I want to train my model with few-shot prompting for a custom chatbot but it's giving me error.
My script:
response = openai.Completion.create(
model = "gpt-3.5-turbo",
messages = conversation,
temperature = 0.6
#max_tokens = 150,
)
Conversations:
conversation=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Who won the world series in 2020?"},
{"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
]