Creating an AI Discord Bot

Creating a Discord bot that utilizes OpenAI's GPT-3.5 Turbo model involves several key steps, including setting up a Discord bot account, programming the bot with Python, and integrating the OpenAI API for interaction with the GPT-3.5 Turbo model. Below is a step-by-step guide designed for integration into Docusaurus documentation.

Requirements

Before starting, ensure you have the following:

• Python (version 3.6 or newer) installed on your machine.
• An OpenAI API key, obtained by creating an account on the OpenAI platform, then going to Settings and clicking on API keys under Platform.
• A Discord account to create a bot and obtain a Discord token.

Step 1: Setting Up a Discord Bot Account

1. Go to the Discord Developer Portal and log in with your Discord account.
2. Click the “New Application” button, give it a name, and click “Create”.
3. Navigate to the “Bot” tab on the left side, then click “Add Bot” and confirm by clicking “Yes, do it!”
4. Under the bot section, you will see the “Token”. Click “Copy” to clipboard. Keep this token private as it allows control over your bot. If you did not see your token then click the Reset Token button.
5. Navigate to the "OAUTH2" tab on the left side, then copy the client id.
6. Open the Discord application on your PC and right click on your guild(server) name, Copy the ID
7. Navigate to the "Intallation" tab on the left side, click on the Install Link dropdown and select None and save the changes.
8. Navigate back to the "Bot" tab on the left side and uncheck the Public Bot option. Then enable the Message Content Intent option and save the changes.

Step 2: Creating a Python Environment

Open your Terminal and run the following commands Create the directory for the new files

sudo mkdir /var/discord && cd /var/discord

Creating the Environment

python3 -m venv .venv

Activating the environment

source .venv/bin/activate

Step 3: Installing Required Libraries

Open your terminal or command prompt and install the following Python libraries:

python3 -m pip install discord openai python-dotenv

• discord: The library to interact with Discord.
• openai: The official OpenAI library to interact with the GPT-3.5 API.
• dotenv: Loads environment variables from .env files.

Step 4: Writing the Bot with Python

Create a new Python file for your bot, e.g., discord_bot.py, and add the following code: To create the file, run

nano discord_bot.py

Nothing in this file needs to be changed

import discord
import os
import logging
from openai import OpenAI
from dotenv import load_dotenv
load_dotenv()  # take environment variables from .env


logging.basicConfig(
    format="[%(asctime)s] [%(filename)s:%(lineno)d] %(message)s", level=logging.INFO
)

# Create a client instance for the bot
intents = discord.Intents.default()
intents.message_content = True # Enables reading messages
intents.messages = True  # Ensure this is enabled
intents.guild_messages = True  # Enables receiving messages in guilds
#intents.direct_messages = True  # Enables receiving direct messages
permissions = discord.Permissions(permissions=274877992000)
permissions.read_messages = True

client = discord.Client(intents=intents)

# This is the default and can be omitted
openai_api_key=os.environ.get("OPENAI_API_KEY"),
openai_client = OpenAI()

# Access the DISCORD_TOKEN environment variable
discord_token = os.getenv("DISCORD_BOT_TOKEN")

@client.event
async def on_ready():
    print(f'Logged in as {client.user}.')

@client.event
async def on_message(message):
    # Don't let the bot respond to its own messages
    if message.author == client.user:
        return
    
    # Check if the message starts with "ask"
    if message.content.startswith('ask') or message.content.startswith('Ask'):
        # Remove "ask" from the message to use as the prompt for the OpenAI model
        prompt = message.content[4:]
        response = generate_openai_response(prompt)
        await message.channel.send(response)

def generate_openai_response(prompt):
    """
    Generates a response using OpenAI's GPT-3.5-turbo model based on the given prompt.
    """
    try:
        response = openai_client.chat.completions.create(
          model="gpt-3.5-turbo",
          messages=[
            {
              "role": "user",
                "content": prompt
            }
          ],
          temperature=1,
          max_tokens=256,
          top_p=1,
          frequency_penalty=0,
          presence_penalty=0
          #content = response.choices[0].message.content
        )
        return response.choices[0].message.content
    except Exception as e:
        print(f"Error generating OpenAI response: {e}")
        return "Sorry, I can't process that right now."

client.run(discord_token),

Save the file with CTRL+SHIFT+X

Create the Environment file .env Run the following to create the file

nano .env

Paste the following contents

Modify the highlighted lines

OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
DISCORD_BOT_TOKEN="YOUR_DISCORD_BOT_TOKEN from step 4"
DISCORD_CLIENT_ID="CLIENT ID from step 5"

ALLOWED_SERVER_IDS="ID copied from step 6"
SERVER_TO_MODERATION_CHANNEL=1:1
DEFAULT_MODEL=gpt-3.5-turbo

Replace YOUR_OPENAI_API_KEY with your actual OpenAI API key and YOUR_DISCORD_TOKEN with your Discord bot token.

Step 5: Creating Systemd File to run the bot on system boot

nano /etc/systemd/system/discord_bot.service

Paste the following

[Unit]
Description=Discord AI Bot service

[Service]
User=root
WorkingDirectory=/var/discord
ExecStart=/var/discord/.venv/bin/python3 -m discord_bot

[Install]
WantedBy=multi-user.target

Enable the service

sudo systemctl enable discord_bot.service

Reload daemon

sudo systemctl daemon-reload

Start the service

sudo systemctl start discord_bot

Step 6: Adding the Bot to Your Discord Server

1. In the Discord Developer Portal, navigate to the “OAuth2” tab.
2. Under “Scopes,” select “bot” and then set the permissions your bot needs under “Bot Permissions.” At a minimum, your bot will need permission to send messages, read message history, send messages in threads and view channels.
3. Copy the generated URL under “Scopes,” open it in your web browser, and select the server to add your bot.

Testing the Bot

Once the bot is added to your server, you can test it by sending a command in the format !ask <your question here> in any text channel where the bot has permission to read and write messages.

Conclusion

You have now created a Discord bot powered by OpenAI's GPT-3.5 model capable of answering questions or performing tasks based on user input. This bot can be expanded further with additional commands or more complex interactions, leveraging the powerful capabilities of the GPT-3.5 model to enhance your Discord server's functionality and user engagement.