What is few-shot prompting? Meaning and example in Python

What is few-shot prompting?

Few-shot prompting (also called Few-shot learning prompt, N-shot prompting): Including a small number of input-output examples (usually 2 to 8) in the prompt so the model copies the pattern for a new input. It teaches format, tone and edge cases without retraining. The quality, variety and order of the examples strongly affect the result.

Few-shot prompting: an example

To tag support tickets, the prompt lists five tickets with labels such as 'refund' or 'delivery delay', then adds a sixth ticket without a label.

Few-shot prompting in Python

A short example you can run (Python 3.11). The output below is what it really prints.

examples = [("The delivery was quick", "positive"), ("Item arrived broken", "negative")]
query = "Customer care solved it in minutes"
messages = [{"role": "system", "content": "Label the sentiment: positive or negative."}]
for text, label in examples:
    messages += [{"role": "user", "content": text}, {"role": "assistant", "content": label}]
messages.append({"role": "user", "content": query})
for m in messages:
    print(f"{m['role']:9s} {m['content']}")

Output

system    Label the sentiment: positive or negative.
user      The delivery was quick
assistant positive
user      Item arrived broken
assistant negative
user      Customer care solved it in minutes

Related terms

More Prompt context engineering terms

Where you learn it

Few-shot prompting is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.