少样本提示与会话角色

Claude 模型入门

Nikhil Rangarajan

Data Scientist

使用消息格式的会话角色

消息数组模拟多轮对话
每条消息都有角色
遵循特定回应风格

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)

少样本提示入门

少样本提示通过示例教会 Claude
用户/助理配对展示期望行为
对新输入同样有效

一位用户与一位助理

理解 zero-shot、few-shot 与 one-shot

Zero-shot：单个提示，无示例
One-shot：任务前提供 1 个示例
Few-shot：提供多个示例展示模式
更多示例通常提升一致性

少样本代码示例

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"}]

少样本的实用场景

格式一致：展示期望输出结构
语气匹配：示范特定沟通风格
复杂推理：引导多步求解
领域知识：教授专门应用

# 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"}]

少样本提示最佳实践

大多数任务使用 2-5 个示例
确保示例高质量且一致
多样化示例以展示模式，而非机械重复
用边界情况测试以验证稳健性

让我们一起练习吧！

Claude 模型入门