Few-shot prompting with Llama
You're using a Llama model to identify the sentiment of customer reviews from Google and Yelp as Positive
or Negative
. To ensure these labels are consistent for each review, you'll design a few-shot prompt containing three examples.
Here are the examples you want to provide to the model:
- I ordered from this place last night, and I'm impressed! → Positive
- My order was delayed by over an hour without any updates. Disappointing! → Negative
- The food quality is top-notch. Highly recommend! → Positive
This exercise is part of the course
Working with Llama 3
Exercise instructions
- Complete the few-shot prompt by assigning
Positive
orNegative
to the reviews provided. - Send the prompt to the model with the
"Review"
stop word so the model only responds to one review.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Complete the few-shot prompt
prompt="""Review 1: I ordered from this place last night, and I'm impressed!
Sentiment 1: ____,
Review 2: My order was delayed by over an hour without any updates. Disappointing!
Sentiment 2: ____,
Review 3: The food quality is top-notch. Highly recommend!
Sentiment 3: ____,
Review 4: Delicious food, and excellent customer service!
Sentiment 4:"""
# Send the prompt to the model with a stop word
output = llm(prompt, max_tokens=2, stop=["____"])
print(output['choices'][0]['text'])