NLQ 入门：第一次自然语言查数

1. 登录平台后进入"智能查询"页（/chat）
2. 点击页面自带的示例问题"查询所有订单"（或手动输入）
3. 按回车，等待链路返回
4. 查看返回的意图、SQL、结果表格

{
  "message": "查询成功",
  "intent": "data_query",
  "confidence": 0.8,
  "data_source_name": "aip_demo_warehouse",
  "sql_query": "SELECT order_id, customer_id, order_date, product_id, quantity, price, sales_amount FROM orders LIMIT 100",
  "sql_explanation": "查询 orders 表中的全部订单字段",
  "query_result": {
    "columns": ["order_id", "customer_id", "order_date", "product_id", "quantity", "price", "sales_amount"],
    "rows": [["1","1","2026-06-09","1","10","99.5","995"],["2","2","2026-07-09","2","5","199","995"],["3","1","2026-07-30","1","20","99.5","1990"],["4","3","2026-08-06","3","2","499","998"],["5","2","2026-08-09","1","15","99.5","1492.5"]]
  },
  "visualization": { "chart_type": "table", "reason": "无明确图表特征，默认表格", "confidence": 0.6, "alternatives": [], "x_axis": "order_id", "series": ["order_id","customer_id","order_date","product_id","quantity","price","sales_amount"] },
  "fix_attempts": 0,
  "dsl": { "version": "1.0", "recommended_chart": "table", "confidence": 0.6, "alternatives": [], "blocks": [{"type":"chart","chart_type":"table","title":"查询所有订单","data_mapping":{"x":"order_id","y":["order_id","customer_id","order_date","product_id","quantity","price","sales_amount"]},"options":{"pagination":true}},{"type":"summary","text":"查询共返回 5 行、7 列数据。"}] },
  "rag_channels_used": ["metadata"],
  "ontology_hit": false
}

1. 进入 /chat 智能查询
2. 输入"查询订单总金额"并回车
3. 查看返回的 SQL 与数值结果

{
  "intent": "data_query",
  "confidence": 0.8,
  "sql_query": "SELECT SUM(sales_amount) AS total_sales FROM orders",
  "sql_explanation": "对 orders 表的 sales_amount 求和，得到订单总金额",
  "query_result": { "columns": ["total_sales"], "rows": [["6470.5"]] },
  "visualization": { "chart_type": "metric_card", "reason": "single numeric value, recommend metric card", "x_axis": "total_sales", "series": ["total_sales"] }
}

1. 进入 /chat
2. 输入"查询每个客户的订单数量"并回车
3. 观察返回 SQL 中是否自动 JOIN 了 customers
4. 查看分组结果与图表推荐

{
  "intent": "data_query",
  "confidence": 0.8,
  "sql_query": "SELECT c.customer_name, COUNT(o.order_id) AS order_count FROM customers c LEFT JOIN orders o ON o.customer_id = c.customer_id GROUP BY c.customer_name",
  "sql_explanation": "按客户名分组，统计每位客户的订单数（LEFT JOIN 保留无订单客户）",
  "query_result": { "columns": ["customer_name", "order_count"], "rows": [["张三","2"],["李四","2"],["王五","1"]] },
  "visualization": { "chart_type": "bar", "reason": "contains one dimension and numeric columns, recommend bar chart", "x_axis": "customer_name", "series": ["customer_name","order_count"] }
}

1. 保持 /chat 对话窗口，不刷新页面
2. 输入"查询上海的客户的订单"（把表名与条件带全）
3. 回车，查看返回的 SQL 与结果

{
  "intent": "data_query",
  "confidence": 0.8,
  "sql_query": "SELECT o.order_id, o.sales_amount, c.customer_name, c.city FROM orders o JOIN customers c ON o.customer_id = c.customer_id WHERE c.city = '上海'",
  "sql_explanation": "关联客户表，筛选城市为上海的客户订单",
  "query_result": { "columns": ["order_id","sales_amount","customer_name","city"], "rows": [["1","995","张三","上海"],["3","1990","张三","上海"]] },
  "visualization": { "chart_type": "table", "reason": "default table view", "x_axis": "order_id", "series": ["order_id","sales_amount","customer_name","city"] }
}