AI powered discord bot
NOTE: In order to run Shappie, you'll need the appropriate environment variables. These must go in a file called
.env.prod
in the same directory as thedocker-compose.yml
This application is packaged as a Docker container. You can use Docker Compose to manage the container.
First, you need to install Docker and Docker Compose on your server if you haven't done so already. You can find instructions in the Docker documentation:
- Docker: https://docs.docker.com/get-docker/
- Docker Compose: https://docs.docker.com/compose/install/
Once Docker and Docker Compose are installed, you can use the following commands to manage the application.
docker-compose -f docker-compose.yml up --build -d
This command builds the Docker image for the application (if it hasn't been built already or if the Dockerfile has changed), and starts the application in the background.
This may take a few seconds
docker-compose down
When you want to update the application to the latest version, you can use the following commands:
docker-compose down
docker-compose -f docker-compose.yml up --build -d
This will stop the current application container, rebuild the Docker image, and start a new container with the latest version of the application.
docker-compose stop db
docker-compose rm db
docker volume rm shappie_shappie-db
docker-compose up --build -d db
docker-compose logs db
Tool functions should return a dictionary with various options:
use_llm
: This tells the bot to use the LLM to respond to the message, this requirescontext
.context
: Additional context passed to the LLM when responding after a using a tool.conent
: The content of the message if not using an LLM. This is added by the LLM ifuse_llm
isTrue
.image_url
: Creates an embed using the given image URL. Used for GIFs currently.url
: Creates an embed with the given URL. Used forwhen2meet
right now.