mirror of
https://github.com/tencentmusic/supersonic.git
synced 2025-12-10 11:07:06 +00:00
1. upgrade text2sql for absolute time related expression in query. 2. add feature of resolved queries retrieval. (#160)
This commit is contained in:
codescracker
@@ -1,371 +1,360 @@
|
||||
examplars = [
|
||||
{
|
||||
"current_date": "2020-12-01",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question": "比较jackjchen和robinlee在内容库的访问次数",
|
||||
"prior_schema_links": """['jackjchen'->用户名, 'robinlee'->用户名]""",
|
||||
examplars= [
|
||||
{ "current_date":"2020-12-01",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question":"比较jackjchen和robinlee在内容库的访问次数",
|
||||
"prior_schema_links":"""['jackjchen'->用户名, 'robinlee'->用户名]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“比较jackjchen和robinlee在内容库的访问次数“中，我们被问：
|
||||
“比较jackjchen和robinlee”，所以我们需要column=[用户名]
|
||||
”内容库的访问次数“，所以我们需要column=[访问次数]
|
||||
基于table和columns，可能的cell values 是 = ['jackjchen', 'robinlee']。""",
|
||||
"schema_links": """["用户名", "访问次数", "'jackjchen'", "'robinlee'"]""",
|
||||
"sql": """select 用户名, 访问次数 from 内容库产品 where 用户名 in ('jackjchen', 'robinlee') and 数据日期 = '2020-12-01' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2022-11-06",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question": "内容库近12个月访问人数 按部门",
|
||||
"prior_schema_links": """[]""",
|
||||
“比较jackjchen和robinlee”，所以我们需要column=[用户名],cell values = ['jackjchen', 'robinlee'],所以有[用户名:('jackjchen', 'robinlee')]
|
||||
”内容库的访问次数“，所以我们需要column=[访问次数]""",
|
||||
"schema_links":"""["用户名":("'jackjchen'", "'robinlee'"), "访问次数"]""",
|
||||
"sql":"""select 用户名, 访问次数 from 内容库产品 where 用户名 in ('jackjchen', 'robinlee')"""
|
||||
},
|
||||
{ "current_date":"2022-11-06",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question":"内容库近12个月访问人数 按部门",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库近12个月访问人数 按部门“中，我们被问：
|
||||
”内容库近12个月“，所以我们需要column=[数据日期]
|
||||
”内容库近12个月“，所以我们需要column=[数据日期],cell values = [12],所以有[数据日期:(12)]
|
||||
“访问人数”，所以我们需要column=[访问人数]
|
||||
”按部门“，所以我们需要column=[部门]
|
||||
基于table和columns，可能的cell values 是 = [12]。""",
|
||||
"schema_links": """["访问人数", "部门", "数据日期", 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 """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-04-21",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question": "内容库美术部、技术研发部的访问时长",
|
||||
"prior_schema_links": """['美术部'->部门, '技术研发部'->部门]""",
|
||||
”按部门“，所以我们需要column=[部门]""",
|
||||
"schema_links":"""["数据日期":(12), "访问人数", "部门"]""",
|
||||
"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 """
|
||||
},
|
||||
{ "current_date":"2023-04-21",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question":"内容库美术部、技术研发部的访问时长",
|
||||
"prior_schema_links":"""['美术部'->部门, '技术研发部'->部门]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库美术部、技术研发部的访问时长“中，我们被问：
|
||||
“访问时长”，所以我们需要column=[访问时长]
|
||||
”内容库美术部、技术研发部“，所以我们需要column=[部门]
|
||||
基于table和columns，可能的cell values 是 = ['美术部', '技术研发部']。""",
|
||||
"schema_links": """["访问时长", "部门", "'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') and 数据日期 = '2023-04-21' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-21",
|
||||
"table_name": "严选",
|
||||
"fields_list": """["严选版权归属系", "付费模式", "结算播放份额", "付费用户结算播放份额", "数据日期"]""",
|
||||
"question": "近3天海田飞系MPPM结算播放份额",
|
||||
"prior_schema_links": """['海田飞系'->严选版权归属系]""",
|
||||
”内容库美术部、技术研发部“，所以我们需要column=[部门], cell values = ['美术部', '技术研发部'],所以有[部门:('美术部', '技术研发部')]""",
|
||||
"schema_links":"""["访问时长", "部门":("'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')"""
|
||||
},
|
||||
{ "current_date":"2023-08-21",
|
||||
"table_name":"严选",
|
||||
"fields_list":"""["严选版权归属系", "付费模式", "结算播放份额", "付费用户结算播放份额", "数据日期"]""",
|
||||
"question":"近3天海田飞系MPPM结算播放份额",
|
||||
"prior_schema_links":"""['海田飞系'->严选版权归属系]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“近3天海田飞系MPPM结算播放份额“中，我们被问：
|
||||
“MPPM结算播放份额”，所以我们需要column=[结算播放份额]
|
||||
”海田飞系“，所以我们需要column=[严选版权归属系]
|
||||
”近3天“，所以我们需要column=[数据日期]
|
||||
基于table和columns，可能的cell values 是 = ['海田飞系', 3]。""",
|
||||
"schema_links": """["结算播放份额", "严选版权归属系", "数据日期", "'海田飞系'", 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 """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-05-22",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["是否潮流人歌曲", "C音歌曲ID", "C音歌曲MID", "歌曲名", "歌曲版本", "语种", "歌曲类型", "翻唱类型", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "结算播放量", "运营播放量", "付费用户结算播放量", "历史累计结算播放量", "运营搜播量", "结算搜播量", "运营完播量", "运营推播量", "近7日复播率", "日均搜播量", "数据日期"]""",
|
||||
"question": "对比近7天翻唱版和纯音乐的歌曲播放量",
|
||||
"prior_schema_links": """['纯音乐'->语种, '翻唱版'->歌曲版本]""",
|
||||
“MPPM结算播放份额”，所以我们需要column=[结算播放份额],
|
||||
”海田飞系“，所以我们需要column=[严选版权归属系], cell values = ['海田飞系'],所以有[严选版权归属系:('海田飞系')],
|
||||
”近3天“，所以我们需要column=[数据日期], cell values = [3],所以有[数据日期:(3)]""",
|
||||
"schema_links":"""["结算播放份额", "严选版权归属系":("'海田飞系'"), "数据日期":(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 """
|
||||
},
|
||||
{ "current_date":"2023-05-22",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["是否潮流人歌曲", "C音歌曲ID", "C音歌曲MID", "歌曲名", "歌曲版本", "语种", "歌曲类型", "翻唱类型", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "结算播放量", "运营播放量", "付费用户结算播放量", "历史累计结算播放量", "运营搜播量", "结算搜播量", "运营完播量", "运营推播量", "近7日复播率", "日均搜播量", "数据日期"]""",
|
||||
"question":"对比近7天翻唱版和纯音乐的歌曲播放量",
|
||||
"prior_schema_links":"""['纯音乐'->语种, '翻唱版'->歌曲版本]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“对比近3天翻唱版和纯音乐的歌曲播放量“中，我们被问：
|
||||
“歌曲播放量”，所以我们需要column=[结算播放量]
|
||||
”翻唱版“，所以我们需要column=[歌曲版本]
|
||||
”和纯音乐的歌曲“，所以我们需要column=[语种]
|
||||
”近7天“，所以我们需要column=[数据日期]
|
||||
基于table和columns，可能的cell values 是 = ['翻唱版', '纯音乐', 7]。""",
|
||||
"schema_links": """["结算播放量", "歌曲版本", "语种", "数据日期", "'翻唱版'", "'纯音乐'", 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 """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-05-31",
|
||||
"table_name": "艺人库",
|
||||
"fields_list": """["上下架状态", "歌手名", "歌手等级", "歌手类型", "歌手来源", "MPPM潮流人等级", "活跃区域", "年龄", "歌手才能", "歌手风格", "粉丝数", "潮音粉丝数", "超声波粉丝数", "推博粉丝数", "超声波歌曲数", "在架歌曲数", "超声波分享数", "独占歌曲数", "超声波在架歌曲评论数", "有播放量歌曲数", "数据日期"]""",
|
||||
"question": "对比一下陈拙悬、孟梅琦、赖媚韵的粉丝数",
|
||||
"prior_schema_links": """['1527896'->MPPM歌手ID, '1565463'->MPPM歌手ID, '2141459'->MPPM歌手ID]""",
|
||||
”翻唱版“，所以我们需要column=[歌曲版本], cell values = ['翻唱版'],所以有[歌曲版本:('翻唱版')]
|
||||
”和纯音乐的歌曲“，所以我们需要column=[语种], cell values = ['纯音乐'],所以有[语种:('纯音乐')]
|
||||
”近7天“，所以我们需要column=[数据日期], cell values = [7],所以有[数据日期:(7)]""",
|
||||
"schema_links":"""["结算播放量", "歌曲版本":("'翻唱版'"), "语种":("'纯音乐'"), "数据日期":(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 """
|
||||
},
|
||||
{ "current_date":"2023-05-31",
|
||||
"table_name":"艺人库",
|
||||
"fields_list":"""["上下架状态", "歌手名", "歌手等级", "歌手类型", "歌手来源", "MPPM潮流人等级", "活跃区域", "年龄", "歌手才能", "歌手风格", "粉丝数", "潮音粉丝数", "超声波粉丝数", "推博粉丝数", "超声波歌曲数", "在架歌曲数", "超声波分享数", "独占歌曲数", "超声波在架歌曲评论数", "有播放量歌曲数", "数据日期"]""",
|
||||
"question":"对比一下陈拙悬、孟梅琦、赖媚韵的粉丝数",
|
||||
"prior_schema_links":"""['1527896'->MPPM歌手ID, '1565463'->MPPM歌手ID, '2141459'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“对比一下陈拙悬、孟梅琦、赖媚韵的粉丝数“中，我们被问：
|
||||
“粉丝数”，所以我们需要column=[粉丝数]
|
||||
”陈拙悬、孟梅琦、赖媚韵“，所以我们需要column=[歌手名]
|
||||
基于table和columns，可能的cell values 是 = ['陈拙悬', '孟梅琦', '赖媚韵']。""",
|
||||
"schema_links": """["粉丝数", "歌手名", "'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') and 数据日期 = '2023-05-31' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-07-31",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "歌曲版本", "歌曲类型", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question": "播放量大于1万的歌曲有多少",
|
||||
"prior_schema_links": """[]""",
|
||||
”陈拙悬、孟梅琦、赖媚韵“，所以我们需要column=[歌手名], cell values = ['陈拙悬', '孟梅琦', '赖媚韵'],所以有[歌手名:('陈拙悬', '孟梅琦', '赖媚韵')]""",
|
||||
"schema_links":"""["粉丝数", "歌手名":("'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')"""
|
||||
},
|
||||
{ "current_date":"2023-07-31",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "歌曲版本", "歌曲类型", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question":"播放量大于1万的歌曲有多少",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“播放量大于1万的歌曲有多少“中，我们被问：
|
||||
“歌曲有多少”，所以我们需要column=[歌曲名]
|
||||
”播放量大于1万的“，所以我们需要column=[结算播放量]
|
||||
基于table和columns，可能的cell values 是 = [10000]。""",
|
||||
"schema_links": """["歌曲名", "结算播放量", 10000]""",
|
||||
"sql": """select 歌曲名 from 歌曲库 where 结算播放量 > 10000 and 数据日期 = '2023-07-31' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-07-31",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links": """['美术部'->部门]""",
|
||||
”播放量大于1万的“，所以我们需要column=[结算播放量], cell values = [10000],所以有[结算播放量:(10000)]""",
|
||||
"schema_links":"""["歌曲名", "结算播放量":(10000)]""",
|
||||
"sql":"""select 歌曲名 from 歌曲库 where 结算播放量 > 10000"""
|
||||
},
|
||||
{ "current_date":"2023-07-31",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links":"""['美术部'->部门]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库访问时长小于1小时，且来自美术部的用户是哪些“中，我们被问：
|
||||
“用户是哪些”，所以我们需要column=[用户名]
|
||||
”美术部的“，所以我们需要column=[部门]
|
||||
”访问时长小于1小时“，所以我们需要column=[访问时长]
|
||||
基于table和columns，可能的cell values 是 = ['美术部', 1]。""",
|
||||
"schema_links": """["用户名", "部门", "访问时长", "'美术部'", 1]""",
|
||||
"sql": """select 用户名 from 内容库产品 where 部门 = '美术部' and 访问时长 < 1 and 数据日期 = '2023-07-31' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-31",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question": "内容库pv最高的用户有哪些",
|
||||
"prior_schema_links": """[]""",
|
||||
”美术部的“，所以我们需要column=[部门], cell values = ['美术部'],所以有[部门:('美术部')]
|
||||
”访问时长小于1小时“，所以我们需要column=[访问时长], cell values = [1],所以有[访问时长:(1)]""",
|
||||
"schema_links":"""["用户名", "部门":("'美术部'"), "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"""
|
||||
},
|
||||
{ "current_date":"2023-08-31",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question":"内容库pv最高的用户有哪些",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库pv最高的用户有哪些“中，我们被问：
|
||||
“用户有哪些”，所以我们需要column=[用户名]
|
||||
”pv最高的“，所以我们需要column=[访问次数]
|
||||
基于table和columns，可能的cell values 是 = []。""",
|
||||
"schema_links": """["用户名", "访问次数"]""",
|
||||
"sql": """select 用户名 from 内容库产品 where 数据日期 = '2023-08-31' order by 访问次数 desc limit 10 """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-31",
|
||||
"table_name": "艺人库",
|
||||
"fields_list": """["播放量层级", "播放量单调性", "播放量方差", "播放量突增类型", "播放量集中度", "歌手名", "歌手等级", "歌手类型", "歌手来源", "MPPM潮流人等级", "结算播放量", "运营播放量", "历史累计结算播放量", "有播放量歌曲数", "历史累计运营播放量", "付费用户结算播放量", "结算播放量占比", "运营播放份额", "免费用户结算播放占比", "完播量", "数据日期"]""",
|
||||
"question": "近90天袁亚伟播放量平均值是多少",
|
||||
"prior_schema_links": """['152789226'->MPPM歌手ID]""",
|
||||
”pv最高的“，所以我们需要column=[访问次数], cell values = [1],所以有[访问次数:(1)]""",
|
||||
"schema_links":"""["用户名", "访问次数":(1)]""",
|
||||
"sql":"""select 用户名 from 内容库产品 order by 访问次数 desc limit 1"""
|
||||
},
|
||||
{ "current_date":"2023-08-31",
|
||||
"table_name":"艺人库",
|
||||
"fields_list":"""["播放量层级", "播放量单调性", "播放量方差", "播放量突增类型", "播放量集中度", "歌手名", "歌手等级", "歌手类型", "歌手来源", "MPPM潮流人等级", "结算播放量", "运营播放量", "历史累计结算播放量", "有播放量歌曲数", "历史累计运营播放量", "付费用户结算播放量", "结算播放量占比", "运营播放份额", "免费用户结算播放占比", "完播量", "数据日期"]""",
|
||||
"question":"近90天袁亚伟播放量平均值是多少",
|
||||
"prior_schema_links":"""['152789226'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“近90天袁亚伟播放量平均值是多少“中，我们被问：
|
||||
“播放量平均值是多少”，所以我们需要column=[结算播放量]
|
||||
”袁亚伟“，所以我们需要column=[歌手名]
|
||||
”近90天“，所以我们需要column=[数据日期]
|
||||
基于table和columns，可能的cell values 是 = ['袁亚伟', 90]。""",
|
||||
"schema_links": """["结算播放量", "歌手名", "数据日期", "'袁亚伟'", 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 """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-31",
|
||||
"table_name": "艺人库",
|
||||
"fields_list": """["播放量层级", "播放量单调性", "播放量方差", "播放量突增类型", "播放量集中度", "歌手名", "歌手等级", "歌手类型", "歌手来源", "MPPM潮流人等级", "结算播放量", "运营播放量", "历史累计结算播放量", "有播放量歌曲数", "历史累计运营播放量", "付费用户结算播放量", "结算播放量占比", "运营播放份额", "免费用户结算播放占比", "完播量", "数据日期"]""",
|
||||
"question": "周倩倩近7天结算播放量总和是多少",
|
||||
"prior_schema_links": """['199509'->MPPM歌手ID]""",
|
||||
”袁亚伟“，所以我们需要column=[歌手名], cell values = ['袁亚伟'],所以有[歌手名:('袁亚伟')]
|
||||
”近90天“，所以我们需要column=[数据日期], cell values = [90],所以有[数据日期:(90)]""",
|
||||
"schema_links":"""["结算播放量", "歌手名":("'袁亚伟'"), "数据日期":(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 """
|
||||
},
|
||||
{ "current_date":"2023-08-31",
|
||||
"table_name":"艺人库",
|
||||
"fields_list":"""["播放量层级", "播放量单调性", "播放量方差", "播放量突增类型", "播放量集中度", "歌手名", "歌手等级", "歌手类型", "歌手来源", "MPPM潮流人等级", "结算播放量", "运营播放量", "历史累计结算播放量", "有播放量歌曲数", "历史累计运营播放量", "付费用户结算播放量", "结算播放量占比", "运营播放份额", "免费用户结算播放占比", "完播量", "数据日期"]""",
|
||||
"question":"周倩倩近7天结算播放量总和是多少",
|
||||
"prior_schema_links":"""['199509'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“周倩倩近7天结算播放量总和是多少“中，我们被问：
|
||||
“结算播放量总和是多少”，所以我们需要column=[结算播放量]
|
||||
”周倩倩“，所以我们需要column=[歌手名]
|
||||
”近7天“，所以我们需要column=[数据日期]
|
||||
基于table和columns，可能的cell values 是 = ['周倩倩', 7]。""",
|
||||
"schema_links": """["结算播放量", "歌手名", "数据日期", "'周倩倩'", 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 """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-14",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question": "内容库访问次数大于1k的部门是哪些",
|
||||
"prior_schema_links": """[]""",
|
||||
”周倩倩“，所以我们需要column=[歌手名], cell values = ['周倩倩'],所以有[歌手名:('周倩倩')]
|
||||
”近7天“，所以我们需要column=[数据日期], cell values = [7],所以有[数据日期:(7)]""",
|
||||
"schema_links":"""["结算播放量", "歌手名":("'周倩倩'"), "数据日期":(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 """
|
||||
},
|
||||
{ "current_date":"2023-09-14",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["部门", "模块", "用户名", "访问次数", "访问人数", "访问时长", "数据日期"]""",
|
||||
"question":"内容库访问次数大于1k的部门是哪些",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库访问次数大于1k的部门是哪些“中，我们被问：
|
||||
“部门是哪些”，所以我们需要column=[部门]
|
||||
”访问次数大于1k的“，所以我们需要column=[访问次数]
|
||||
基于table和columns，可能的cell values 是 = [1000]。""",
|
||||
"schema_links": """["部门", "访问次数", 1000]""",
|
||||
"sql": """select 部门 from 内容库产品 where 访问次数 > 1000 and 数据日期 = '2023-09-14' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-18",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "MPPM歌手ID", "歌曲版本", "歌曲类型", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question": "陈亿训唱的所有的播放量大于20k的孤勇者有哪些",
|
||||
"prior_schema_links": """['199509'->MPPM歌手ID, '1527123'->MPPM歌曲ID]""",
|
||||
”访问次数大于1k的“，所以我们需要column=[访问次数], cell values = [1000],所以有[访问次数:(1000)]""",
|
||||
"schema_links":"""["部门", "访问次数":(1000)]""",
|
||||
"sql":"""select 部门 from 内容库产品 where 访问次数 > 1000"""
|
||||
},
|
||||
{ "current_date":"2023-09-18",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "MPPM歌手ID", "歌曲版本", "歌曲类型", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question":"陈亿训唱的所有的播放量大于20k的孤勇者有哪些",
|
||||
"prior_schema_links":"""['199509'->MPPM歌手ID, '1527123'->MPPM歌曲ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“陈亿训唱的所有的播放量大于20k的孤勇者有哪些“中，我们被问：
|
||||
“孤勇者有哪些”，所以我们需要column=[歌曲名]
|
||||
”播放量大于20k的“，所以我们需要column=[结算播放量]
|
||||
”陈亿训唱的“，所以我们需要column=[歌手名]
|
||||
基于table和columns，可能的cell values 是 = [20000, '陈亿训', '孤勇者']。""",
|
||||
"schema_links": """["歌曲名", "结算播放量", "歌手名", 20000, "'陈亿训'", "'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' and 数据日期 = '2023-09-18' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-18",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question": "周洁轮去年发布的歌曲有哪些",
|
||||
"prior_schema_links": """['23109'->MPPM歌手ID]""",
|
||||
“孤勇者有哪些”，所以我们需要column=[歌曲名], cell values = ['孤勇者'],所以有[歌曲名:('孤勇者')]
|
||||
”播放量大于20k的“，所以我们需要column=[结算播放量], cell values = [20000],所以有[结算播放量:(20000)]
|
||||
”陈亿训唱的“，所以我们需要column=[歌手名], cell values = ['陈亿训'],所以有[歌手名:('陈亿训')]""",
|
||||
"schema_links":"""["歌曲名":("'孤勇者'"), "结算播放量":(20000), "歌手名":("'陈亿训'")]""",
|
||||
"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'"""
|
||||
},
|
||||
{ "current_date":"2023-09-18",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question":"周洁轮去年发布的歌曲有哪些",
|
||||
"prior_schema_links":"""['23109'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“周洁轮去年发布的歌曲有哪些“中，我们被问：
|
||||
“歌曲有哪些”，所以我们需要column=[歌曲名]
|
||||
”去年发布的“，所以我们需要column=[发布时间]
|
||||
”周洁轮“，所以我们需要column=[歌手名]
|
||||
基于table和columns，可能的cell values 是 = ['周洁轮', 1]。""",
|
||||
"schema_links": """["歌曲名", "发布时间", "歌手名", 1, "'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' and 数据日期 = '2023-09-18' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-11",
|
||||
"table_name": "艺人库",
|
||||
"fields_list": """["播放量层级", "播放量单调性", "播放量方差", "播放量突增类型", "播放量集中度", "歌手名", "歌手等级", "歌手类型", "歌手来源", "签约日期", "MPPM潮流人等级", "结算播放量", "运营播放量", "历史累计结算播放量", "有播放量歌曲数", "历史累计运营播放量", "付费用户结算播放量", "结算播放量占比", "运营播放份额", "免费用户结算播放占比", "完播量", "数据日期"]""",
|
||||
"question": "我想要近半年签约的播放量前十的歌手有哪些",
|
||||
"prior_schema_links": """[]""",
|
||||
”去年发布的“，所以我们需要column=[发布时间], cell values = [1],所以有[发布时间:(1)]
|
||||
”周洁轮“，所以我们需要column=[歌手名], cell values = ['周洁轮'],所以有[歌手名:('周洁轮')]""",
|
||||
"schema_links":"""["歌曲名", "发布时间":(1), "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'"""
|
||||
},
|
||||
{ "current_date":"2023-09-11",
|
||||
"table_name":"艺人库",
|
||||
"fields_list":"""["播放量层级", "播放量单调性", "播放量方差", "播放量突增类型", "播放量集中度", "歌手名", "歌手等级", "歌手类型", "歌手来源", "签约日期", "MPPM潮流人等级", "结算播放量", "运营播放量", "历史累计结算播放量", "有播放量歌曲数", "历史累计运营播放量", "付费用户结算播放量", "结算播放量占比", "运营播放份额", "免费用户结算播放占比", "完播量", "数据日期"]""",
|
||||
"question":"我想要近半年签约的播放量前十的歌手有哪些",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“我想要近半年签约的播放量前十的歌手“中，我们被问：
|
||||
“歌手有哪些”，所以我们需要column=[歌手名]
|
||||
”播放量前十的“，所以我们需要column=[结算播放量]
|
||||
”近半年签约的“，所以我们需要column=[签约日期]
|
||||
基于table和columns，可能的cell values 是 = [0.5, 10]。""",
|
||||
"schema_links": """["歌手名", "结算播放量", "签约日期", 0.5, 10]""",
|
||||
"sql": """select 歌手名 from 艺人库 where datediff('year', 签约日期, '2023-09-11') <= 0.5 and 数据日期 = '2023-09-11' order by 结算播放量 desc limit 10""",
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-12",
|
||||
"table_name": "歌曲库",
|
||||
”播放量前十的“，所以我们需要column=[结算播放量], cell values = [10],所以有[结算播放量:(10)]
|
||||
”近半年签约的“，所以我们需要column=[签约日期], cell values = [0.5],所以有[签约日期:(0.5)]""",
|
||||
"schema_links":"""["歌手名", "结算播放量":(10), "签约日期":(0.5)]""",
|
||||
"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"""
|
||||
},
|
||||
{ "current_date":"2023-08-12",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list": """["发行日期", "歌曲语言", "歌曲来源", "歌曲流派", "歌曲名", "歌曲版本", "歌曲类型", "发行时间", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links": """[]""",
|
||||
"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",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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“中，我们被问：
|
||||
“发行的歌曲中，有哪些”，所以我们需要column=[歌曲名]
|
||||
”最近一年发行的“，所以我们需要column=[发行日期]
|
||||
”在近7天播放超过一千万的“，所以我们需要column=[数据日期, 结算播放量]
|
||||
基于table和columns，可能的cell values 是 = [1, 10000000]""",
|
||||
"schema_links": """["歌曲名", "发行日期", "数据日期", "结算播放量", 1, 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""",
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-12",
|
||||
"table_name": "歌曲库",
|
||||
”最近一年发行的“，所以我们需要column=[发行日期], cell values = [1],所以有[发行日期:(1)]
|
||||
”在近7天播放超过一千万的“，所以我们需要column=[数据日期, 结算播放量], cell values = [7, 10000000],所以有[数据日期:(7), 结算播放量:(10000000)]""",
|
||||
"schema_links":"""["歌曲名", "发行日期":(1), "数据日期":(7), "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"""
|
||||
},
|
||||
{ "current_date":"2023-08-12",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list": """["发行日期", "歌曲语言", "歌曲来源", "歌曲流派", "歌曲名", "歌曲版本", "歌曲类型", "发行时间", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links": """[]""",
|
||||
"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",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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“中，我们被问：
|
||||
“发行的歌曲中，有哪些”，所以我们需要column=[歌曲名]
|
||||
”今年以来发行的“，所以我们需要column=[发行日期]
|
||||
”在近7天播放超过一千万的“，所以我们需要column=[数据日期, 结算播放量]
|
||||
基于table和columns，可能的cell values 是 = [0, 7, 10000000]""",
|
||||
"schema_links": """["歌曲名", "发行日期", "数据日期", "结算播放量", 0, 7, 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""",
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-12",
|
||||
"table_name": "歌曲库",
|
||||
”今年以来发行的“，所以我们需要column=[发行日期], cell values = [0],所以有[发行日期:(0)]
|
||||
”在近7天播放超过一千万的“，所以我们需要column=[数据日期, 结算播放量], cell values = [7, 10000000],所以有[数据日期:(7), 结算播放量:(10000000)]""",
|
||||
"schema_links":"""["歌曲名", "发行日期":(0), "数据日期":(7), "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"""
|
||||
},
|
||||
{ "current_date":"2023-08-12",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list": """["发行日期", "歌曲语言", "歌曲来源", "歌曲流派", "歌曲名", "歌曲版本", "歌曲类型", "发行时间", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links": """['514129144'->MPPM歌曲ID]""",
|
||||
"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",
|
||||
"prior_schema_links":"""['514129144'->MPPM歌曲ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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“中，我们被问：
|
||||
“发行的歌曲中，有哪些”，所以我们需要column=[歌曲名]
|
||||
”2023年以来发行的“，所以我们需要column=[发行日期]
|
||||
”在近7天播放超过一千万的“，所以我们需要column=[数据日期, 结算播放量]
|
||||
基于table和columns，可能的cell values 是 = [2023, 7, 10000000]""",
|
||||
"schema_links": """["歌曲名", "发行日期", "数据日期", "结算播放量", 2023, 7, 10000000]""",
|
||||
"sql": """select 歌曲名 from 歌曲库 where YEAR(发行日期) >= 2023 and datediff('day', 数据日期, '2023-08-12') <= 7 and 结算播放量 > 10000000""",
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-01",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question": "周洁轮2023年6月之后发布的歌曲有哪些",
|
||||
"prior_schema_links": """['23109'->MPPM歌手ID]""",
|
||||
”2023年以来发行的“，所以我们需要column=[发行日期], cell values = ['2023-01-01'],所以有[发行日期:('2023-01-01')]
|
||||
”在近7天播放超过一千万的“，所以我们需要column=[数据日期, 结算播放量], cell values = [7, 10000000],所以有[数据日期:(7), 结算播放量:(10000000)]""",
|
||||
"schema_links":"""["歌曲名", "发行日期":("'2023-01-01'"), "数据日期":(7), "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"""
|
||||
},
|
||||
{ "current_date":"2023-08-01",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question":"周洁轮2023年6月之后发布的歌曲有哪些",
|
||||
"prior_schema_links":"""['23109'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“周洁轮2023年6月之后发布的歌曲有哪些“中，我们被问：
|
||||
“歌曲有哪些”，所以我们需要column=[歌曲名]
|
||||
”2023年6月之后发布的“，所以我们需要column=[发布时间]
|
||||
”周洁轮“，所以我们需要column=[歌手名]
|
||||
基于table和columns，可能的cell values 是 = ['周洁轮', 2023, 6]。""",
|
||||
"schema_links": """["歌曲名", "发布时间", "歌手名", "周洁轮", 2023, 6]""",
|
||||
"sql": """select 歌曲名 from 歌曲库 where YEAR(发布时间) >= 2023 and MONTH(发布时间) >= 6 and 歌手名 = '周洁轮' and 数据日期 = '2023-08-01' """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-01",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"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？",
|
||||
"prior_schema_links": """['2312311'->MPPM歌手ID]""",
|
||||
”2023年6月之后发布的“，所以我们需要column=[发布时间], cell values = ['2023-06-01'],所以有[发布时间:('2023-06-01')]
|
||||
”周洁轮“，所以我们需要column=[歌手名], cell values = ['周洁轮'],所以有[歌手名:('周洁轮')]""",
|
||||
"schema_links":"""["歌曲名", "发布时间":("'2023-06-01'"), "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'"""
|
||||
},
|
||||
{ "current_date":"2023-08-01",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"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？",
|
||||
"prior_schema_links":"""['2312311'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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？“中，我们被问：
|
||||
“播放量大于500W的”，所以我们需要column=[结算播放量]
|
||||
”邓梓琦在2023年1月5日之后发布的“，所以我们需要column=[发布时间]
|
||||
”邓梓琦“，所以我们需要column=[歌手名]
|
||||
基于table和columns，可能的cell values 是 = ['邓梓琦', 2023, 1, 5, 5000000]。""",
|
||||
"schema_links": """["结算播放量", "发布时间", "歌手名", "邓梓琦", 2023, 1, 5, 5000000]""",
|
||||
"sql": """select 歌曲名 from 歌曲库 where YEAR(发布时间) >= 2023 and MONTH(发布时间) >= 1 and DAY(发布时间) >= 5 and 歌手名 = '邓梓琦' and 结算播放量 > 5000000 and 数据日期 = '2023-08-01'""",
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-17",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question": "2023年6月以后，张亮英播放量大于200万的歌曲有哪些？",
|
||||
"prior_schema_links": """['45453'->MPPM歌手ID]""",
|
||||
“播放量大于500W的”，所以我们需要column=[结算播放量], cell values = [5000000],所以有[结算播放量:(5000000)]
|
||||
”邓梓琦在2023年1月5日之后发布的“，所以我们需要column=[发布时间], cell values = ['2023-01-05'],所以有[发布时间:('2023-01-05')]
|
||||
”邓梓琦“，所以我们需要column=[歌手名], cell values = ['邓梓琦'],所以有[歌手名:('邓梓琦')]""",
|
||||
"schema_links":"""["结算播放量":(5000000), "发布时间":("'2023-01-05'"), "歌手名":("'邓梓琦'")]""",
|
||||
"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"""
|
||||
},
|
||||
{ "current_date":"2023-09-17",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"question":"2023年6月以后，张亮英播放量大于200万的歌曲有哪些？",
|
||||
"prior_schema_links":"""['45453'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“2023年6月以后，张亮英播放量大于200万的歌曲有哪些？“中，我们被问：
|
||||
“播放量大于200万的”，所以我们需要column=[结算播放量]
|
||||
”2023年6月以后，张亮英“，所以我们需要column=[数据日期, 歌手名]
|
||||
”歌曲有哪些“，所以我们需要column=[歌曲名]
|
||||
基于table和columns，可能的cell values 是 = ['张亮英', 2023, 6, 2000000]。""",
|
||||
"schema_links": """["结算播放量", "数据日期", "歌手名", "张亮英", 2023, 6, 2000000]""",
|
||||
"sql": """select 歌曲名 from 歌曲库 where YEAR(数据日期) >= 2023 and MONTH(数据日期) >= 6 and 歌手名 = '张亮英' and 结算播放量 > 2000000 """,
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-16",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links": """['23109'->MPPM歌手ID]""",
|
||||
“播放量大于200万的”，所以我们需要column=[结算播放量], cell values = [2000000],所以有[结算播放量:(2000000)]
|
||||
”2023年6月以后，张亮英“，所以我们需要column=[数据日期, 歌手名], cell values = ['2023-06-01', '张亮英'],所以有[数据日期:('2023-06-01'), 歌手名:('张亮英')],
|
||||
”歌曲有哪些“，所以我们需要column=[歌曲名]""",
|
||||
"schema_links":"""["结算播放量":(2000000), "数据日期":("'2023-06-01'"), "歌手名":("'张亮英'"), "歌曲名"]""",
|
||||
"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"""
|
||||
},
|
||||
{ "current_date":"2023-08-16",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links":"""['23109'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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“中，我们被问：
|
||||
“播放量大于20万的”，所以我们需要column=[结算播放量]
|
||||
”2021年6月以后发布的“，所以我们需要column=[发布时间]
|
||||
”李雨纯“，所以我们需要column=[歌手名]
|
||||
基于table和columns，可能的cell values 是 = ['李雨纯', 2021, 6, 200000]。""",
|
||||
"schema_links": """["结算播放量", "发布时间", "歌手名", "李雨纯", 2021, 6, 200000]""",
|
||||
"sql": """select 歌曲名 from 歌曲库 where YEAR(发布时间) >= 2021 and MONTH(发布时间) >= 6 and 歌手名 = '李雨纯' and 结算播放量 > 200000 and 数据日期 = '2023-08-16'""",
|
||||
},
|
||||
{
|
||||
"current_date": "2023-08-16",
|
||||
"table_name": "歌曲库",
|
||||
"fields_list": """["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links": """['4234234'->MPPM歌手ID]""",
|
||||
“播放量大于20万的”，所以我们需要column=[结算播放量], cell values = [200000],所以有[结算播放量:(200000)]
|
||||
”2021年6月以后发布的“，所以我们需要column=[发布时间], cell values = ['2021-06-01'],所以有[发布时间:('2021-06-01')]
|
||||
”李雨纯“，所以我们需要column=[歌手名], cell values = ['李雨纯'],所以有[歌手名:('李雨纯')]""",
|
||||
"schema_links":"""["结算播放量":(200000), "发布时间":("'2021-06-01'"), "歌手名":("'李雨纯'")]""",
|
||||
"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"""
|
||||
},
|
||||
{ "current_date":"2023-08-16",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲名", "歌曲版本", "歌手名", "歌曲类型", "发布时间", "MPPM歌曲ID", "是否严选窄口径歌曲", "是否严选宽口径歌曲", "是否潮流人歌曲", "超声波歌曲ID", "C音歌曲ID", "C音歌曲MID", "结算播放量", "运营播放量", "分享量", "收藏量", "运营搜播量", "结算搜播量", "拉新用户数", "拉活用户数", "分享率", "结算播放份额", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links":"""['4234234'->MPPM歌手ID]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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“中，我们被问：
|
||||
“播放量大于20万的”，所以我们需要column=[结算播放量]
|
||||
”1992年4月2日到2020年5月2日之间发布的“，所以我们需要column=[发布时间]
|
||||
”刘锝桦“，所以我们需要column=[歌手名]
|
||||
基于table和columns，可能的cell values 是 = ['刘锝桦', 1992, 4, 2, 2020, 5, 2, 200000]。""",
|
||||
"schema_links": """["结算播放量", "发布时间", "歌手名", "刘锝桦", 1992, 4, 2, 2020, 5, 2, 200000]""",
|
||||
"sql": """select 歌曲名 from 歌曲库 where YEAR(发布时间) >= 1992 and MONTH(发布时间) >= 4 and DAY(发布时间) >= 2 and YEAR(发布时间) <= 2020 and MONTH(发布时间) <= 5 and DAY(发布时间) <= 2 and 歌手名 = '刘锝桦' and 结算播放量 > 200000 and 数据日期 = '2023-08-16'""",
|
||||
},
|
||||
“播放量大于20万的”，所以我们需要column=[结算播放量], cell values = [200000],所以有[结算播放量:(200000)]
|
||||
”1992年4月2日到2020年5月2日之间发布的“， 所以我们需要column=[发布时间], cell values = ['1992-04-02', '2020-05-02'],所以有[发布时间:('1992-04-02', '2020-05-02')]
|
||||
”刘锝桦“，所以我们需要column=[歌手名], cell values = ['刘锝桦'],所以有[歌手名:('刘锝桦')]""",
|
||||
"schema_links":"""["结算播放量":(200000), "发布时间":("'1992-04-02'", "'2020-05-02'"), "歌手名":("'刘锝桦'")]""",
|
||||
"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"""
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-04",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question": "内容库近30天访问次数的平均数",
|
||||
"prior_schema_links": """[]""",
|
||||
"current_date":"2023-09-04",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question":"内容库近30天访问次数的平均数",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库近30天访问次数的平均数“中，我们被问：
|
||||
“访问次数的平均数”，所以我们需要column=[访问次数]
|
||||
”内容库近30天“，所以我们需要column=[数据日期]
|
||||
基于table和columns，可能的cell values 是 = [30]。""",
|
||||
"schema_links": """["访问次数", "数据日期", 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 """,
|
||||
},
|
||||
”内容库近30天“，所以我们需要column=[数据日期], cell values = [30],所以有[数据日期:(30)]""",
|
||||
"schema_links":"""["访问次数", "数据日期":(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 """
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-04",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question": "内容库近半年哪个月的访问次数汇总最高",
|
||||
"prior_schema_links": """[]""",
|
||||
"current_date":"2023-09-04",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question":"内容库近半年哪个月的访问次数汇总最高",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库近半年哪个月的访问次数汇总最高“中，我们被问：
|
||||
“访问次数汇总最高”，所以我们需要column=[访问次数]
|
||||
”内容库近半年“，所以我们需要column=[数据日期]
|
||||
基于table和columns，可能的cell values 是 = [0.5]。""",
|
||||
"schema_links": """["访问次数", "数据日期", 0.5]""",
|
||||
"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 """,
|
||||
},
|
||||
“访问次数汇总最高”，所以我们需要column=[访问次数], cell values = [1],所以有[访问次数:(1)]
|
||||
”内容库近半年“，所以我们需要column=[数据日期], cell values = [0.5],所以有[数据日期:(0.5)]""",
|
||||
"schema_links":"""["访问次数":(1), "数据日期":(0.5)]""",
|
||||
"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"""
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-04",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question": "内容库近半年每个月的平均访问次数",
|
||||
"prior_schema_links": """[]""",
|
||||
"current_date":"2023-09-04",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question":"内容库近半年每个月的平均访问次数",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库近半年每个月的平均访问次数“中，我们被问：
|
||||
“每个月的平均访问次数”，所以我们需要column=[访问次数]
|
||||
”内容库近半年“，所以我们需要column=[数据日期]
|
||||
基于table和columns，可能的cell values 是 = [0.5]。""",
|
||||
"schema_links": """["访问次数", "数据日期", 0.5]""",
|
||||
"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) """,
|
||||
},
|
||||
”内容库近半年“，所以我们需要column=[数据日期], cell values = [0.5],所以有[数据日期:(0.5)]""",
|
||||
"schema_links":"""["访问次数", "数据日期":(0.5)]""",
|
||||
"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)"""
|
||||
},
|
||||
{
|
||||
"current_date": "2023-09-10",
|
||||
"table_name": "内容库产品",
|
||||
"fields_list": """["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question": "内容库 按部门统计访问次数 top10 的部门",
|
||||
"prior_schema_links": """[]""",
|
||||
"current_date":"2023-09-10",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question":"内容库 按部门统计访问次数 top10 的部门",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“内容库 按部门统计访问次数 top10 的部门“中，我们被问：
|
||||
“访问次数 top10 的部门”，所以我们需要column=[访问次数]
|
||||
”内容库 按部门统计“，所以我们需要column=[部门]
|
||||
基于table和columns，可能的cell values 是 = [10]。""",
|
||||
"schema_links": """["访问次数", "部门", 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 """,
|
||||
},
|
||||
]
|
||||
“访问次数 top10 的部门”，所以我们需要column=[访问次数], cell values = [10],所以有[访问次数:(10)]
|
||||
”内容库 按部门统计“，所以我们需要column=[部门]""",
|
||||
"schema_links":"""["访问次数":(10), "部门"]""",
|
||||
"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"""
|
||||
},
|
||||
{
|
||||
"current_date":"2023-09-10",
|
||||
"table_name":"内容库产品",
|
||||
"fields_list":"""["用户名", "部门", "模块", "访问时长", "访问次数", "访问人数", "数据日期"]""",
|
||||
"question":"超音速 近7个月，月度总访问量超过 2万的月份",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“超音速 近7个月，月度总访问量超过 2万的月份“中，我们被问：
|
||||
“月度总访问量超过 2万的月份”，所以我们需要column=[访问次数], cell values = [20000],所以有[访问次数:(20000)]
|
||||
”超音速 近7个月“，所以我们需要column=[数据日期], cell values = [7],所以有[数据日期:(7)]""",
|
||||
"schema_links":"""["访问次数":(20000), "数据日期":(7)]""",
|
||||
"sql":"""select MONTH(数据日期) from 内容库产品 where datediff('day', 数据日期, '2023-09-10') <= 7 group by MONTH(数据日期) having sum(访问次数) > 20000"""
|
||||
},
|
||||
{
|
||||
"current_date":"2023-09-10",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲语言", "歌曲来源", "运营播放量", "播放量", "歌曲名", "结算播放量", "专辑名", "发布日期", "歌曲版本", "歌曲类型", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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“中，我们被问：
|
||||
“按月粒度来统计近1年的运营播放量”，所以我们需要column=[运营播放量, 数据日期], cell values = [1],所以有[运营播放量, 数据日期:(1)]
|
||||
”按播放量取top 100“，所以我们需要column=[播放量], cell values = [100],所以有[播放量:(100)]
|
||||
“2022年7月到2023年7月之间发布到歌曲”，所以我们需要column=[发布日期], cell values = ['2022-07-01', '2023-07-01'],所以有[发布日期:('2022-07-01', '2023-07-01')]""",
|
||||
"schema_links":"""["运营播放量", "数据日期":(1), "播放量":(100), "发布日期":("'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)"""
|
||||
},
|
||||
{
|
||||
"current_date":"2023-09-10",
|
||||
"table_name":"歌曲库",
|
||||
"fields_list":"""["歌曲语言", "歌曲来源", "运营播放量", "播放量", "歌曲名", "结算播放量", "专辑名", "发布日期", "歌曲版本", "歌曲类型", "数据日期"]""",
|
||||
"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",
|
||||
"prior_schema_links":"""[]""",
|
||||
"analysis": """让我们一步一步地思考。在问题“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“中，我们被问：
|
||||
“筛选出其中运营播放量之和大于2k的月份”，所以我们需要column=[运营播放量], cell values = [2000],所以有[运营播放量:(2000)]
|
||||
”按月粒度来统计近1年的运营播放量之和“，所以我们需要column=[数据日期], cell values = [1],所以有[数据日期:(1)]
|
||||
”按播放量取top100“，所以我们需要column=[播放量], cell values = [100],所以有[播放量:(100)]
|
||||
”2022年7月到2023年7月之间发布到歌曲“，所以我们需要column=[发布日期], cell values = ['2022-07-01', '2023-07-01'],所以有[发布日期:('2022-07-01', '2023-07-01')]""",
|
||||
"schema_links":"""["运营播放量":(2000), "数据日期":(1), "播放量":(100), "发布日期":("'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"""
|
||||
}
|
||||
]
|
||||
@@ -14,6 +14,7 @@ TEMPERATURE = 0.0
|
||||
|
||||
CHROMA_DB_PERSIST_DIR = "chm_db"
|
||||
PRESET_QUERY_COLLECTION_NAME = "preset_query_collection"
|
||||
SOLVED_QUERY_COLLECTION_NAME = "solved_query_collection"
|
||||
TEXT2DSL_COLLECTION_NAME = "text2dsl_collection"
|
||||
TEXT2DSL_FEW_SHOTS_EXAMPLE_NUM = 15
|
||||
TEXT2DSL_IS_SHORTCUT = False
|
||||
|
||||
85
chat/core/src/main/python/services/query_retrieval/run.py
Normal file
85
chat/core/src/main/python/services/query_retrieval/run.py
Normal file
@@ -0,0 +1,85 @@
|
||||
# -*- coding:utf-8 -*-
|
||||
|
||||
import os
|
||||
import sys
|
||||
import uuid
|
||||
from typing import Any, List, Mapping, Optional, Union
|
||||
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
|
||||
|
||||
import chromadb
|
||||
from chromadb.config import Settings
|
||||
from chromadb.api import Collection, Documents, Embeddings
|
||||
|
||||
from util.text2vec import Text2VecEmbeddingFunction
|
||||
|
||||
from run_config import SOLVED_QUERY_COLLECTION_NAME, PRESET_QUERY_COLLECTION_NAME
|
||||
from util.chromadb_instance import (client,
|
||||
get_chroma_collection_size, query_chroma_collection,
|
||||
parse_retrieval_chroma_collection_query, chroma_collection_query_retrieval_format,
|
||||
get_chroma_collection_by_ids, get_chroma_collection_size,
|
||||
add_chroma_collection, update_chroma_collection, delete_chroma_collection_by_ids,
|
||||
empty_chroma_collection_2)
|
||||
|
||||
emb_func = Text2VecEmbeddingFunction()
|
||||
|
||||
solved_query_collection = client.get_or_create_collection(name=SOLVED_QUERY_COLLECTION_NAME,
|
||||
embedding_function=emb_func,
|
||||
metadata={"hnsw:space": "cosine"}
|
||||
) # Get a collection object from an existing collection, by name. If it doesn't exist, create it.
|
||||
print("init_solved_query_collection_size: ", get_chroma_collection_size(solved_query_collection))
|
||||
|
||||
|
||||
preset_query_collection = client.get_or_create_collection(name=PRESET_QUERY_COLLECTION_NAME,
|
||||
embedding_function=emb_func,
|
||||
metadata={"hnsw:space": "cosine"}
|
||||
)
|
||||
print("init_preset_query_collection_size: ", get_chroma_collection_size(preset_query_collection))
|
||||
|
||||
class ChromaCollectionRetriever(object):
|
||||
def __init__(self, collection:Collection):
|
||||
self.collection = collection
|
||||
|
||||
def retrieval_query_run(self, query_texts_list:List[str],
|
||||
filter_condition:Mapping[str,str]=None, n_results:int=5):
|
||||
|
||||
retrieval_res = query_chroma_collection(self.collection, query_texts_list,
|
||||
filter_condition, n_results)
|
||||
|
||||
parsed_retrieval_res = parse_retrieval_chroma_collection_query(retrieval_res)
|
||||
parsed_retrieval_res_format = chroma_collection_query_retrieval_format(query_texts_list, parsed_retrieval_res)
|
||||
|
||||
print('parsed_retrieval_res_format: ', parsed_retrieval_res_format)
|
||||
|
||||
return parsed_retrieval_res_format
|
||||
|
||||
def get_query_by_ids(self, query_ids:List[str]):
|
||||
queries = get_chroma_collection_by_ids(self.collection, query_ids)
|
||||
return queries
|
||||
|
||||
def get_query_size(self):
|
||||
return get_chroma_collection_size(self.collection)
|
||||
|
||||
def add_queries(self, query_text_list:List[str],
|
||||
query_id_list:List[str], metadatas:List[Mapping[str, str]]=None):
|
||||
add_chroma_collection(self.collection, query_text_list, query_id_list, metadatas)
|
||||
return True
|
||||
|
||||
def update_queries(self, query_text_list:List[str],
|
||||
query_id_list:List[str], metadatas:List[Mapping[str, str]]=None):
|
||||
update_chroma_collection(self.collection, query_text_list, query_id_list, metadatas)
|
||||
return True
|
||||
|
||||
def delete_queries_by_ids(self, query_ids:List[str]):
|
||||
delete_chroma_collection_by_ids(self.collection, query_ids)
|
||||
return True
|
||||
|
||||
def empty_query_collection(self):
|
||||
self.collection = empty_chroma_collection_2(self.collection)
|
||||
|
||||
return True
|
||||
|
||||
|
||||
solved_query_retriever = ChromaCollectionRetriever(solved_query_collection)
|
||||
preset_query_retriever = ChromaCollectionRetriever(preset_query_collection)
|
||||
@@ -0,0 +1,33 @@
|
||||
# -*- coding:utf-8 -*-
|
||||
import os
|
||||
import sys
|
||||
from typing import Any, List, Mapping, Optional, Union
|
||||
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
|
||||
from services.plugin_call.run import plugin_selection_run
|
||||
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
@router.post("/plugin_selection/")
|
||||
async def tool_selection(query_body: Mapping[str, Any]):
|
||||
if "queryText" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="query_text is not in query_body")
|
||||
else:
|
||||
query_text = query_body["queryText"]
|
||||
|
||||
if "pluginConfigs" not in query_body:
|
||||
raise HTTPException(
|
||||
status_code=400, detail="pluginConfigs is not in query_body"
|
||||
)
|
||||
else:
|
||||
plugin_configs = query_body["pluginConfigs"]
|
||||
|
||||
resp = plugin_selection_run(query_text=query_text, plugin_configs=plugin_configs)
|
||||
|
||||
return resp
|
||||
|
||||
@@ -0,0 +1,71 @@
|
||||
# -*- coding:utf-8 -*-
|
||||
import os
|
||||
import sys
|
||||
from typing import Any, List, Mapping, Optional, Union
|
||||
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
|
||||
from services.query_retrieval.run import preset_query_retriever
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
@router.post("/preset_query_retrival")
|
||||
def preset_query_retrival(query_text_list: List[str], n_results: int = 5):
|
||||
parsed_retrieval_res_format = preset_query_retriever.retrieval_query_run(query_texts_list=query_text_list, filter_condition=None, n_results=n_results)
|
||||
|
||||
return parsed_retrieval_res_format
|
||||
|
||||
|
||||
@router.post("/preset_query_add")
|
||||
def preset_query_add(preset_info_list: List[Mapping[str, str]]):
|
||||
preset_queries = []
|
||||
preset_query_ids = []
|
||||
|
||||
for preset_info in preset_info_list:
|
||||
preset_queries.append(preset_info['preset_query'])
|
||||
preset_query_ids.append(preset_info['preset_query_id'])
|
||||
|
||||
preset_query_retriever.add_queries(query_text_list=preset_queries, query_id_list=preset_query_ids, metadatas=None)
|
||||
|
||||
return "success"
|
||||
|
||||
@router.post("/preset_query_update")
|
||||
def preset_query_update(preset_info_list: List[Mapping[str, str]]):
|
||||
preset_queries = []
|
||||
preset_query_ids = []
|
||||
|
||||
for preset_info in preset_info_list:
|
||||
preset_queries.append(preset_info['preset_query'])
|
||||
preset_query_ids.append(preset_info['preset_query_id'])
|
||||
|
||||
preset_query_retriever.update_queries(query_text_list=preset_queries, query_id_list=preset_query_ids, metadatas=None)
|
||||
|
||||
return "success"
|
||||
|
||||
|
||||
@router.get("/preset_query_empty")
|
||||
def preset_query_empty():
|
||||
preset_query_retriever.empty_query_collection()
|
||||
|
||||
return "success"
|
||||
|
||||
@router.post("/preset_delete_by_ids")
|
||||
def preset_delete_by_ids(preset_query_ids: List[str]):
|
||||
preset_query_retriever.delete_queries_by_ids(preset_query_ids)
|
||||
|
||||
return "success"
|
||||
|
||||
@router.post("/preset_get_by_ids")
|
||||
def preset_get_by_ids(preset_query_ids: List[str]):
|
||||
preset_queries = preset_query_retriever.get_query_by_ids(preset_query_ids)
|
||||
|
||||
return preset_queries
|
||||
|
||||
@router.get("/preset_query_size")
|
||||
def preset_query_size():
|
||||
size = preset_query_retriever.get_query_size()
|
||||
|
||||
return size
|
||||
@@ -0,0 +1,66 @@
|
||||
# -*- coding:utf-8 -*-
|
||||
import os
|
||||
import sys
|
||||
from typing import Any, List, Mapping, Optional, Union
|
||||
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
|
||||
from services.sql.run import text2sql_agent
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post("/query2sql/")
|
||||
def din_query2sql(query_body: Mapping[str, Any]):
|
||||
if "queryText" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="query_text is not in query_body")
|
||||
else:
|
||||
query_text = query_body["queryText"]
|
||||
|
||||
if "schema" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="schema is not in query_body")
|
||||
else:
|
||||
schema = query_body["schema"]
|
||||
|
||||
if "currentDate" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="currentDate is not in query_body")
|
||||
else:
|
||||
current_date = query_body["currentDate"]
|
||||
|
||||
if "linking" not in query_body:
|
||||
linking = None
|
||||
else:
|
||||
linking = query_body["linking"]
|
||||
|
||||
resp = text2sql_agent.query2sql_run(
|
||||
query_text=query_text, schema=schema, current_date=current_date, linking=linking
|
||||
)
|
||||
|
||||
return resp
|
||||
|
||||
|
||||
@router.post("/query2sql_setting_update/")
|
||||
def query2sql_setting_update(query_body: Mapping[str, Any]):
|
||||
if "sqlExamplars" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="sqlExamplars is not in query_body")
|
||||
else:
|
||||
sql_examplars = query_body["sqlExamplars"]
|
||||
|
||||
if "exampleNums" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="exampleNums is not in query_body")
|
||||
else:
|
||||
example_nums = query_body["exampleNums"]
|
||||
|
||||
if "isShortcut" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="isShortcut is not in query_body")
|
||||
else:
|
||||
is_shortcut = query_body["isShortcut"]
|
||||
|
||||
text2sql_agent.update_examples(
|
||||
sql_examples=sql_examplars, example_nums=example_nums, is_shortcut=is_shortcut
|
||||
)
|
||||
|
||||
return "success"
|
||||
@@ -0,0 +1,80 @@
|
||||
# -*- coding:utf-8 -*-
|
||||
import os
|
||||
import sys
|
||||
from typing import Any, List, Mapping, Optional, Union
|
||||
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
|
||||
from services.query_retrieval.run import solved_query_retriever
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
@router.post("/solved_query_retrival")
|
||||
def solved_query_retrival(query_info: Mapping[str, Any], n_results: int = 5):
|
||||
query_texts_list = query_info['queryTextsList']
|
||||
filter_condition = query_info['filterCondition']
|
||||
|
||||
parsed_retrieval_res_format = solved_query_retriever.retrieval_query_run(query_texts_list=query_texts_list,
|
||||
filter_condition=filter_condition,
|
||||
n_results=n_results)
|
||||
|
||||
return parsed_retrieval_res_format
|
||||
|
||||
|
||||
@router.post("/solved_query_add")
|
||||
def add_solved_queries(sovled_query_info_list: List[Mapping[str, Any]]):
|
||||
queries = []
|
||||
query_ids = []
|
||||
metadatas = []
|
||||
|
||||
for sovled_query_info in sovled_query_info_list:
|
||||
queries.append(sovled_query_info['query'])
|
||||
query_ids.append(sovled_query_info['query_id'])
|
||||
metadatas.append(sovled_query_info['metadata'])
|
||||
|
||||
solved_query_retriever.add_queries(query_text_list=queries, query_id_list=query_ids, metadatas=metadatas)
|
||||
|
||||
return "success"
|
||||
|
||||
@router.post("/solved_query_update")
|
||||
def solved_query_update(sovled_query_info_list: List[Mapping[str, Any]]):
|
||||
queries = []
|
||||
query_ids = []
|
||||
metadatas = []
|
||||
|
||||
for sovled_query_info in sovled_query_info_list:
|
||||
queries.append(sovled_query_info['query'])
|
||||
query_ids.append(sovled_query_info['query_id'])
|
||||
metadatas.append(sovled_query_info['metadata'])
|
||||
|
||||
solved_query_retriever.update_queries(query_text_list=queries, query_id_list=query_ids, metadatas=metadatas)
|
||||
|
||||
return "success"
|
||||
|
||||
|
||||
@router.get("/solved_query_empty")
|
||||
def solved_query_empty():
|
||||
solved_query_retriever.empty_query_collection()
|
||||
|
||||
return "success"
|
||||
|
||||
@router.post("/solved_query_delete_by_ids")
|
||||
def solved_query_delete_by_ids(query_ids: List[str]):
|
||||
solved_query_retriever.delete_queries_by_ids(query_ids=query_ids)
|
||||
|
||||
return "success"
|
||||
|
||||
@router.post("/solved_query_get_by_ids")
|
||||
def solved_query_get_by_ids(query_ids: List[str]):
|
||||
queries = solved_query_retriever.get_query_by_ids(query_ids=query_ids)
|
||||
|
||||
return queries
|
||||
|
||||
@router.get("/solved_query_size")
|
||||
def solved_query_size():
|
||||
size = solved_query_retriever.get_query_size()
|
||||
|
||||
return size
|
||||
@@ -11,177 +11,18 @@ from typing import Any, List, Mapping
|
||||
|
||||
from fastapi import FastAPI, HTTPException
|
||||
|
||||
from sql.run import text2sql_agent
|
||||
from run_config import LLMPARSER_HOST, LLMPARSER_PORT
|
||||
|
||||
from preset_retrieval.run import (
|
||||
preset_query_retrieval_run,
|
||||
collection as preset_query_collection,
|
||||
)
|
||||
from preset_retrieval.preset_query_db import (
|
||||
add2preset_query_collection,
|
||||
empty_preset_query_collection,
|
||||
delete_preset_query_by_ids,
|
||||
update_preset_query_collection,
|
||||
get_preset_query_by_ids,
|
||||
preset_query_collection_size,
|
||||
)
|
||||
from services_router import (query2sql_service, preset_query_service,
|
||||
solved_query_service, plugin_call_service)
|
||||
|
||||
from plugin_call.run import plugin_selection_run
|
||||
|
||||
from run_config import LLMPARSER_HOST
|
||||
from run_config import LLMPARSER_PORT
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
|
||||
@app.post("/query2sql/")
|
||||
async def din_query2sql(query_body: Mapping[str, Any]):
|
||||
if "queryText" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="query_text is not in query_body")
|
||||
else:
|
||||
query_text = query_body["queryText"]
|
||||
|
||||
if "schema" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="schema is not in query_body")
|
||||
else:
|
||||
schema = query_body["schema"]
|
||||
|
||||
if "currentDate" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="currentDate is not in query_body")
|
||||
else:
|
||||
current_date = query_body["currentDate"]
|
||||
|
||||
if "linking" not in query_body:
|
||||
linking = None
|
||||
else:
|
||||
linking = query_body["linking"]
|
||||
|
||||
resp = text2sql_agent.query2sql_run(
|
||||
query_text=query_text, schema=schema, current_date=current_date, linking=linking
|
||||
)
|
||||
|
||||
return resp
|
||||
|
||||
|
||||
@app.post("/query2sql_setting_update/")
|
||||
async def query2sql_setting_update(query_body: Mapping[str, Any]):
|
||||
if "sqlExamplars" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="sqlExamplars is not in query_body")
|
||||
else:
|
||||
sql_examplars = query_body["sqlExamplars"]
|
||||
|
||||
if "exampleNums" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="exampleNums is not in query_body")
|
||||
else:
|
||||
example_nums = query_body["exampleNums"]
|
||||
|
||||
if "isShortcut" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="isShortcut is not in query_body")
|
||||
else:
|
||||
is_shortcut = query_body["isShortcut"]
|
||||
|
||||
text2sql_agent.update_examples(
|
||||
sql_examples=sql_examplars, example_nums=example_nums, is_shortcut=is_shortcut
|
||||
)
|
||||
|
||||
return "success"
|
||||
|
||||
|
||||
@app.post("/preset_query_retrival/")
|
||||
async def preset_query_retrival(query_text_list: List[str], n_results: int = 5):
|
||||
parsed_retrieval_res_format = preset_query_retrieval_run(
|
||||
preset_query_collection, query_text_list, n_results
|
||||
)
|
||||
|
||||
return parsed_retrieval_res_format
|
||||
|
||||
|
||||
@app.post("/preset_query_add/")
|
||||
async def preset_query_add(preset_info_list: List[Mapping[str, str]]):
|
||||
preset_queries = []
|
||||
preset_query_ids = []
|
||||
|
||||
for preset_info in preset_info_list:
|
||||
preset_queries.append(preset_info["preset_query"])
|
||||
preset_query_ids.append(preset_info["preset_query_id"])
|
||||
|
||||
add2preset_query_collection(
|
||||
collection=preset_query_collection,
|
||||
preset_queries=preset_queries,
|
||||
preset_query_ids=preset_query_ids,
|
||||
)
|
||||
|
||||
return "success"
|
||||
|
||||
|
||||
@app.post("/preset_query_update/")
|
||||
async def preset_query_update(preset_info_list: List[Mapping[str, str]]):
|
||||
preset_queries = []
|
||||
preset_query_ids = []
|
||||
|
||||
for preset_info in preset_info_list:
|
||||
preset_queries.append(preset_info["preset_query"])
|
||||
preset_query_ids.append(preset_info["preset_query_id"])
|
||||
|
||||
update_preset_query_collection(
|
||||
collection=preset_query_collection,
|
||||
preset_queries=preset_queries,
|
||||
preset_query_ids=preset_query_ids,
|
||||
)
|
||||
|
||||
return "success"
|
||||
|
||||
|
||||
@app.get("/preset_query_empty/")
|
||||
async def preset_query_empty():
|
||||
empty_preset_query_collection(collection=preset_query_collection)
|
||||
|
||||
return "success"
|
||||
|
||||
|
||||
@app.post("/preset_delete_by_ids/")
|
||||
async def preset_delete_by_ids(preset_query_ids: List[str]):
|
||||
delete_preset_query_by_ids(
|
||||
collection=preset_query_collection, preset_query_ids=preset_query_ids
|
||||
)
|
||||
|
||||
return "success"
|
||||
|
||||
|
||||
@app.post("/preset_get_by_ids/")
|
||||
async def preset_get_by_ids(preset_query_ids: List[str]):
|
||||
preset_queries = get_preset_query_by_ids(
|
||||
collection=preset_query_collection, preset_query_ids=preset_query_ids
|
||||
)
|
||||
|
||||
return preset_queries
|
||||
|
||||
|
||||
@app.get("/preset_query_size/")
|
||||
async def preset_query_size():
|
||||
size = preset_query_collection_size(collection=preset_query_collection)
|
||||
|
||||
return size
|
||||
|
||||
|
||||
@app.post("/plugin_selection/")
|
||||
async def tool_selection(query_body: Mapping[str, Any]):
|
||||
if "queryText" not in query_body:
|
||||
raise HTTPException(status_code=400, detail="query_text is not in query_body")
|
||||
else:
|
||||
query_text = query_body["queryText"]
|
||||
|
||||
if "pluginConfigs" not in query_body:
|
||||
raise HTTPException(
|
||||
status_code=400, detail="pluginConfigs is not in query_body"
|
||||
)
|
||||
else:
|
||||
plugin_configs = query_body["pluginConfigs"]
|
||||
|
||||
resp = plugin_selection_run(query_text=query_text, plugin_configs=plugin_configs)
|
||||
|
||||
return resp
|
||||
|
||||
app.include_router(preset_query_service.router)
|
||||
app.include_router(solved_query_service.router)
|
||||
app.include_router(query2sql_service.router)
|
||||
app.include_router(plugin_call_service.router)
|
||||
|
||||
if __name__ == "__main__":
|
||||
uvicorn.run(app, host=LLMPARSER_HOST, port=LLMPARSER_PORT)
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
# -*- coding:utf-8 -*-
|
||||
from typing import Any, List, Mapping, Optional, Union
|
||||
|
||||
import chromadb
|
||||
from chromadb.api import Collection
|
||||
@@ -14,7 +15,7 @@ client = chromadb.Client(
|
||||
)
|
||||
|
||||
|
||||
def empty_chroma_collection_2(collection: Collection):
|
||||
def empty_chroma_collection_2(collection:Collection):
|
||||
collection_name = collection.name
|
||||
client = collection._client
|
||||
metadata = collection.metadata
|
||||
@@ -22,18 +23,113 @@ def empty_chroma_collection_2(collection: Collection):
|
||||
|
||||
client.delete_collection(collection_name)
|
||||
|
||||
new_collection = client.get_or_create_collection(
|
||||
name=collection_name, metadata=metadata, embedding_function=embedding_function
|
||||
)
|
||||
new_collection = client.get_or_create_collection(name=collection_name,
|
||||
metadata=metadata,
|
||||
embedding_function=embedding_function)
|
||||
|
||||
size_of_new_collection = new_collection.count()
|
||||
|
||||
print(
|
||||
f"Collection {collection_name} emptied. Size of new collection: {size_of_new_collection}"
|
||||
)
|
||||
print(f'Collection {collection_name} emptied. Size of new collection: {size_of_new_collection}')
|
||||
|
||||
return new_collection
|
||||
|
||||
|
||||
def empty_chroma_collection(collection: Collection):
|
||||
def empty_chroma_collection(collection:Collection) -> None:
|
||||
collection.delete()
|
||||
|
||||
|
||||
def add_chroma_collection(collection:Collection,
|
||||
queries:List[str],
|
||||
query_ids:List[str],
|
||||
metadatas:List[Mapping[str, str]]=None
|
||||
) -> None:
|
||||
|
||||
collection.add(documents=queries,
|
||||
ids=query_ids,
|
||||
metadatas=metadatas)
|
||||
|
||||
|
||||
def update_chroma_collection(collection:Collection,
|
||||
queries:List[str],
|
||||
query_ids:List[str],
|
||||
metadatas:List[Mapping[str, str]]=None
|
||||
) -> None:
|
||||
|
||||
collection.update(documents=queries,
|
||||
ids=query_ids,
|
||||
metadatas=metadatas)
|
||||
|
||||
|
||||
def query_chroma_collection(collection:Collection, query_texts:List[str],
|
||||
filter_condition:Mapping[str,str]=None, n_results:int=10):
|
||||
outer_opt = '$and'
|
||||
inner_opt = '$eq'
|
||||
|
||||
if filter_condition is not None:
|
||||
if len(filter_condition)==1:
|
||||
outer_filter = filter_condition
|
||||
else:
|
||||
inner_filter = [{_k: {inner_opt:_v}} for _k, _v in filter_condition.items()]
|
||||
outer_filter = {outer_opt: inner_filter}
|
||||
else:
|
||||
outer_filter = None
|
||||
|
||||
print('outer_filter: ', outer_filter)
|
||||
res = collection.query(query_texts=query_texts, n_results=n_results, where=outer_filter)
|
||||
return res
|
||||
|
||||
|
||||
def parse_retrieval_chroma_collection_query(res:List[Mapping[str, Any]]):
|
||||
parsed_res = [[] for _ in range(0, len(res['ids']))]
|
||||
|
||||
retrieval_ids = res['ids']
|
||||
retrieval_distances = res['distances']
|
||||
retrieval_sentences = res['documents']
|
||||
retrieval_metadatas = res['metadatas']
|
||||
|
||||
for query_idx in range(0, len(retrieval_ids)):
|
||||
id_ls = retrieval_ids[query_idx]
|
||||
distance_ls = retrieval_distances[query_idx]
|
||||
sentence_ls = retrieval_sentences[query_idx]
|
||||
metadata_ls = retrieval_metadatas[query_idx]
|
||||
|
||||
for idx in range(0, len(id_ls)):
|
||||
id = id_ls[idx]
|
||||
distance = distance_ls[idx]
|
||||
sentence = sentence_ls[idx]
|
||||
metadata = metadata_ls[idx]
|
||||
|
||||
parsed_res[query_idx].append({
|
||||
'id': id,
|
||||
'distance': distance,
|
||||
'query': sentence,
|
||||
'metadata': metadata
|
||||
})
|
||||
|
||||
return parsed_res
|
||||
|
||||
def chroma_collection_query_retrieval_format(query_list:List[str], retrieval_list:List[Mapping[str, Any]]):
|
||||
res = []
|
||||
for query_idx in range(0, len(query_list)):
|
||||
query = query_list[query_idx]
|
||||
retrieval = retrieval_list[query_idx]
|
||||
|
||||
res.append({
|
||||
'query': query,
|
||||
'retrieval': retrieval
|
||||
})
|
||||
|
||||
return res
|
||||
|
||||
|
||||
def delete_chroma_collection_by_ids(collection:Collection, query_ids:List[str]) -> None:
|
||||
collection.delete(ids=query_ids)
|
||||
|
||||
def get_chroma_collection_by_ids(collection:Collection, query_ids:List[str]):
|
||||
res = collection.get(ids=query_ids)
|
||||
|
||||
return res
|
||||
|
||||
def get_chroma_collection_size(collection:Collection) -> int:
|
||||
return collection.count()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user