This project is a simple chat completion client using a private api proxy that has a lot of language models including gpt-3.5-turbo, gpt-4, and other opensource models as well. It allows users to input a prompt and receives possible completions from the models.
- Uses a private api proxy for chat completion
- Supports both non-streaming and streaming mode
- Allows users to select one of the provided choices or input their own response
- Clone the repository and install dependencies using
pip install -r requirements.txtorpip3 install -r requirements.txt - Set the
API KEYinopenai.api_key = ""to the API given to you. - Run the script using
python main.py