OpenAI PoC implemented in Next.js

This repository was developed using openai-node and based on openai-quickstart-node, with several additional elements added.

• Supports styled-components and TypeScript
• Remember conversation context instead of one-time responses
• More intuitive and clean UI with easy customization options

Getting Started

1. If you don’t have Node.js installed, install it from here (Node.js version >= 14.6.0 required)

2. Clone this repository

3. Navigate into the project directory

   $ cd openai-poc

4. Install the requirements

   $ npm install

5. Make a copy of the example environment variables file

   On Linux systems:

   $ cp .env.example .env

   On Windows:

   $ copy .env.example .env

6. Add your API key to the newly created .env file

7. Run the app

   $ npm run dev

8. Deploy it to the cloud with Vercel (Documentation)

Customizing the Model

You can customize the following model-related variables in the setting.ts file.

Variable	Description	Option	Type
PREFIX	Prefix to include in all conversations	Whatever you want (language, role, tone..)	string
MODEL	Models	Available models	string
TEMPERATURE	Adjust your settings	Number between 0 and 1	number
MAX_TOKENS	What are tokens and how to count them?	Maximum number of tokens allowed by each model	number

License

MIT