* 1.refactor the retrieval module. 2.refactor the http service module. 3.upgrade text2sql output format the parse for absolute time related expression in query.
* fix bug.
* upgrade the config module, now support config llm suppoted by langchain.
* fix conflicts.
* update text2sql config reload to be compitable with new config format.
* modify default config.
* 1.add self-consistency feature for text2sql. 2.upgrade llm api call from sync to async. 3.refactor text2sql module. 4. refactor semantical retriever modules.
* merege with upstream master
* add general retrieve service.
* add api service for sql_agent for crud opereations of few-shots examples.
* modify requirements
* add auto-cot feature
* 1. output log to a fixed log file. 2.allow few-shots examples tied to data model, and add strategy that extend examples when retrieved examples tied to a data model is not enough. 3. fix misformat in s2ql args.
* add prior_ext to output.
---------
Co-authored-by: shaoweigong <shaoweigong@tencent.com>
"sql":"""select MONTH(数据日期), sum(访问次数) from 内容库产品 where datediff('year', 数据日期, '2023-09-04') <= 0.5 group by MONTH(数据日期) order by sum(访问次数) desc limit 1"""
"sql":"""select MONTH(数据日期), sum(运营播放量) from (select 数据日期, 运营播放量 from 歌曲库 where 发布日期 >= '2022-07-01' and 发布日期 <= '2023-07-01' order by 播放量 desc limit 100) t where datediff('year', 数据日期, '2023-09-10') <= 1 group by MONTH(数据日期)"""
"sql":"""select MONTH(数据日期), sum(运营播放量) from (select 数据日期, 运营播放量 from 歌曲库 where 发布日期 >= '2022-07-01' and 发布日期 <= '2023-07-01' order by 播放量 desc limit 100) t where datediff('year', 数据日期, '2023-09-10') <= 1 group by MONTH(数据日期) having sum(运营播放量) > 2000"""
"sql":"""select 国家中文名, sum(销量) from 营销月模型 where 机型类别 = '智能机' and 数据日期 >= '2023-01-01' and 数据日期 <= '2023-11-01' group by 国家中文名 order by sum(销量) desc limit 1"""
"sql":"select 用户名, 访问次数 from 内容库产品 where 用户名 in ('jackjchen', 'robinlee')",
"sql":"select 用户名, 访问次数 from 内容库产品 where 用户名 in ('jackjchen', 'robinlee')",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"比较jackjchen和robinlee在内容库的访问次数 (补充信息:’'jackjchen'‘是一个’用户名‘，’ 'robinlee'‘是一个’用户名‘。当前的日期是2020-12-01) (备注: )\", we are asked:\n\"’用户名‘，\" so we need column = [用户名]\n\"的访问次数 \" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [jackjchen,robinlee]. So the Schema_links are:\nSchema_links: [用户名,访问次数,jackjchen,robinlee]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"比较jackjchen和robinlee在内容库的访问次数 (补充信息:’'jackjchen'‘是一个’用户名‘，’ 'robinlee'‘是一个’用户名‘。当前的日期是2020-12-01) (备注: )\", we are asked:\n\"的访问次数 \" so we need column = [访问次数]\n\"’用户名‘，\" so we need column = [用户名]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [jackjchen,robinlee]. So the Schema_links are:\nSchema_links: [访问次数,用户名,jackjchen,robinlee]",
"sql":"select 部门, 数据日期, 访问人数 from 内容库产品 where datediff('month', 数据日期, '2022-11-06') <= 12 ",
"sql":"select 部门, 数据日期, 访问人数 from 内容库产品 where datediff('month', 数据日期, '2022-11-06') <= 12 ",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近12个月访问人数 按部门 (补充信息:。当前的日期是2022-11-06) (备注: )\", we are asked:\n\" 按部门 (\" so we need column = [部门]\n\"访问人数 按\" so we need column = [访问人数]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [12,month]. So the Schema_links are:\nSchema_links: [部门,访问人数,数据日期,12,month]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近12个月访问人数 按部门 (补充信息:。当前的日期是2022-11-06) (备注: )\", we are asked:\n\"当前的日期是\" so we need column = [数据日期]\n\" 按部门 (\" so we need column = [部门]\n\"访问人数 按\" so we need column = [访问人数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [12,month]. So the Schema_links are:\nSchema_links: [数据日期,部门,访问人数,12,month]",
"sql":"select 部门, 访问时长 from 内容库产品 where 部门 in ('美术部', '技术研发部')",
"sql":"select 部门, 访问时长 from 内容库产品 where 部门 in ('美术部', '技术研发部')",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库美术部、技术研发部的访问时长 (补充信息:’'美术部'‘是一个’部门‘，’ '技术研发部'‘是一个’部门‘。当前的日期是2023-04-21) (备注: )\", we are asked:\n\"部门‘，’ \" so we need column = [部门]\n\"的访问时长 \" so we need column = [访问时长]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [美术部,技术研发部]. So the Schema_links are:\nSchema_links: [部门,访问时长,美术部,技术研发部]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库美术部、技术研发部的访问时长 (补充信息:’'美术部'‘是一个’部门‘，’ '技术研发部'‘是一个’部门‘。当前的日期是2023-04-21) (备注: )\", we are asked:\n\"部门‘，’ \" so we need column = [部门]\n\"的访问时长 \" so we need column = [访问时长]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [美术部,技术研发部]. So the Schema_links are:\nSchema_links: [部门,访问时长,美术部,技术研发部]",
"sql":"select 严选版权归属系, 结算播放份额 from 严选 where 严选版权归属系 = '海田飞系' and datediff('day', 数据日期, '2023-08-21') <= 3 ",
"sql":"select 严选版权归属系, 结算播放份额 from 严选 where 严选版权归属系 = '海田飞系' and datediff('day', 数据日期, '2023-08-21') <= 3 ",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"近3天海田飞系MPPM结算播放份额 (补充信息:’'海田飞系'‘是一个’严选版权归属系‘。当前的日期是2023-08-21) (备注: )\", we are asked:\n\"结算播放份额 \" so we need column = [结算播放份额]\n\"严选版权归属系\" so we need column = [严选版权归属系]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [海田飞系,3,day]. So the Schema_links are:\nSchema_links: [结算播放份额,严选版权归属系,数据日期,海田飞系,3,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"近3天海田飞系MPPM结算播放份额 (补充信息:’'海田飞系'‘是一个’严选版权归属系‘。当前的日期是2023-08-21) (备注: )\", we are asked:\n\"结算播放份额 \" so we need column = [结算播放份额]\n\"当前的日期是\" so we need column = [数据日期]\n\"严选版权归属系\" so we need column = [严选版权归属系]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [海田飞系,3,day]. So the Schema_links are:\nSchema_links: [结算播放份额,数据日期,严选版权归属系,海田飞系,3,day]",
"sql":"select 歌曲版本, 语种, 结算播放量 from 歌曲库 where 歌曲版本 = '翻唱版' and 语种 = '纯音乐' and datediff('day', 数据日期, '2023-05-22') <= 7 ",
"sql":"select 歌曲版本, 语种, 结算播放量 from 歌曲库 where 歌曲版本 = '翻唱版' and 语种 = '纯音乐' and datediff('day', 数据日期, '2023-05-22') <= 7 ",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"对比近7天翻唱版和纯音乐的歌曲播放量 (补充信息:’'纯音乐'‘是一个’语种‘，’ '翻唱版'‘是一个’歌曲版本‘。当前的日期是2023-05-22) (备注: )\", we are asked:\n\"曲播放量 (\" so we need column = [结算播放量]\n\"’歌曲版本‘\" so we need column = [歌曲版本]\n\"语种‘，’ \" so we need column = [语种]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [7,翻唱版,纯音乐,day]. So the Schema_links are:\nSchema_links: [结算播放量,歌曲版本,语种,数据日期,7,翻唱版,纯音乐,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"对比近7天翻唱版和纯音乐的歌曲播放量 (补充信息:’'纯音乐'‘是一个’语种‘，’ '翻唱版'‘是一个’歌曲版本‘。当前的日期是2023-05-22) (备注: )\", we are asked:\n\"当前的日期是\" so we need column = [数据日期]\n\"’歌曲版本‘\" so we need column = [歌曲版本]\n\"语种‘，’ \" so we need column = [语种]\n\"曲播放量 (\" so we need column = [结算播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [7,翻唱版,纯音乐,day]. So the Schema_links are:\nSchema_links: [数据日期,歌曲版本,语种,结算播放量,7,翻唱版,纯音乐,day]",
"sql":"select 歌手名, 粉丝数 from 艺人库 where 歌手名 in ('陈拙悬', '孟梅琦', '赖媚韵')",
"sql":"select 歌手名, 粉丝数 from 艺人库 where 歌手名 in ('陈拙悬', '孟梅琦', '赖媚韵')",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"对比一下陈拙悬、孟梅琦、赖媚韵的粉丝数 (补充信息:’'1527896'‘是一个’MPPM歌手ID‘，’ '1565463'‘是一个’MPPM歌手ID‘，’ '2141459'‘是一个’MPPM歌手ID‘。当前的日期是2023-05-31) (备注: )\", we are asked:\n\"歌手ID‘，\" so we need column = [歌手名]\n\"的粉丝数 (\" so we need column = [粉丝数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [陈拙悬,孟梅琦,赖媚韵]. So the Schema_links are:\nSchema_links: [歌手名,粉丝数,陈拙悬,孟梅琦,赖媚韵]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"对比一下陈拙悬、孟梅琦、赖媚韵的粉丝数 (补充信息:’'1527896'‘是一个’MPPM歌手ID‘，’ '1565463'‘是一个’MPPM歌手ID‘，’ '2141459'‘是一个’MPPM歌手ID‘。当前的日期是2023-05-31) (备注: )\", we are asked:\n\"歌手ID‘，\" so we need column = [歌手名]\n\"的粉丝数 (\" so we need column = [粉丝数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [陈拙悬,孟梅琦,赖媚韵]. So the Schema_links are:\nSchema_links: [歌手名,粉丝数,陈拙悬,孟梅琦,赖媚韵]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"播放量大于1万的歌曲有多少 (补充信息:。当前的日期是2023-07-31) (备注: )\", we are asked:\n\"歌曲有多少 \" so we need column = [歌曲名]\n\"播放量大于1\" so we need column = [结算播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,10000]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"播放量大于1万的歌曲有多少 (补充信息:。当前的日期是2023-07-31) (备注: )\", we are asked:\n\"歌曲有多少 \" so we need column = [歌曲名]\n\"播放量大于1\" so we need column = [结算播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,10000]",
"sql":"select 用户名 from 内容库产品 where 部门 = '美术部' and 访问时长 < 1",
"sql":"select 用户名 from 内容库产品 where 部门 = '美术部' and 访问时长 < 1",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库访问时长小于1小时，且来自美术部的用户是哪些 (补充信息:’'美术部'‘是一个’部门‘。当前的日期是2023-07-31) (备注: )\", we are asked:\n\"术部的用户是\" so we need column = [用户名]\n\"一个’部门‘\" so we need column = [部门]\n\"访问时长小于\" so we need column = [访问时长]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [美术部,1]. So the Schema_links are:\nSchema_links: [用户名,部门,访问时长,美术部,1]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库访问时长小于1小时，且来自美术部的用户是哪些 (补充信息:’'美术部'‘是一个’部门‘。当前的日期是2023-07-31) (备注: )\", we are asked:\n\"一个’部门‘\" so we need column = [部门]\n\"访问时长小于\" so we need column = [访问时长]\n\"术部的用户是\" so we need column = [用户名]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [美术部,1]. So the Schema_links are:\nSchema_links: [部门,访问时长,用户名,美术部,1]",
"sql":"select 用户名 from 内容库产品 order by 访问次数 desc limit 1",
"sql":"select 用户名 from 内容库产品 order by 访问次数 desc limit 1",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库pv最高的用户有哪些 (补充信息:。当前的日期是2023-08-31) (备注: )\", we are asked:\n\"用户有哪些 (\" so we need column = [用户名]\n\"最高的用户有\" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1]. So the Schema_links are:\nSchema_links: [用户名,访问次数,1]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库pv最高的用户有哪些 (补充信息:。当前的日期是2023-08-31) (备注: )\", we are asked:\n\"最高的用户有\" so we need column = [访问次数]\n\"用户有哪些 (\" so we need column = [用户名]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1]. So the Schema_links are:\nSchema_links: [访问次数,用户名,1]",
"sql":"select avg(结算播放量) from 艺人库 where 歌手名 = '袁亚伟' and datediff('day', 数据日期, '2023-08-31') <= 90 ",
"sql":"select avg(结算播放量) from 艺人库 where 歌手名 = '袁亚伟' and datediff('day', 数据日期, '2023-08-31') <= 90 ",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"近90天袁亚伟播放量平均值是多少 (补充信息:’'152789226'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-31) (备注: )\", we are asked:\n\"播放量平均值\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [袁亚伟,90,day]. So the Schema_links are:\nSchema_links: [结算播放量,歌手名,数据日期,袁亚伟,90,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"近90天袁亚伟播放量平均值是多少 (补充信息:’'152789226'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-31) (备注: )\", we are asked:\n\"歌手ID‘。\" so we need column = [歌手名]\n\"当前的日期是\" so we need column = [数据日期]\n\"播放量平均值\" so we need column = [结算播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [袁亚伟,90,day]. So the Schema_links are:\nSchema_links: [歌手名,数据日期,结算播放量,袁亚伟,90,day]",
"sql":"select sum(结算播放量) from 艺人库 where 歌手名 = '周倩倩' and datediff('day', 数据日期, '2023-08-31') <= 7 ",
"sql":"select sum(结算播放量) from 艺人库 where 歌手名 = '周倩倩' and datediff('day', 数据日期, '2023-08-31') <= 7 ",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"周倩倩近7天结算播放量总和是多少 (补充信息:’'199509'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-31) (备注: )\", we are asked:\n\"结算播放量总\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [周倩倩,7,day]. So the Schema_links are:\nSchema_links: [结算播放量,歌手名,数据日期,周倩倩,7,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"周倩倩近7天结算播放量总和是多少 (补充信息:’'199509'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-31) (备注: )\", we are asked:\n\"歌手ID‘。\" so we need column = [歌手名]\n\"当前的日期是\" so we need column = [数据日期]\n\"结算播放量总\" so we need column = [结算播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [周倩倩,7,day]. So the Schema_links are:\nSchema_links: [歌手名,数据日期,结算播放量,周倩倩,7,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库访问次数大于1k的部门是哪些 (补充信息:。当前的日期是2023-09-14) (备注: )\", we are asked:\n\"访问次数大于\" so we need column = [访问次数]\n\"部门是哪些 \" so we need column = [部门]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1000]. So the Schema_links are:\nSchema_links: [访问次数,部门,1000]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库访问次数大于1k的部门是哪些 (补充信息:。当前的日期是2023-09-14) (备注: )\", we are asked:\n\"部门是哪些 \" so we need column = [部门]\n\"访问次数大于\" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1000]. So the Schema_links are:\nSchema_links: [部门,访问次数,1000]",
"sql":"select 歌曲名 from 歌曲库 where 结算播放量 > 20000 and 歌手名 = '陈亿训' and 歌曲名 = '孤勇者'",
"sql":"select 歌曲名 from 歌曲库 where 结算播放量 > 20000 and 歌手名 = '陈亿训' and 歌曲名 = '孤勇者'",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"陈亿训唱的所有的播放量大于20k的孤勇者有哪些 (补充信息:’'199509'‘是一个’MPPM歌手ID‘，’ '1527123'‘是一个’MPPM歌曲ID‘。当前的日期是2023-09-18) (备注: )\", we are asked:\n\"歌曲ID‘。\" so we need column = [歌曲名]\n\"的所有的播放量\" so we need column = [结算播放量]\n\"歌手ID‘，\" so we need column = [歌手名]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [孤勇者,20000,陈亿训]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,孤勇者,20000,陈亿训]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"陈亿训唱的所有的播放量大于20k的孤勇者有哪些 (补充信息:’'199509'‘是一个’MPPM歌手ID‘，’ '1527123'‘是一个’MPPM歌曲ID‘。当前的日期是2023-09-18) (备注: )\", we are asked:\n\"歌曲ID‘。\" so we need column = [歌曲名]\n\"的所有的播放量\" so we need column = [结算播放量]\n\"歌手ID‘，\" so we need column = [歌手名]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [孤勇者,20000,陈亿训]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,孤勇者,20000,陈亿训]",
"sql":"select 歌曲名 from 歌曲库 where datediff('year', 发布时间, '2023-09-18') <= 1 and 歌手名 = '周洁轮'",
"sql":"select 歌曲名 from 歌曲库 where datediff('year', 发布时间, '2023-09-18') <= 1 and 歌手名 = '周洁轮'",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"周洁轮去年发布的歌曲有哪些 (补充信息:’'23109'‘是一个’MPPM歌手ID‘。当前的日期是2023-09-18) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"发布的歌曲有\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,周洁轮,year]. So the Schema_links are:\nSchema_links: [歌曲名,歌手名,发布时间,1,周洁轮,year]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"周洁轮去年发布的歌曲有哪些 (补充信息:’'23109'‘是一个’MPPM歌手ID‘。当前的日期是2023-09-18) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"发布的歌曲有\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,周洁轮,year]. So the Schema_links are:\nSchema_links: [歌曲名,歌手名,发布时间,1,周洁轮,year]",
"sql":"select 歌手名 from 艺人库 where datediff('year', 签约日期, '2023-09-11') <= 0.5 order by 结算播放量 desc limit 10",
"sql":"select 歌手名 from 艺人库 where datediff('year', 签约日期, '2023-09-11') <= 0.5 order by 结算播放量 desc limit 10",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"我想要近半年签约的播放量前十的歌手有哪些 (补充信息:。当前的日期是2023-09-11) (备注: )\", we are asked:\n\"歌手有哪些 \" so we need column = [歌手名]\n\"签约的播放量\" so we need column = [结算播放量]\n\"签约的播放量\" so we need column = [签约日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10,0.5,year]. So the Schema_links are:\nSchema_links: [歌手名,结算播放量,签约日期,10,0.5,year]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"我想要近半年签约的播放量前十的歌手有哪些 (补充信息:。当前的日期是2023-09-11) (备注: )\", we are asked:\n\"签约的播放量\" so we need column = [签约日期]\n\"歌手有哪些 \" so we need column = [歌手名]\n\"签约的播放量\" so we need column = [结算播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10,0.5,year]. So the Schema_links are:\nSchema_links: [签约日期,歌手名,结算播放量,10,0.5,year]",
"sql":"select 歌曲名 from 歌曲库 where datediff('year', 发行日期, '2023-08-12') <= 1 and datediff('day', 数据日期, '2023-08-12') <= 7 and 结算播放量 > 10000000",
"sql":"select 歌曲名 from 歌曲库 where datediff('year', 发行日期, '2023-08-12') <= 1 and datediff('day', 数据日期, '2023-08-12') <= 7 and 结算播放量 > 10000000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"最近一年发行的歌曲中，有哪些在近7天播放超过一千万的 (补充信息:。当前的日期是2023-08-12) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"天播放超过一\" so we need column = [结算播放量]\n\"最近一年发行\" so we need column = [发行日期]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000000,1,7,year,day]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,发行日期,数据日期,10000000,1,7,year,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"最近一年发行的歌曲中，有哪些在近7天播放超过一千万的 (补充信息:。当前的日期是2023-08-12) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"当前的日期是\" so we need column = [数据日期]\n\"天播放超过一\" so we need column = [结算播放量]\n\"最近一年发行\" so we need column = [发行日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000000,1,7,year,day]. So the Schema_links are:\nSchema_links: [歌曲名,数据日期,结算播放量,发行日期,10000000,1,7,year,day]",
"sql":"select 歌曲名 from 歌曲库 where datediff('year', 发行日期, '2023-08-12') <= 0 and datediff('day', 数据日期, '2023-08-12') <= 7 and 结算播放量 > 10000000",
"sql":"select 歌曲名 from 歌曲库 where datediff('year', 发行日期, '2023-08-12') <= 0 and datediff('day', 数据日期, '2023-08-12') <= 7 and 结算播放量 > 10000000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"今年以来发行的歌曲中，有哪些在近7天播放超过一千万的 (补充信息:。当前的日期是2023-08-12) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"天播放超过一\" so we need column = [结算播放量]\n\"年以来发行的\" so we need column = [发行日期]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000000,0,7,year,day]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,发行日期,数据日期,10000000,0,7,year,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"今年以来发行的歌曲中，有哪些在近7天播放超过一千万的 (补充信息:。当前的日期是2023-08-12) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"当前的日期是\" so we need column = [数据日期]\n\"天播放超过一\" so we need column = [结算播放量]\n\"年以来发行的\" so we need column = [发行日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000000,0,7,year,day]. So the Schema_links are:\nSchema_links: [歌曲名,数据日期,结算播放量,发行日期,10000000,0,7,year,day]",
"sql":"select 歌曲名 from 歌曲库 where 发行日期 >= '2023-01-01' and datediff('day', 数据日期, '2023-08-12') <= 7 and 结算播放量 > 10000000",
"sql":"select 歌曲名 from 歌曲库 where 发行日期 >= '2023-01-01' and datediff('day', 数据日期, '2023-08-12') <= 7 and 结算播放量 > 10000000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2023年以来发行的歌曲中，有哪些在近7天播放超过一千万的 (补充信息:’'514129144'‘是一个’MPPM歌曲ID‘。当前的日期是2023-08-12) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"天播放超过一\" so we need column = [结算播放量]\n\"年以来发行的\" so we need column = [发行日期]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000000,2023-01-01,7,day]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,发行日期,数据日期,10000000,2023-01-01,7,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2023年以来发行的歌曲中，有哪些在近7天播放超过一千万的 (补充信息:’'514129144'‘是一个’MPPM歌曲ID‘。当前的日期是2023-08-12) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"当前的日期是\" so we need column = [数据日期]\n\"天播放超过一\" so we need column = [结算播放量]\n\"年以来发行的\" so we need column = [发行日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10000000,2023-01-01,7,day]. So the Schema_links are:\nSchema_links: [歌曲名,数据日期,结算播放量,发行日期,10000000,2023-01-01,7,day]",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '2023-06-01' and 歌手名 = '周洁轮'",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '2023-06-01' and 歌手名 = '周洁轮'",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"周洁轮2023年6月之后发布的歌曲有哪些 (补充信息:’'23109'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-01) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"月之后发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [2023-06-01,周洁轮]. So the Schema_links are:\nSchema_links: [歌曲名,歌手名,发布时间,2023-06-01,周洁轮]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"周洁轮2023年6月之后发布的歌曲有哪些 (补充信息:’'23109'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-01) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"月之后发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [2023-06-01,周洁轮]. So the Schema_links are:\nSchema_links: [歌曲名,歌手名,发布时间,2023-06-01,周洁轮]",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '2023-01-05' and 歌手名 = '邓梓琦' and 结算播放量 > 5000000",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '2023-01-05' and 歌手名 = '邓梓琦' and 结算播放量 > 5000000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"邓梓琦在2023年1月5日之后发布的歌曲中，有哪些播放量大于500W的？ (补充信息:’'2312311'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-01) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"中，有哪些播放量\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"日之后发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [5000000,2023-01-05,邓梓琦]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,发布时间,5000000,2023-01-05,邓梓琦]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"邓梓琦在2023年1月5日之后发布的歌曲中，有哪些播放量大于500W的？ (补充信息:’'2312311'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-01) (备注: )\", we are asked:\n\"的歌曲中，有\" so we need column = [歌曲名]\n\"中，有哪些播放量\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"日之后发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [5000000,2023-01-05,邓梓琦]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,发布时间,5000000,2023-01-05,邓梓琦]",
"sql":"select 歌曲名 from 歌曲库 where 数据日期 >= '2023-06-01' and 歌手名 = '张亮英' and 结算播放量 > 2000000",
"sql":"select 歌曲名 from 歌曲库 where 数据日期 >= '2023-06-01' and 歌手名 = '张亮英' and 结算播放量 > 2000000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2023年6月以后，张亮英播放量大于200万的歌曲有哪些？ (补充信息:’'45453'‘是一个’MPPM歌手ID‘。当前的日期是2023-09-17) (备注: )\", we are asked:\n\"的歌曲有哪些？ (\" so we need column = [歌曲名]\n\"后，张亮英播放量大\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [2000000,2023-06-01,张亮英]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,数据日期,2000000,2023-06-01,张亮英]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2023年6月以后，张亮英播放量大于200万的歌曲有哪些？ (补充信息:’'45453'‘是一个’MPPM歌手ID‘。当前的日期是2023-09-17) (备注: )\", we are asked:\n\"的歌曲有哪些？ (\" so we need column = [歌曲名]\n\"当前的日期是\" so we need column = [数据日期]\n\"后，张亮英播放量大\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [2000000,2023-06-01,张亮英]. So the Schema_links are:\nSchema_links: [歌曲名,数据日期,结算播放量,歌手名,2000000,2023-06-01,张亮英]",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '2021-06-01' and 歌手名 = '李雨纯' and 结算播放量 > 200000",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '2021-06-01' and 歌手名 = '李雨纯' and 结算播放量 > 200000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2021年6月以后发布的李雨纯的播放量大于20万的歌曲有哪些 (补充信息:’'23109'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-16) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"的播放量大于\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"月以后发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [200000,2021-06-01,李雨纯]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,发布时间,200000,2021-06-01,李雨纯]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2021年6月以后发布的李雨纯的播放量大于20万的歌曲有哪些 (补充信息:’'23109'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-16) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"的播放量大于\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"月以后发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [200000,2021-06-01,李雨纯]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,发布时间,200000,2021-06-01,李雨纯]",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '1992-04-02' and 发布时间 <= '2020-05-02' and 歌手名 = '刘锝桦' and 结算播放量 > 200000",
"sql":"select 歌曲名 from 歌曲库 where 发布时间 >= '1992-04-02' and 发布时间 <= '2020-05-02' and 歌手名 = '刘锝桦' and 结算播放量 > 200000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"刘锝桦在1992年4月2日到2020年5月2日之间发布的播放量大于20万的歌曲有哪些 (补充信息:’'4234234'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-16) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"发布的播放量\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"日之间发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [200000,刘锝桦,1992-04-02,2020-05-02]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,发布时间,200000,刘锝桦,1992-04-02,2020-05-02]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"刘锝桦在1992年4月2日到2020年5月2日之间发布的播放量大于20万的歌曲有哪些 (补充信息:’'4234234'‘是一个’MPPM歌手ID‘。当前的日期是2023-08-16) (备注: )\", we are asked:\n\"歌曲有哪些 \" so we need column = [歌曲名]\n\"发布的播放量\" so we need column = [结算播放量]\n\"歌手ID‘。\" so we need column = [歌手名]\n\"日之间发布的\" so we need column = [发布时间]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [200000,刘锝桦,1992-04-02,2020-05-02]. So the Schema_links are:\nSchema_links: [歌曲名,结算播放量,歌手名,发布时间,200000,刘锝桦,1992-04-02,2020-05-02]",
"sql":"select avg(访问次数) from 内容库产品 where datediff('day', 数据日期, '2023-09-04') <= 30 ",
"sql":"select avg(访问次数) from 内容库产品 where datediff('day', 数据日期, '2023-09-04') <= 30 ",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近30天访问次数的平均数 (补充信息:。当前的日期是2023-09-04) (备注: )\", we are asked:\n\"访问次数的平均数\" so we need column = [访问次数]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [30,day]. So the Schema_links are:\nSchema_links: [访问次数,数据日期,30,day]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近30天访问次数的平均数 (补充信息:。当前的日期是2023-09-04) (备注: )\", we are asked:\n\"当前的日期是\" so we need column = [数据日期]\n\"访问次数的平均数\" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [30,day]. So the Schema_links are:\nSchema_links: [数据日期,访问次数,30,day]",
"sql":"select MONTH(数据日期), sum(访问次数) from 内容库产品 where datediff('year', 数据日期, '2023-09-04') <= 0.5 group by MONTH(数据日期) order by sum(访问次数) desc limit 1",
"sql":"select MONTH(数据日期), sum(访问次数) from 内容库产品 where datediff('year', 数据日期, '2023-09-04') <= 0.5 group by MONTH(数据日期) order by sum(访问次数) desc limit 1",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近半年哪个月的访问次数汇总最高 (补充信息:。当前的日期是2023-09-04) (备注: )\", we are asked:\n\"的访问次数汇总\" so we need column = [访问次数]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,0.5,year]. So the Schema_links are:\nSchema_links: [访问次数,数据日期,1,0.5,year]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近半年哪个月的访问次数汇总最高 (补充信息:。当前的日期是2023-09-04) (备注: )\", we are asked:\n\"当前的日期是\" so we need column = [数据日期]\n\"的访问次数汇总\" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,0.5,year]. So the Schema_links are:\nSchema_links: [数据日期,访问次数,1,0.5,year]",
"sql":"select MONTH(数据日期), avg(访问次数) from 内容库产品 where datediff('year', 数据日期, '2023-09-04') <= 0.5 group by MONTH(数据日期)",
"sql":"select MONTH(数据日期), avg(访问次数) from 内容库产品 where datediff('year', 数据日期, '2023-09-04') <= 0.5 group by MONTH(数据日期)",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近半年每个月的平均访问次数 (补充信息:。当前的日期是2023-09-04) (备注: )\", we are asked:\n\"访问次数 (\" so we need column = [访问次数]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [0.5,year]. So the Schema_links are:\nSchema_links: [访问次数,数据日期,0.5,year]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库近半年每个月的平均访问次数 (补充信息:。当前的日期是2023-09-04) (备注: )\", we are asked:\n\"当前的日期是\" so we need column = [数据日期]\n\"访问次数 (\" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [0.5,year]. So the Schema_links are:\nSchema_links: [数据日期,访问次数,0.5,year]",
"sql":"select 部门, sum(访问次数) from 内容库产品 group by 部门 order by sum(访问次数) desc limit 10",
"sql":"select 部门, sum(访问次数) from 内容库产品 group by 部门 order by sum(访问次数) desc limit 10",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库 按部门统计访问次数 top10 的部门 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\"计访问次数 \" so we need column = [访问次数]\n\" 的部门 (\" so we need column = [部门]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10]. So the Schema_links are:\nSchema_links: [访问次数,部门,10]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"内容库 按部门统计访问次数 top10 的部门 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\" 的部门 (\" so we need column = [部门]\n\"计访问次数 \" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [10]. So the Schema_links are:\nSchema_links: [部门,访问次数,10]",
"sql":"select MONTH(数据日期) from 内容库产品 where datediff('month', 数据日期, '2023-09-10') <= 7 group by MONTH(数据日期) having sum(访问次数) > 20000",
"sql":"select MONTH(数据日期) from 内容库产品 where datediff('month', 数据日期, '2023-09-10') <= 7 group by MONTH(数据日期) having sum(访问次数) > 20000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"超音速 近7个月，月度总访问量超过 2万的月份 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\"访问量超过 \" so we need column = [访问次数]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [7,20000,month]. So the Schema_links are:\nSchema_links: [访问次数,数据日期,7,20000,month]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"超音速 近7个月，月度总访问量超过 2万的月份 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\"当前的日期是\" so we need column = [数据日期]\n\"访问量超过 \" so we need column = [访问次数]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [7,20000,month]. So the Schema_links are:\nSchema_links: [数据日期,访问次数,7,20000,month]",
"sql":"select MONTH(数据日期), sum(运营播放量) from (select 数据日期, 运营播放量 from 歌曲库 where 发布日期 >= '2022-07-01' and 发布日期 <= '2023-07-01' order by 播放量 desc limit 100) t where datediff('year', 数据日期, '2023-09-10') <= 1 group by MONTH(数据日期)",
"sql":"select MONTH(数据日期), sum(运营播放量) from (select 数据日期, 运营播放量 from 歌曲库 where 发布日期 >= '2022-07-01' and 发布日期 <= '2023-07-01' order by 播放量 desc limit 100) t where datediff('year', 数据日期, '2023-09-10') <= 1 group by MONTH(数据日期)",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2022年7月到2023年7月之间发布到歌曲，按播放量取top 100，再按月粒度来统计近1年的运营播放量 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\"月之间发布到\" so we need column = [发布日期]\n\"运营播放量 \" so we need column = [播放量]\n\"运营播放量 \" so we need column = [运营播放量]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,year,100,2022-07-01,2023-07-01]. So the Schema_links are:\nSchema_links: [发布日期,播放量,运营播放量,数据日期,1,year,100,2022-07-01,2023-07-01]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2022年7月到2023年7月之间发布到歌曲，按播放量取top 100，再按月粒度来统计近1年的运营播放量 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\"运营播放量 \" so we need column = [播放量]\n\"当前的日期是\" so we need column = [数据日期]\n\"月之间发布到\" so we need column = [发布日期]\n\"运营播放量 \" so we need column = [运营播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,year,100,2022-07-01,2023-07-01]. So the Schema_links are:\nSchema_links: [播放量,数据日期,发布日期,运营播放量,1,year,100,2022-07-01,2023-07-01]",
"sql":"select MONTH(数据日期), sum(运营播放量) from (select 数据日期, 运营播放量 from 歌曲库 where 发布日期 >= '2022-07-01' and 发布日期 <= '2023-07-01' order by 播放量 desc limit 100) t where datediff('year', 数据日期, '2023-09-10') <= 1 group by MONTH(数据日期) having sum(运营播放量) > 2000",
"sql":"select MONTH(数据日期), sum(运营播放量) from (select 数据日期, 运营播放量 from 歌曲库 where 发布日期 >= '2022-07-01' and 发布日期 <= '2023-07-01' order by 播放量 desc limit 100) t where datediff('year', 数据日期, '2023-09-10') <= 1 group by MONTH(数据日期) having sum(运营播放量) > 2000",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2022年7月到2023年7月之间发布到歌曲，按播放量取top100，再按月粒度来统计近1年的运营播放量之和，筛选出其中运营播放量之和大于2k的月份 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\"月之间发布到\" so we need column = [发布日期]\n\"播放量之和，\" so we need column = [播放量]\n\"运营播放量之\" so we need column = [运营播放量]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,2000,year,100,2022-07-01,2023-07-01]. So the Schema_links are:\nSchema_links: [发布日期,播放量,运营播放量,数据日期,1,2000,year,100,2022-07-01,2023-07-01]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"2022年7月到2023年7月之间发布到歌曲，按播放量取top100，再按月粒度来统计近1年的运营播放量之和，筛选出其中运营播放量之和大于2k的月份 (补充信息:。当前的日期是2023-09-10) (备注: )\", we are asked:\n\"播放量之和，\" so we need column = [播放量]\n\"当前的日期是\" so we need column = [数据日期]\n\"月之间发布到\" so we need column = [发布日期]\n\"运营播放量之\" so we need column = [运营播放量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,2000,year,100,2022-07-01,2023-07-01]. So the Schema_links are:\nSchema_links: [播放量,数据日期,发布日期,运营播放量,1,2000,year,100,2022-07-01,2023-07-01]",
"sql":"select 国家中文名, sum(销量) from 营销月模型 where 机型类别 = '智能机' and 数据日期 >= '2023-01-01' and 数据日期 <= '2023-11-01' group by 国家中文名 order by sum(销量) desc limit 1",
"sql":"select 国家中文名, sum(销量) from 营销月模型 where 机型类别 = '智能机' and 数据日期 >= '2023-01-01' and 数据日期 <= '2023-11-01' group by 国家中文名 order by sum(销量) desc limit 1",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"今年智能机在哪个国家的销量之和最高 (补充信息:’'智能机'‘是一个’机型类别‘。当前的日期是2023-11-01) (备注: )\", we are asked:\n\"国家的销量之和\" so we need column = [国家中文名]\n\"个国家的销量\" so we need column = [销量]\n\"’机型类别‘\" so we need column = [机型类别]\n\"当前的日期是\" so we need column = [数据日期]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,2023-11-01,智能机,2023-01-01]. So the Schema_links are:\nSchema_links: [国家中文名,销量,机型类别,数据日期,1,2023-11-01,智能机,2023-01-01]",
"generatedSchemaLinkingCoT":"Let’s think step by step. In the question \"今年智能机在哪个国家的销量之和最高 (补充信息:’'智能机'‘是一个’机型类别‘。当前的日期是2023-11-01) (备注: )\", we are asked:\n\"’机型类别‘\" so we need column = [机型类别]\n\"当前的日期是\" so we need column = [数据日期]\n\"国家的销量之和\" so we need column = [国家中文名]\n\"个国家的销量\" so we need column = [销量]\nBased on the tables, columns, and Foreign_keys, The set of possible cell values are = [1,2023-11-01,智能机,2023-01-01]. So the Schema_links are:\nSchema_links: [机型类别,数据日期,国家中文名,销量,1,2023-11-01,智能机,2023-01-01]",
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
codescracker