A quick testing of OpenAI ChatGPT
run on your local environments
pip install -r requirements.txt
python server/server.pyquick start with docker-compose:
- copy your env file
mv env.example .env - change the OPEN_AI_KEY which you need get from OpenAI. Change CUSTOM_BASE_PROMPT which you want the chatGPT act as therole.
OPEN_AI_KEY="sk-xxx"
TEMPRATURE="0.5"
MAX_TOKENS="1024"
CUSTOM_BASE_PROMPT="You are ChatGPT, a large language model trained by OpenAI. You answer as concisely as possible for each response (e.g. Don't be verbose).\n"
- Start service
docker-compose up -d - Add voice recognition
- Add different prompt