This is a ChatGPT-powered Slack chatbot built on the Bolt JS framework. The bot includes canned responses and falls back to ChatGPT for messages that don't match a predefined pattern. You can customize the bot's personality and responses to suit your needs.
You will need a local Redis installation to persist the bot's conversation memory. You can install Redis server on Ubuntu like this:
sudo apt -y install redis-server- Go to https://api.slack.com/apps
- Click Create App
- Choose a workspace
- Copy the manifest.yaml contents into the input box
- Update the name and display name settings
- Click Create
Once the app is created click Install to Workspace Then scroll down in Basic Info and click Generate Token and Scopes with all three scopes enabled.
# Replace with your bot and tokens
export SLACK_BOT_TOKEN=<your-bot-token> # from the OAuth section
export SLACK_APP_TOKEN=<your-app-level-token> # from the Basic Info App Token Section
export SLACK_BOT_USER_NAME=<your-bot-username> # must match the short name of your bot user
export OPENAI_API_KEY=<your-openai-api-key> # get from here: https://platform.openai.com/account/api-keys
export BOT_PERSONALITY="Your custom bot personality prompt here" # Optional: Set a custom personality for your bot
export THINKING_MESSAGE=":gear: _Processing your request..._" # Optional: Customize the thinking indicator message# Replace with your bot and tokens
$env:SLACK_BOT_TOKEN = "xoxb-your-bot-token"
$env:SLACK_APP_TOKEN = "xapp-your-app-token"
$env:SLACK_BOT_USER_NAME = "Data" # Change to match your bot's name
$env:OPENAI_API_KEY = "your-openai-api-key"
$env:BOT_PERSONALITY = "Your custom bot personality prompt here" # Optional: Set a custom personality for your bot
$env:THINKING_MESSAGE = ":gear: _Processing your request..._" # Optional: Customize the thinking indicator message
# Optional: Set Redis URL if you're using a custom Redis instance
# $env:REDIS_URL = "redis://localhost:6379"
# Start the bot
npm start# Clone this project onto your machine
git clone https://github.com/scarolan/data.gitThe bot's personality is now configurable via the BOT_PERSONALITY environment variable. You can set this in your script or directly in your environment:
# Example of customizing the bot's personality
export BOT_PERSONALITY="You are a helpful assistant with a cheerful disposition. You love to tell jokes and answer questions clearly and concisely."If you don't set the BOT_PERSONALITY variable, the bot will use a default Star Trek "Data" personality.
# Change into the project
cd data
# Install the dependencies
npm installnpm run startGo to the installed workspace and type help in a DM to your new bot.
Use the /dalle slash command for functionality:
Direct mention example (in a channel or DM):
@Data help
Slash command example (image generation):
/dalle An image of Lt. Commander Data and his cat
You'll need a Linux server, container, or application platform that supports nodejs to keep the bot running. Slack has a tutorial for getting an app running on the Glitch platform: https://api.slack.com/tutorials/hello-world-bolt
The bot supports generating images with DALL-E through the /dalle slash command.
Note: The older direct @Data image ... handler was removed to simplify the codebase. Please use /dalle for image generation.
When using the /dalle slash command:
- The bot acknowledges your request and shows a "generating" message
- Image generation happens asynchronously in the background
- When complete, the image is posted directly to the channel
| Variable | Required | Description |
|---|---|---|
| SLACK_BOT_TOKEN | Yes | Your Slack bot token from OAuth section |
| SLACK_APP_TOKEN | Yes | Your Slack app-level token |
| SLACK_BOT_USER_NAME | Yes | Must match the short name of your bot user |
| OPENAI_API_KEY | Yes | Your OpenAI API key |
| BOT_PERSONALITY | No | Custom personality prompt for your bot |
| THINKING_MESSAGE | No | Custom thinking indicator message |
| REDIS_URL | No | Custom Redis URL (default: redis://localhost:6379) |