System messages
Your previous messages gave you a valid response, but it also allows users to ask any question they like, even if it doesn't relate to internet service support. In this exercise, you'll utilize a system message to steer the model into only answering customer questions about their internet service.
The Llama model is still available as llm.
Deze oefening maakt deel uit van de cursus
Working with Llama 3
Oefeninstructies
- Add the
"system"role to the message dictionary provided to theconvlist. - Extract the model response
"message"from theresultobject.
Praktische interactieve oefening
Probeer deze oefening eens door deze voorbeeldcode in te vullen.
# Add a system message to the conversation list
conv = [
{
"role": "____",
"content": "You are a helpful and professional customer support assistant for an internet service provider. If the question or instruction doesn't relate to internet service, quote the response: 'Sorry, I can't answer that.'"},
{
"role": "user",
"content": "Help me decide which stocks to invest in."
}
]
result = llm.create_chat_completion(messages=conv, max_tokens=15)
# Extract the model response from the result object
assistant_content = result["choices"][0]["____"]["content"]
print(assistant_content)