One-shot chain-of-thought prompts
When you need to sum the even numbers within a given set, you first have to identify these even numbers and then sum them. You can teach this to a language model via one or more examples, and it will follow this strategy to operate on new sets.
Your goal in this exercise is to teach the model how to apply this procedure on the following set: {9, 10, 13, 4, 2}, and then ask the model to perform it on a new set: {15, 13, 82, 7, 14}. This is how you perform chain-of-thought prompting through one-shot prompting.
The OpenAI package and the get_response() function have been pre-loaded for you.
This exercise is part of the course
Prompt Engineering with the OpenAI API
Exercise instructions
- Define an
examplethat teaches the model how to sum the even numbers on the set{9, 10, 13, 4, 2}. - Define a
question, similar to the one in theexample, that asks the model to reason on a new set{15, 13, 82, 7, 14}. - Create the final prompt.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
client = OpenAI(api_key="")
# Define the example
example = """Q: Sum the even numbers in the following set: ____.
A: Even numbers: ____. Adding them: ____+____+____=____"""
# Define the question
question = """Q: ____
A:"""
# Create the final prompt
prompt = ____
response = get_response(prompt)
print(response)