Nhắc lệnh theo "shot"

Làm việc với DeepSeek bằng Python

James Chapman

Curriculum Manager, DataCamp

Cung cấp ví dụ

Một robot đang xem ví dụ

Nhắc lệnh theo "shot"

Nhắc lệnh theo "shot" là gì?

Nhắc lệnh theo "shot": thêm ví dụ để định hướng phản hồi của AI

Zero-shot: không có ví dụ, chỉ hướng dẫn
One-shot: một ví dụ dẫn dắt phản hồi
Few-shot: nhiều ví dụ cho thêm ngữ cảnh

Minh họa từ zero đến few shots

Vì sao shot prompting quan trọng?

✅ Trường hợp dùng shot prompting:

📑 Phân loại văn bản
💬 Phân tích cảm xúc
🔍 Trích xuất dữ liệu
✨ ... và nhiều nữa!

Các trường hợp dùng shot prompting

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

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

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

Vamos praticar!

Làm việc với DeepSeek bằng Python