
history: Effortlessly manage session history in single-page apps. Learn more
framer-motion: Add smooth animations and transitions to your React components. Learn more
react-select: Create highly customizable and user-friendly select inputs in your React applications. Learn more

(Sourced from a survey of over 600 popular repositories.)

SEO for websites with multiple languages 🇬🇧🇫🇷🇨🇳

James Murdza — Wed, 27 Dec 2023 06:16:12 +0000

If your website contains content that is available in multiple languages, you may want to let Google know.

Let's say you have a page which is available in three languages: English, French and Mandarin Chinese.

You would first look up the correct language codes for those languages (see below) and then, in your page <head>, add these tags:

<link rel="alternate" hreflang="en-US” href="https://mywebsite.com" />
<link rel="alternate" hreflang="fr” href="https://mywebsite.com/fr" />
<link rel="alternate" hreflang="zh-Hans” href="https://mywebsite.com/cn" />

Language code formats

But how do you know the right language codes to put in the hreflang attribute? According to Google's SEO docs there are three valid formats:

Language code. Example: zh is Chinese
Language with a region. Example: zh-TW is Chinese as spoken in Taiwan
Language and script codes. Example: zh-Hant is Traditional Chinese

The first option should do just fine for most cases!

Lists of language codes

You can quickly find the language code you're looking for on Wikipedia.

That's it!

The minimalist guide to deploying a website in 2023 🧘

James Murdza — Sun, 24 Dec 2023 20:19:54 +0000

This short document gives suggestions for how to deploy websites in 2023 without any more expenses or work than is necessary. After getting accustomed to the right tools, it should be able to set up a fast and secure hosted website in about 30 minutes while only paying the cost of the domain name.

Domain names and DNS

Cloudflare offers low/no markup domain name registration with a free DNS service. This will virtually always be your cheapest option for domain name renewals. They don't list prices for all TLDs upfront, so use this list to get your best estimate.

Notes:

If you want to save even more money, you can register your first year on a registrar (GoDaddy, Namecheap, etc.) when they have a sale and then transfer the domain to Cloudflare. The best possible price for any TLD can normally be found on TLD List. This will only be cheaper than Cloudflare for the first year.
Another benefit to using Cloudflare is the free DNS service they provide. (For more info: "How can CloudFlare offer a free CDN with unlimited bandwidth?")

Hosting

There are a wide number of hosting services you can use which really depends on your requirements, mainly:
1) Can you get by with a static site, or do you require server-side rendering?
2) How much bandwidth will you use?
3) How much storage space will you use?

There are a variety of options you can choose for low-cost sites. Below are a few of the best:

If you just need a simple static website, consider Netlify.
- Free for unlimited sites
- Deploy via web interface, GitHub integration, or command-line tools
- 100GB/month free bandwidth
If you use GitHub and need to host a static website, consider GitHub Pages.
- Free for one site
- Stored on a GitHub public respository
- Deploy via web interface, or Git
- 100GB/month free bandwidth
If you need to run a website with a server-side backend, consider Vercel.
- Free for unlimited sites
- Supports Node.js, Next.js
- 100 GB-hours of serverless function usage (up to 10 seconds per execution)
- Deploy via GitHub integration, or command-line tools
- 100GB/month free bandwidth

All these options allow you to connect to custom domains and at least 1GB of storage. None of them require a credit card to get started. The easiest option for a static site is definitely Netlify, which even has a drag-and-drop interface for uploading files. However I included GitHub Pages since the ubiquity of GitHub among programmers makes it a very convenient option.

Note: None of these options allow you to access a server directly with SSH or FTP they way that you would with a a traditional web host. They are "serverless."

Also, if you're using Cloudflare's free CDN service as mentioned above, the traffic that your host sees could greatly be decreased due to caching, effectively giving you up to ten times more traffic while and staying within the free range.

Email

If you need simple email forwarding for your domain, you can use ImprovMX.

Free for one domain
Unlimited forwarding and addresses
Attachments up to 10MB

If you're looking for hosted email for your domain, you can use Zoho Mail.

Free for one domain
Up to five email accounts with 5GB storage each
Attachments up 25MB

The only Docker cheatsheet you need 🐳

James Murdza — Sun, 24 Dec 2023 20:14:55 +0000

My reference of the most useful commands to know when you're building in Docker:

Build and run

Build an image:

docker build -t myimage .

Build an image, deleting the old one:

docker rmi myimage && docker build -t myimage .

Build an image, and print all the steps:

docker build --progress=plain -t myimage .

Run container from image, with port forwarding:

docker run -p 80:80 myimage

Run container for debugging purposes, replacing the entrypoint with a shell:

docker run --rm -it --entrypoint bash myimage

Inventory

List all images:

docker image ls

List all containers: (The -a flag is to show stopped containers as well)

docker container ls -a

List all docker images and containers and file sizes:

docker system df -v

Show the history of an image:

docker history myimage

Clean up

**Dangling images* are untagged and not needed by any tagged images.*
**Unused image* are not needed by any existing containers.*

Delete stopped containers:

docker container prune

Remove dangling images:

docker image prune

Remove unused images:

docker image prune -a

Remove build cache:

docker builder prune