OpenAI has not released a specific “ChatGPT template”. However, OpenAI does provide extensive information on how to implement and interact with the ChatGPT models using their API. You can find details in the OpenAI Cookbook’s guide on how to use the ChatGPT.
ChatGPT is based on the GPT “base” models, just like Text Generation GPT. It uses the transformer architecture that has been trained with Reinforcement Learning from Human Feedback (RLHF). Prompt engineering is often used to control the model’s behavior. Responses from the model can be received as a list to simulate a conversation.
To use the ChatGPT, you pass an array of message objects, each containing a ‘role’ and ‘content’. The ‘role’ can be ‘system’, ‘user’, or ‘assistant’, and the ‘content’ is the text of the message from the role.
For more information, you can visit OpenAI’s official documentation: https://platform.openai.com/docs/guides/chat/
