Shot Prompting

Arbeiten mit DeepSeek in Python

James Chapman

AI Curriculum Lead, DataCamp

Beispiele geben

Ein Roboter betrachtet Beispiele

  • Shot Prompting
Arbeiten mit DeepSeek in Python

Was ist Shot Prompting?

Shot Prompting: Beispiele einbinden, um KI-Antworten zu steuern

$$

  • Zero-shot: keine Beispiele, nur Anweisungen
  • One-shot: ein Beispiel leitet die Antwort
  • Few-shot: mehrere Beispiele geben mehr Kontext

Darstellung von Zero bis Few Shots

Arbeiten mit DeepSeek in Python

Warum ist Shot Prompting wichtig?

$$

✅ Anwendungsfälle für Shot Prompting:

  • 📑 Textklassifikation
  • 💬 Sentimentanalyse
  • 🔍 Datenextraktion
  • ✨ ... und viele mehr!

Anwendungsfälle von Shot Prompting

Arbeiten mit 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
Arbeiten mit 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
Arbeiten mit 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
Arbeiten mit DeepSeek in Python

Lass uns üben!

Arbeiten mit DeepSeek in Python

Preparing Video For Download...