My project is a ChatGPT replica that uses OpenAI's API to generate responses to user prompts. The web UI is designed to mimic the look and functionality of the ChatGPT interface. The user enters text prompts in the UI, which are sent to a Python backend via Ajax requests. The Python backend then makes a call to OpenAI's API to generate a response based on the user's prompt and then sent back to Ajax.
The project also features a side panel that allows the user to adjust the temperature and number of tokens sent to OpenAI's API. The temperature parameter controls the creativity of the AI-generated responses, while the number of tokens parameter determines the length of the response. By adjusting these settings, the user can fine-tune the AI-generated responses to their liking.