OpenWebUI Discord Bot

Build your own Discord bot using OpenWebUI

This repo derived from chatGPT-discord-bot after customization for OpenWebUI.

---

Important

Major Update (2024/03):

• GPT-4 now supported for free
• Utilize OpenAI API can ensure smoother experiences, refer Optional: Configuring OpenAI API

Chat

Setup

Prerequisites

• Python 3.9 or later
• Rename the file .env.example to .env
• Running poetry install to install the required dependencies
• Google Chrome for Image Generation

---

Step 1: Create a Discord bot

1. Go to https://discord.com/developers/applications create an application

2. Build a Discord bot under the application

3. Get the token from bot setting

   

4. Store the token to .env under the DISCORD_BOT_TOKEN

   

5. Turn MESSAGE CONTENT INTENT ON

   

6. Invite your bot to your server

   • via OAuth2 URL Generator
   • Or via the standard bot preview

Step 2: Run the bot on the desktop

1. Open a terminal or command prompt

2. Navigate to the directory where you installed the OpenWebUI Discord bot

3. Run poetry run python3 -m openwebui_discord_bot.main to run the bot

---

Step 2: Run the bot with Docker

1. Build the Docker image & run the Docker container with docker compose up -d

2. Inspect whether the bot works well docker logs -t openwebui_discord_bot

   Stop the bot:

   • docker ps to see the list of running services
   • docker stop <BOT CONTAINER ID> to stop the running bot

Have a good chat!

---

Optional: Configuring OpenAI API

1. Obtain your API key by visiting https://platform.openai.com/api-keys
2. Paste the API key under OPENAI_KEY in .env
3. Set OPENAI_ENABLED to True in .env

Note

GPT-4 API is subject to certain restrictions.

Details https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4

Image Generation

Microsoft Bing Image Generation

1. Go to https://www.bing.com/chat and log in

2. Open console with F12

3. Open Application tab > Cookies

4. Copy the value for _U from cookies and paste it into .env under BING_COOKIE

Google Gemini Image Generation

1. Go to https://gemini.google.com/app and log in

2. Open console with F12

3. Open Application tab > Cookies

4. Copy the value for __Secure-1PSID from cookies and paste it into .env under GOOGLE_PSID

Optional: Setup system prompt

• A system prompt would be invoked when the bot is first started or reset

• You can set it up by modifying the content in system_prompt.txt

• All the text in the file will be fired as a prompt to the bot

• Get the first message from OpenWebUI in your discord channel!

• Go Discord setting turn developer mode on

  1. Right-click the channel you want to recieve the message, Copy ID

     

  2. paste it into .env under DISCORD_CHANNEL_ID

Optional: Disable logging

• Set the value of LOGGING in the .env to False

---

中文設置教學

---

Commands

• /chat [message] Chat with OpenWebUI/Gemini

• /draw [prompt] Generate an image with Gemini/OpenAI/Bing

• /switchpersona [persona] Switch between optional OpenWebUI jailbreaks

  • random: Picks a random persona
  • standard: Standard OpenWebUI mode
  • dan: DAN 13.5 (Latest Working OpenWebUI Jailbreak prompt)
  • Smart mode: AIM (Always Intelligent and Machiavellian)
  • Developer Mode: software developer who specializes in the AI's area

• /private OpenWebUI switch to private mode

• /public OpenWebUI switch to public mode

• /replyall OpenWebUI switch between replyAll mode and default mode

• /reset Clear OpenWebUI conversation history

• /chat-model Switch different chat model

  • gpt-4: GPT-4 model
  • Gemini: Google Gemini Model

Special Features

Switch Persona

Warning

Certain personas may generate vulgar or disturbing content. Use at your own risk.

Mode

• public mode (default) the bot directly reply on the channel

  

• private mode the bot's reply can only be seen by the person who used the command

  

• replyall mode the bot will reply to all messages in the channel without using slash commands (/chat will also be unavailable)

  Warning The bot will easily be triggered in replyall mode, which could cause program failures

---