高级提示策略

Amazon Bedrock 入门

Nikhil Rangarajan

Data Scientist

提示架构

系统提示设定风格与方法
链式思维提示提供解题框架
少样本提示提供示例
逐层构建理解，提升可靠性

一个包含四个相连齿轮的图表，展示提示架构顺序：系统提示、链式思维步骤、少样本示例和内容请求。

系统提示与风格控制

prompt_template = {
    "system_prompt": f"""System: Write in a professional but approachable tone.""",

    "content_type": "blog_post",

    "examples": [
        {
            "title": "Cloud Migration Basics",
            "content": "Moving to the cloud doesn't have to be complex..."
        }
    ],

    "task": f"Write a blog post about {topic}"

}

链式思维提示

def generate_message_content(text_data):
    steps = [
        "1. Understand the target audience",
        "2. Outline key points",
        "3. Draft a promotional email"
    ]

    text_data["text"] += f"\nSteps:{' '.join(steps)}"

    return text_data

💡 引导模型的思维过程

内容适配与参数

parameters = {

    "blog_post": {"temperature": 0.7, "top_p": 0.9},
    "social_media": {"temperature": 0.8, "top_p": 0.95},

    "technical": {"temperature": 0.4, "top_p": 0.8}

}

content_type = "blog_post"
prompt_data["parameters"] = parameters[content_type]

按内容类型调整参数
预设参数保证一致性

使用模板生成提示

# Write the prompt
topic = "Cloud Security"
content_type = "blog_post"
prompt = f"Write a {topic} blog post. Use this example: {prompt_template["examples"][0]}"


# Define the parameters
temperature = parameters[content_type]["temperature"]
top_p = parameters[content_type]["top_p"]


# Call the model
response = bedrock.invoke_model(modelId=model_id, body=json.dumps({"messages": 
           [{"role": "user","content": [{"type": "text", "text": prompt}]}],
           "temperature": temperature, "top_p": top_p}))

Passons à la pratique !

Amazon Bedrock 入门