Skip to content

A Discord bot designed to summarize chaotic text channels using GPT-3. Slotherizer bridges the gap between high-volume chat activity and information retention, featuring integrated ELK stack monitoring for usage metrics.

Notifications You must be signed in to change notification settings

bazingiu/Slotherizer

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

53 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Slotherizer

Slotherizer ensures you don't miss any updates in busy Discord text channels, thanks to automatic summaries generated with GPT-3.

Getting Started

  1. You will need a Discord bot to connect to the system. Create a new one by following this guide

    You will need the bot Token to add to the System configuration (Check this guide)

  2. You will also need an OpenAI account to use the GPT-3 based APIs

    You will need:

    • The Organization ID (Which you can find on this page)
    • The API Key (Which you can find on this page)
  3. Create the environment variable configuration file .env in the project root

    DISCORD_TOKEN="<Token>"
    ORGANIZATION="<Organization ID>"
    OPENAI_API_KEY="<API Key>"
    
  4. Run docker-compose up to build and start Slotherizer

How to use it

To use the Discord bot you must first invite it to your Discord server (Follow this guide).

When the bot is in a server, you can invoke it in text chats using the command !slotherizer <n>, replacing <n> with the number of messages you want to summarize.

Metrics

In this project, we use Kibana to visualize system usage metrics. There is a default version included that can be imported into Kibana as soon as it starts, providing a dashboard with some useful metrics: kibana/monitoring.ndjson

About

A Discord bot designed to summarize chaotic text channels using GPT-3. Slotherizer bridges the gap between high-volume chat activity and information retention, featuring integrated ELK stack monitoring for usage metrics.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 76.5%
  • Python 20.8%
  • Dockerfile 2.7%