MultiRole-ChatGPT

Description

Welcome to the MultiRole-ChatGPT repository! This project is a Python-based orchestration system designed to manage multiple GPT-based AI models with varying roles and intelligence levels. It's built to handle complex queries and make intelligent decisions through a multi-model approach.

Table of Contents

1. Installation
2. Configuration
3. Usage
4. License

Installation

To get started, you'll need to clone the repository:

git clone git@github.com:patterns-complexity/multirole-chatgpt.git

Then go to the project directory:

cd multirole-chatgpt

Then install the required packages:

pip install -r requirements.txt

Configuration

Provide your OpenAI API Key

• Rename .env.example to .env.
• Fill in your OpenAI API Key in .env.

# file: /.env
OPENAI_API_KEY=your_api_key_here

Where to get the API key from?

You can get your OpenAI API Key here:

• https://platform.openai.com/account/api-keys.

Warning

In order for this code to work, you need to have access to the following models:

• gpt-3.5-turbo - available by default at the time of writing this README.
• gpt-4 - you have to top up your OpenAI account with at least $1 worth of prepaid credits to access this model. Doing it will immediately unlock the gpt-4 model for you.

Usage

To run the project, simply execute the following command:

python ./app.py

You'll be prompted to enter your query. The manager will then communicate with the designated models to provide you with a well-rounded answer.

License

This project is licensed under the MIT License.