Hello everyone. Someone implemented the printing effect in GPT-3.5, can you tell me how you did it or what methods you used for this?
Welcome to the community @cf6oz70e
If you’re referring to streaming.
Here’s how you can do it in python:
for line in openai.ChatCompletion.create(model="gpt-3.5-turbo",
messages=conversation,
max_tokens=100,
stream=True):
token = getattr(line.choices[0].delta, "content", "")
print(token, end="")