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;

import anthropic

client = anthropic.Anthropic(
  # 默认为 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="将以下自然语言请求转换为有效的 SQL 查询。假设存在具有以下表和列的数据库：\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根据自然语言请求提供可以检索数据的 SQL 查询。",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "获取已下订单但未提供任何评论的客户列表，以及他们在订单上花费的总金额。"
        }
      ]
    }
  ]
)
print(message.content)