Would it be possible for someone to give an example of using the stream parameter to print a completion in real time kind of like how ChatGPT would print a response?
I have the code:
import openai
# Set the API key for OpenAI
openai.api_key = "YOUR_API_KEY"
def generate_response(prompt):
completions = openai.Completion.create(
engine="text-davinci-003",
prompt=prompt,
max_tokens=256,
n=1,
stop=None,
temperature=0.9,
)
message = completions.choices[0].text
return message
# Example usage
while True:
user_input = input("You: ")
if user_input == "exit":
break
response = generate_response(user_input)
print(f"ChatGPT: {response}")
But I want to modify this to use streaming and print the response as it comes in.