comment-ai-moderation

Description

comment-ai-moderation is a library that allows you to moderate comments/texts using OpenAI LLM in its gpt-3.5-turbo version. Based on the comment/text received by the "moderate" function, the model will analyze its content and context and then return relevant information that allows the user to know whether the comment should be banned or not along with the corresponding reason.

Installation

To install the library, you can use npm:

npm install comment-ai-moderation

Usage

First, you need to import the moderate function from the library:

import { moderate } from 'comment-ai-moderation';

Next, you need to have a valid OpenAI api key (keep in mind that this is a paid service).

In your environment variables file you must define the api key as follows:

 OPENAI_API_KEY= your_openai_key

Finally, to moderate a comment all you have to do is use the function as follows

 moderate("Your example comment")

Example Response

 moderate("This event rules!")

{
  sentiment: 'positive',
  aggressiveness: '1',
  ban: false,
  reason: '',
  language: 'English'
}

 moderate("You are a bastard!")

{
  sentiment: 'negative',
  aggressiveness: '5',
  ban: true,
  reason: 'offensive',
  language: 'English'
}

Contributions

Contributions to comment-ai-moderation are welcome. Please ensure you follow code and testing conventions before making a pull request.

License

This project is licensed under the terms of the MIT license. See the LICENSE file for details.