Open-Assistant Data Collection Discord Bot

This bot collects human feedback to create a dataset for RLHF-alignment of an assistant chat bot based on a large language model. You and other people can teach the bot how to respond to user requests by demonstration and by ranking the bot's outputs. If you want to learn more about RLHF please refer to OpenAI's InstructGPT blog post.

Invite official bot

To add the official Open-Assistant data collection bot to your discord server click here. The bot needs access to read the contents of user text messages.

Contributing

If you are unfamiliar with hikari, lightbulb, or miru, please refer to the large list of examples

Setup

To run the bot

cp .env.example .env

python -V  # 3.10

pip install -r requirements.txt
python -m bot

Before you push, make sure the pre-commit hooks are installed and run successfully.

pip install pre-commit
pre-commit install

...

git add .
git commit -m "<good commit message>"
# if the pre-commit fails
git add .
git commit -m "<good commit message>"

To test the bot on your own discord server you need to register a discord application at the Discord Developer Portal and get at bot token.

1. Follow a tutorial on how to get a bot token, for example this one: Creating a discord bot & getting a token
2. The bot script expects the bot token to be in the .env file under the TOKEN variable.

Resources

Structure

Important files

.env                        # Environment variables
.env.example                # Example environment variables
CONTRIBUTING.md             # This file
README.md                   # Project readme
EXAMPLES.md                 # Examples for commands and listeners
requirements.txt            # Requirements

bot/
├─  __main__.py             # Entrypoint
├─  api_client.py           # API Client for interacting with the backend
├─  bot.py                  # Main bot class
├─  settings.py             # Settings and secrets
├─  utils.py                # Utility Functions
│
├─  db/                     # Database related code
│   ├─  database.db         # SQLite database
│   ├─  schema.sql          # SQL schema
│   └─  schemas.py          # Python table schemas
│
└── extensions/             # Application logic, see https://hikari-lightbulb.readthedocs.io/en/latest/guides/extensions.html
    ├─  work.py             # Task handling logic  <-- most important file
    ├─  guild_settings.py   # Server specific settings
    └─  hot_reload.py       # Utility for hot reload extensions during development

Adding a new command/listener

1. Create a new file in the extensions folder
2. Copy the template below

# -*- coding: utf-8 -*-
"""My plugin."""
import lightbulb

plugin = lightbulb.Plugin("MyPlugin")

# Add your commands here

def load(bot: lightbulb.BotApp):
    """Add the plugin to the bot."""
    bot.add_plugin(plugin)


def unload(bot: lightbulb.BotApp):
    """Remove the plugin to the bot."""
    bot.remove_plugin(plugin)

Docs

Discord

• Discord API Reference

hikari (main framework)

• Hikari Repo
• Hikari Docs

lightbulb (command handler)

• Lightbulb Repo
• Lightbulb Docs

miru (component handler: buttons, modals, etc... )

• Miru Repo