Controlling output structure
One way to control the output structure provided by a language model is to give it a sample question-answer in the prompt. The model will learn from it and follow it when generating responses for similar questions. This exercise aims to let you build a one-shot prompt that extracts odd numbers from a given set of numbers and displays them as a set of numbers between brackets, separated by commas as shown in the instructions.
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
- Create a one-shot
prompt
that provides an example showing how to extract the odd numbers from the set{1, 3, 7, 12, 19}
, and seeks an answer for the set{3, 5, 11, 12, 16}
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
client = OpenAI(api_key="")
# Create a one-shot prompt
prompt = """____"""
response = get_response(prompt)
print(response)