직접 시도해보려면 이 프롬프트를 개발자 Console에 복사하세요!

Content
System다음의 자연어 요청을 유효한 SQL 쿼리로 변환하세요. 다음과 같은 테이블과 컬럼이 있는 데이터베이스가 있다고 가정합니다:

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)

자연어 요청을 바탕으로 데이터를 검색하는 SQL 쿼리를 제공하세요.
User주문은 했지만 리뷰를 작성하지 않은 고객 목록과 그들이 주문에 지출한 총액을 가져오세요.

​
예시 출력

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 요청

import anthropic

client = anthropic.Anthropic(
  # defaults to os.environ.get("ANTHROPIC_API_KEY")
  api_key="my_api_key",
)
message = client.messages.create(
  model="claude-3-5-sonnet-20241022",
  max_tokens=1000,
  temperature=0,
  system="다음의 자연어 요청을 유효한 SQL 쿼리로 변환하세요. 다음과 같은 테이블과 컬럼이 있는 데이터베이스가 있다고 가정합니다: \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 \n자연어 요청을 바탕으로 데이터를 검색하는 SQL 쿼리를 제공하세요.",
  messages=[
    {
      "role": "user", 
      "content": [
        {
          "type": "text",
          "text": "주문은 했지만 리뷰를 작성하지 않은 고객 목록과 그들이 주문에 지출한 총액을 가져오세요."
        }
      ]
    }
  ]
)
print(message.content)

Was this page helpful?

출처 인용하기꿈 해석가