少量範例提示與對話角色

Claude 模型入門

Nikhil Rangarajan

Data Scientist

以訊息格式定義對話角色

Messages 陣列模擬多輪對話
每則訊息都有角色
可遵循特定回應風格

messages = [
    {"role": "user", 
 "content": "What's the weather like?"},
    {"role": "assistant", 
 "content": "I don't have access to 
     current weather data. You might 
     want to check a weather app."},
    {"role": "user", 
 "content": "How's traffic downtown?"}]

response = client.messages.create(
    model="claude-sonnet-4-6",
    messages=messages)

少量範例提示入門

少量範例提示用範例教會 Claude
user/assistant 成對訊息示範預期行為
對新輸入同樣有效

一位使用者與一位助理

理解 zero-shot、few-shot、one-shot 的差異

Zero-shot：無範例的單一提示
One-shot：任務前提供 1 個範例
Few-shot：提供多個範例展示模式
更多範例通常可提升一致性

Few-shot 程式碼範例

messages = [{"role": "user", "content": "Translate to French: Hello"}] # Zero-shot

# One-shot  
messages = [{"role": "user", "content": "Translate to French: Good morning"},
    {"role": "assistant", "content": "Bonjour"},
    {"role": "user", "content": "Translate to French: Hello"}]

# Few-shot (multiple examples)
messages = [{"role": "user", "content": "Translate to French: Good morning"},
    {"role": "assistant", "content": "Bonjour"},
    {"role": "user", "content": "Translate to French: Thank you"},
    {"role": "assistant", "content": "Merci"},
    {"role": "user", "content": "Translate to French: Hello"}]

少量範例的實務應用

格式一致：示範期望輸出結構
語氣匹配：呈現特定溝通風格
複雜推理：引導多步解題
領域知識：教導專業應用

# Teaching email response format
messages = [{"role": "user", "content": "Customer complaint: Late delivery"},
    {"role": "assistant", "content": "Dear Customer,\n\nWe apologize for the delay. 
     We'll track your order and update you within 24 hours.
     \n\nBest regards,\nSupport Team"},
    {"role": "user", "content": "Customer complaint: Wrong item received"}]

少量範例提示的最佳做法

多數任務用 2–5 個範例即可
範例需高品質且一致
變化範例以呈現模式而非重複
以邊界情況測試以驗證穩健性

一起來練習吧！

Claude 模型入門