Shot prompting

Working with DeepSeek in Python

James Chapman

Curriculum Manager, DataCamp

Providing examples

A robot looks at examples

  • Shot prompting
Working with DeepSeek in Python

What is shot prompting?

Shot prompting: including examples to guide AI responses

$$

  • Zero-shot: no examples, just instructions
  • One-shot: one example guides the response
  • Few-shot: multiple examples provide more context

Zero to few shots represantation

Working with DeepSeek in Python

Why does shot prompting matter?

$$

✅ Use cases of shot prompting:

  • 📑 Text classification
  • 💬 Sentiment analysis
  • 🔍 Data extraction
  • ✨ ... and many more!

Use cases of shot prompting

Working with DeepSeek in Python

Zero-shot prompting

prompt = """Classify sentiment as 1-5 (bad-good) in the following statements:
1. Meal was decent, but I've had better.
2. My food was delayed, but drinks were good.
"""
...

1. 3  
2. 2
Working with DeepSeek in Python

One-shot prompting

prompt = """Classify sentiment as 1-5 (bad-good) in the following statements. Return no
explanations:
1. The service was very slow -> 1
2. Meal was decent, but I've had better. ->
3. My food was delayed, but drinks were good. ->
"""

2. Meal was decent, but I've had better. -> 3  
3. My food was delayed, but drinks were good. -> 2
Working with DeepSeek in Python

Few-shot prompting

prompt = """Classify sentiment as 1-5 (bad-good) in the following statements. Return no
explanations:
1. The service was very slow -> 1
2. The steak was awfully good! -> 5
3. It was ok, no massive complaints. -> 3
4. Meal was decent, but I've had better. ->
5. My food was delayed, but drinks were good. ->
"""

4. Meal was decent, but I've had better. -> 3  
5. My food was delayed, but drinks were good. -> 2
Working with DeepSeek in Python

Let's practice!

Working with DeepSeek in Python

Preparing Video For Download...