A simple Discord bot integrating OpenAI libraries for ChatGPT and DALL-E, capable of generating text and images in Discord conversations.
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
Table of Contents
Formerly known as 'Aurora AI', Aurora AI is a Discord chatbot that utilizes the GPT-3.5-Turbo language model by OpenAI. Built with discord.js, it generates responses to user input in a conversational format. Designed for simplicity, it's a great tool to explore the capabilities of GPT-3.5-Turbo within Discord. Additionally, it also supports the use of DALL-E, the image generation model also developed by OpenAI, allowing it to generate creative images alongside its natural language abilities.
-
Get a necessary API Keys
-
Clone the repo
git clone https://github.com/KrozT/openai-discord.git
-
Install packages
yarn install
-
Add the API Keys to your environment variables
DISCORD_API_KEY='YOUR DISCORD API KEY' OPENAI_API_KEY='YOUR OPENAI API KEY'
-
Build project
yarn run build
-
Start binaries
yarn run start
Once you have the project initialized just add the bot to your server and enjoy.
Command | Options | Type | Description |
---|---|---|---|
/ping |
ephimeral |
embed-info |
Ping the bot to check if it is online |
/about |
ephimeral |
embed-info |
Get information about the bot |
/help |
ephimeral |
embed-info |
Get a list of all the commands |
/chat |
question ephimeral |
embed-request embed-response |
Chat with the bot |
/clear |
None | embed-info |
Clear the chat history with the bot |
/image |
prompt quantity size ephimeral |
embed-request embed-response |
Generate an image with the bot |
Option | Command | Required | Default | Choices | Description |
---|---|---|---|---|---|
question |
/chat |
true |
None | None | The question to ask the bot |
prompt |
/image |
true |
None | None | The text to generate the image from |
quantity |
/image |
false |
1 |
1 to 10 |
Quantity of images to generate |
size |
/image |
false |
256x256 |
256x256 512x512 1024x1024 |
Size of the image to generate |
ephimeral |
/ping /about /help /chat /image |
false |
false |
true false |
Hide the response from other users |
The bot uses a variety of visual embeds code located in the footer of each message. The following table describes the embeds and their colors.
Footer | Color | Description |
---|---|---|
embed-info |
Aqua | System message by the bot |
embed-error |
Red | Error message by the bot |
embed-response |
Green | Response by the bot with AI-generated content |
embed-request |
Gold | Request by the user |
- Docker Integration
- Dockerfile
- Docker Compose
- Discord Integration
- API REST
- Slash Commands
- Text Channels
- Ephemeral (Optional)
- Direct Messages
- Ephemeral (Optional)
- Language Model Integration
- GPT-3.5
- Chat
- GPT-4
- GPT-3.5
- DALL-E Integration
- Image generation
- Image editing
- Context-based usability
- Single user
- Multiple users
See the open issues for a full list of proposed features (and known issues).
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
Distributed under the MIT License. See LICENSE
for more information.