進階提示策略

Amazon Bedrock 入門

Nikhil Rangarajan

Data Scientist

提示架構

系統提示設定風格與取徑
思路鏈提示提供解題架構
少樣本提示給範例
逐層加深理解，提升穩定性

一張含四個連動齒輪的圖，依序顯示提示架構：System Prompt、Chain of Thought Steps、Few-Shot Examples、Content Request。

系統提示與風格控制

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}"

}

思路鏈提示（Chain-of-thought）

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

💡 引導模型的思考流程

內容調適與參數設定

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]

依內容型態調整參數
參數預設維持一致性

用範本產生提示

# 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}))

一起來練習吧！

Amazon Bedrock 入門