Multi-turn conversations
Let's extend the travel chatbot to allow users to respond to the model's initial recommendation. You'll again use the Conversation
class, but this time, you'll make repeated calls to the model to see how the model handles previous information.
As a reminder, here are the methods from the Conversation
class:
__init__(self, llm: Llama, system_prompt='', history=[])
create_completion(self, user_prompt='')
This exercise is part of the course
Working with Llama 3
Exercise instructions
- Ask for an initial travel recommendation, and provide a follow-up request after the first model response.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
chatbot = Conversation(llm, system_prompt="You are a travel expert that recommends a travel destination based on a prompt. Return the location name only as 'City, Country'.")
# Ask for the initial travel recommendation
first_recommendation = chatbot.____("Recommend a Spanish-speaking city.")
print(first_recommendation)
# Add an additional request to update the recommendation
second_recommendation = chatbot.____("A different city in the same country")
print(second_recommendation)