Shot prompting

Praca z DeepSeek w Pythonie

James Chapman

AI Curriculum Lead, DataCamp

Podawanie przykładów

Robot przegląda przykłady

Shot prompting

Czym jest shot prompting?

Shot prompting: podawanie przykładów w celu ukierunkowania odpowiedzi AI

Zero-shot: brak przykładów, tylko instrukcje
One-shot: jeden przykład ukierunkowuje odpowiedź
Few-shot: wiele przykładów zapewnia więcej kontekstu

Reprezentacja podejść zero-shot do few-shot

Dlaczego shot prompting jest ważny?

✅ Zastosowania shot promptingu:

📑 Klasyfikacja tekstu
💬 Analiza sentymentu
🔍 Ekstrakcja danych
✨ ... i wiele więcej!

Zastosowania shot promptingu

Prompting zero-shot

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

Prompting one-shot

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

Prompting few-shot

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

Czas na ćwiczenia!

Praca z DeepSeek w Pythonie