Skip to content

Latest commit

 

History

History
65 lines (49 loc) · 3.9 KB

README.md

File metadata and controls

65 lines (49 loc) · 3.9 KB

IstaAI bot written in Python that uses the completions API to have conversations with the text-davinci-003 model, and the moderations API to filter the messages.

This bot is based on https://github.com/openai/gpt-discord-bot

This bot uses the OpenAI Python Library and discord.py.

This repo is not accepting pull requests. Please fork this repo if you want to add or change features.

Features

  • /chat starts a public thread, with a message argument which is the first user message passed to the bot
  • The model will generate a reply for every user message in any threads started with /chat
  • The entire thread will be passed to the model for each request, so the model will remember previous messages in the thread
  • when the context limit is reached, or a max message count is reached in the thread, bot will close the thread
  • you can customize the bot instructions by modifying config.yaml
  • you can change the model, the hardcoded value is text-davinci-003

Setup

  1. Copy .env.example to .env and start filling in the values as detailed below
  2. Go to https://beta.openai.com/account/api-keys, create a new API key, and fill in OPENAI_API_KEY
  3. Create your own Discord application at https://discord.com/developers/applications
  4. Go to the Bot tab and click "Add Bot"
    • Click "Reset Token" and fill in DISCORD_BOT_TOKEN
    • Disable "Public Bot" unless you want your bot to be visible to everyone
    • Enable "Message Content Intent" under "Privileged Gateway Intents"
  5. Go to the OAuth2 tab, copy your "Client ID", and fill in DISCORD_CLIENT_ID
  6. Copy the ID the server you want to allow your bot to be used in by right clicking the server icon and clicking "Copy ID". Fill in ALLOWED_SERVER_IDS. If you want to allow multiple servers, separate the IDs by "," like server_id_1,server_id_2
  7. Install dependencies and run the bot 
    pip install -r requirements.txt
python -m src.main
    You should see an invite URL in the console. Copy and paste it into your browser to add the bot to your server.

Optional configuration

  1. If you want moderation messages, create and copy the channel id for each server that you want the moderation messages to send to in SERVER_TO_MODERATION_CHANNEL. This should be of the format: server_id:channel_id,server_id_2:channel_id_2
  2. If you want to change the personality of the bot, go to src/config.yaml and edit the instructions
  3. If you want to change the moderation settings for which messages get flagged or blocked, edit the values in src/constants.py. A lower value means less chance of it triggering.

FAQ

Why isn't my bot responding to commands?

Ensure that the channels your bots have access to allow the bot to have these permissions.

  • Send Messages
  • Send Messages in Threads
  • Create Public Threads
  • Manage Messages (only for moderation to delete blocked messages)
  • Manage Threads
  • Read Message History
  • Use Application Commands

Current bot configuration

The above described functionality is achievable by main_threaded.py. The main.py file is an attempt at replacing threaded answers with @ mentions within a channel (but to no avail so far).

Roadmap

The following features needed to complete the bot:

  • Give the bot access to Discord server data and enable it to generate responses via OpenAI API feeding off of the server data (message history, channels, user activity, etc)
  • Give the bot the ability to "consume content" by uploading a file (txt, pdf) to the message
  • Give the bot the ability to "consume a website" by placing a URL to the message
  • Give the bot the ability to set predefined prompts being run on certain predefined criteria ("give me a summary and a basic sentiment analysis every 7 days of #general starting now", etc)