提示語料庫
SQL 魔法師
提示語料庫
SQL 魔法師
將日常語言轉換為 SQL 查詢。
將此提示複製到我們的開發人員 Console 中，自己嘗試一下！
| 內容 | |
|---|---|
| System | 將以下自然語言請求轉換為有效的 SQL 查詢。假設存在具有以下表和列的數據庫： Customers: - customer_id (INT, PRIMARY KEY) - first_name (VARCHAR) - last_name (VARCHAR) - email (VARCHAR) - phone (VARCHAR) - address (VARCHAR) - city (VARCHAR) - state (VARCHAR) - zip_code (VARCHAR) Products: - product_id (INT, PRIMARY KEY) - product_name (VARCHAR) - description (TEXT) - category (VARCHAR) - price (DECIMAL) - stock_quantity (INT) Orders: - order_id (INT, PRIMARY KEY) - customer_id (INT, FOREIGN KEY REFERENCES Customers) - order_date (DATE) - total_amount (DECIMAL) - status (VARCHAR) Order_Items: - order_item_id (INT, PRIMARY KEY) - order_id (INT, FOREIGN KEY REFERENCES Orders) - product_id (INT, FOREIGN KEY REFERENCES Products) - quantity (INT) - price (DECIMAL) Reviews: - review_id (INT, PRIMARY KEY) - product_id (INT, FOREIGN KEY REFERENCES Products) - customer_id (INT, FOREIGN KEY REFERENCES Customers) - rating (INT) - comment (TEXT) - review_date (DATE) Employees: - employee_id (INT, PRIMARY KEY) - first_name (VARCHAR) - last_name (VARCHAR) - email (VARCHAR) - phone (VARCHAR) - hire_date (DATE) - job_title (VARCHAR) - department (VARCHAR) - salary (DECIMAL) 提供基於自然語言請求檢索數據的 SQL 查詢。 |
| User | 獲取已下訂單但未提供任何評論的客戶列表，以及他們在訂單上花費的總金額。 |
示例輸出
SELECT c.first_name, c.last_name, SUM(o.total_amount) AS total_spent
FROM Customers c
INNER JOIN Orders o ON c.customer_id = o.customer_id
LEFT JOIN Reviews r ON c.customer_id = r.customer_id
WHERE r.review_id IS NULL
GROUP BY c.customer_id, c.first_name, c.last_name;
API 請求
注意： Claude 3 Opus 即將在 Bedrock API 中推出。
import anthropic
client = anthropic.Anthropic(
# 默認為 os.environ.get("ANTHROPIC_API_KEY")
api_key="my_api_key",
)
message = client.messages.create(
model="claude-3-opus-20240229",
max_tokens=1000,
temperature=0,
system="將以下自然語言請求轉換為有效的 SQL 查詢。假設存在具有以下表和列的數據庫：\n \nCustomers: \n- customer_id (INT, PRIMARY KEY) \n- first_name (VARCHAR) \n- last_name (VARCHAR) \n- email (VARCHAR) \n- phone (VARCHAR) \n- address (VARCHAR) \n- city (VARCHAR) \n- state (VARCHAR) \n- zip_code (VARCHAR) \n \nProducts: \n- product_id (INT, PRIMARY KEY) \n- product_name (VARCHAR) \n- description (TEXT) \n- category (VARCHAR) \n- price (DECIMAL) \n- stock_quantity (INT) \n \nOrders: \n- order_id (INT, PRIMARY KEY) \n- customer_id (INT, FOREIGN KEY REFERENCES Customers) \n- order_date (DATE) \n- total_amount (DECIMAL) \n- status (VARCHAR) \n \nOrder_Items: \n- order_item_id (INT, PRIMARY KEY) \n- order_id (INT, FOREIGN KEY REFERENCES Orders) \n- product_id (INT, FOREIGN KEY REFERENCES Products) \n- quantity (INT) \n- price (DECIMAL) \n \nReviews: \n- review_id (INT, PRIMARY KEY) \n- product_id (INT, FOREIGN KEY REFERENCES Products) \n- customer_id (INT, FOREIGN KEY REFERENCES Customers) \n- rating (INT) \n- comment (TEXT) \n- review_date (DATE) \n \nEmployees: \n- employee_id (INT, PRIMARY KEY) \n- first_name (VARCHAR) \n- last_name (VARCHAR) \n- email (VARCHAR) \n- phone (VARCHAR) \n- hire_date (DATE) \n- job_title (VARCHAR) \n- department (VARCHAR) \n- salary (DECIMAL) \n \n提供基於自然語言請求檢索數據的 SQL 查詢。",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "獲取已下訂單但未提供任何評論的客戶列表，以及他們在訂單上花費的總金額。"
}
]
}
]
)
print(message.content)