Почетна Преглед Помоћ
Пријавите се
wangxiaoqing_citu
/
citu_vanna
1
0
Креирај огранак 0
Датотеке Дискусије 0 Захтеви за спајање 0 Вики
Дрво: 68988d52d4
Гране Ознаке
citu_vanna
/
logs
/
vanna.log.2025-07-22

vanna.log.2025-07-22 117 KB
Историја Датотека

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486 
  1. 2025-07-22 01:03:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    2. 

  2. 2025-07-22 01:03:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    3. 

  3. 2025-07-22 01:03:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    4. 

  4. 2025-07-22 01:03:07 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    5. 

  5. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    6. 

  6. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    7. 

  7. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    8. 

  8. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    9. 

  9. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    10. 

  10. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    11. 

  11. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    12. 

  12. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    13. 

  13. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    14. 

  14. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    15. 

  15. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    16. 

  16. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000022E4EDBB830>
    17. 

  17. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    18. 

  18. 2025-07-22 01:03:07 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    19. 

  19. 2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    20. 

  20. 2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    21. 

  21. 2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    22. 

  22. 2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    23. 

  23. 2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    24. 

  24. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    25. 

  25. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    26. 

  26. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    27. 

  27. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    28. 

  28. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    29. 

  29. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    30. 

  30. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    31. 

  31. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    32. 

  32. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    33. 

  33. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    34. 

  34. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    35. 

  35. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000022E4F300350>
    36. 

  36. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    37. 

  37. 2025-07-22 01:03:08 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    38. 

  38. 2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    39. 

  39. 2025-07-22 01:03:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    40. 

  40. 2025-07-22 11:33:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    41. 

  41. 2025-07-22 11:33:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    42. 

  42. 2025-07-22 11:33:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    43. 

  43. 2025-07-22 11:33:44 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    44. 

  44. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    45. 

  45. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    46. 

  46. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    47. 

  47. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    48. 

  48. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    49. 

  49. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    50. 

  50. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    51. 

  51. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    52. 

  52. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    53. 

  53. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    54. 

  54. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    55. 

  55. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001F8D8D51D90>
    56. 

  56. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    57. 

  57. 2025-07-22 11:33:44 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    58. 

  58. 2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    59. 

  59. 2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    60. 

  60. 2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    61. 

  61. 2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    62. 

  62. 2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    63. 

  63. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    64. 

  64. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    65. 

  65. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    66. 

  66. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    67. 

  67. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    68. 

  68. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    69. 

  69. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    70. 

  70. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    71. 

  71. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    72. 

  72. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    73. 

  73. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    74. 

  74. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001F8D97D3230>
    75. 

  75. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    76. 

  76. 2025-07-22 11:33:46 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    77. 

  77. 2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    78. 

  78. 2025-07-22 11:33:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    79. 

  79. 2025-07-22 11:53:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    80. 

  80. 2025-07-22 11:53:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    81. 

  81. 2025-07-22 11:53:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    82. 

  82. 2025-07-22 11:53:46 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    83. 

  83. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    84. 

  84. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    85. 

  85. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    86. 

  86. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    87. 

  87. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    88. 

  88. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    89. 

  89. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    90. 

  90. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    91. 

  91. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    92. 

  92. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    93. 

  93. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    94. 

  94. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000024333E01DC0>
    95. 

  95. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    96. 

  96. 2025-07-22 11:53:46 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    97. 

  97. 2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    98. 

  98. 2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    99. 

  99. 2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    100. 

  100. 2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    101. 

  101. 2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    102. 

  102. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    103. 

  103. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    104. 

  104. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    105. 

  105. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    106. 

  106. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    107. 

  107. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    108. 

  108. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    109. 

  109. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    110. 

  110. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    111. 

  111. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    112. 

  112. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    113. 

  113. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000024335C330B0>
    114. 

  114. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    115. 

  115. 2025-07-22 11:53:47 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    116. 

  116. 2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    117. 

  117. 2025-07-22 11:53:49 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    118. 

  118. 2025-07-22 11:56:58 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    119. 

  119. 2025-07-22 11:56:58 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    120. 

  120. 2025-07-22 11:56:58 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    121. 

  121. 2025-07-22 11:56:59 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    122. 

  122. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    123. 

  123. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    124. 

  124. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    125. 

  125. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    126. 

  126. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    127. 

  127. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    128. 

  128. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    129. 

  129. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    130. 

  130. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    131. 

  131. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    132. 

  132. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    133. 

  133. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000281E9462A20>
    134. 

  134. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    135. 

  135. 2025-07-22 11:56:59 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    136. 

  136. 2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    137. 

  137. 2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    138. 

  138. 2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    139. 

  139. 2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    140. 

  140. 2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    141. 

  141. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    142. 

  142. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    143. 

  143. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    144. 

  144. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    145. 

  145. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    146. 

  146. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    147. 

  147. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    148. 

  148. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    149. 

  149. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    150. 

  150. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    151. 

  151. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    152. 

  152. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000281E9B23080>
    153. 

  153. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    154. 

  154. 2025-07-22 11:57:01 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    155. 

  155. 2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    156. 

  156. 2025-07-22 11:57:02 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    157. 

  157. 2025-07-22 12:08:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    158. 

  158. 2025-07-22 12:08:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    159. 

  159. 2025-07-22 12:08:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    160. 

  160. 2025-07-22 12:08:43 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    161. 

  161. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    162. 

  162. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    163. 

  163. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    164. 

  164. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    165. 

  165. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    166. 

  166. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    167. 

  167. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    168. 

  168. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    169. 

  169. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    170. 

  170. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    171. 

  171. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    172. 

  172. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002198FF31D60>
    173. 

  173. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    174. 

  174. 2025-07-22 12:08:43 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    175. 

  175. 2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    176. 

  176. 2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    177. 

  177. 2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    178. 

  178. 2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    179. 

  179. 2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    180. 

  180. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    181. 

  181. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    182. 

  182. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    183. 

  183. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    184. 

  184. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    185. 

  185. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    186. 

  186. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    187. 

  187. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    188. 

  188. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    189. 

  189. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    190. 

  190. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    191. 

  191. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000021991D13170>
    192. 

  192. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    193. 

  193. 2025-07-22 12:08:45 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    194. 

  194. 2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    195. 

  195. 2025-07-22 12:08:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    196. 

  196. 2025-07-22 12:26:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    197. 

  197. 2025-07-22 12:26:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    198. 

  198. 2025-07-22 12:26:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    199. 

  199. 2025-07-22 12:26:17 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    200. 

  200. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    201. 

  201. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    202. 

  202. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    203. 

  203. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    204. 

  204. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    205. 

  205. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    206. 

  206. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    207. 

  207. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    208. 

  208. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    209. 

  209. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    210. 

  210. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    211. 

  211. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000025BB4681D60>
    212. 

  212. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    213. 

  213. 2025-07-22 12:26:17 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    214. 

  214. 2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    215. 

  215. 2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    216. 

  216. 2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    217. 

  217. 2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    218. 

  218. 2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    219. 

  219. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    220. 

  220. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    221. 

  221. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    222. 

  222. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    223. 

  223. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    224. 

  224. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    225. 

  225. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    226. 

  226. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    227. 

  227. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    228. 

  228. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    229. 

  229. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    230. 

  230. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000025BB5F38050>
    231. 

  231. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    232. 

  232. 2025-07-22 12:26:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    233. 

  233. 2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    234. 

  234. 2025-07-22 12:26:20 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    235. 

  235. 2025-07-22 13:24:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    236. 

  236. 2025-07-22 13:24:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    237. 

  237. 2025-07-22 13:24:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    238. 

  238. 2025-07-22 13:24:45 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    239. 

  239. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    240. 

  240. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    241. 

  241. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    242. 

  242. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    243. 

  243. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    244. 

  244. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    245. 

  245. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    246. 

  246. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    247. 

  247. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    248. 

  248. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    249. 

  249. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    250. 

  250. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001C7F90D1D30>
    251. 

  251. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    252. 

  252. 2025-07-22 13:24:45 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    253. 

  253. 2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    254. 

  254. 2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    255. 

  255. 2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    256. 

  256. 2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    257. 

  257. 2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    258. 

  258. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    259. 

  259. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    260. 

  260. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    261. 

  261. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    262. 

  262. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    263. 

  263. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    264. 

  264. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    265. 

  265. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    266. 

  266. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    267. 

  267. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    268. 

  268. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    269. 

  269. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001C7FAAF3080>
    270. 

  270. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    271. 

  271. 2025-07-22 13:24:46 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    272. 

  272. 2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    273. 

  273. 2025-07-22 13:24:48 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    274. 

  274. 2025-07-22 13:32:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    275. 

  275. 2025-07-22 13:32:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    276. 

  276. 2025-07-22 13:32:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    277. 

  277. 2025-07-22 13:32:18 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    278. 

  278. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    279. 

  279. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    280. 

  280. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    281. 

  281. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    282. 

  282. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    283. 

  283. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    284. 

  284. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    285. 

  285. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    286. 

  286. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    287. 

  287. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    288. 

  288. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    289. 

  289. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001438F619A00>
    290. 

  290. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    291. 

  291. 2025-07-22 13:32:18 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    292. 

  292. 2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    293. 

  293. 2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    294. 

  294. 2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    295. 

  295. 2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    296. 

  296. 2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    297. 

  297. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    298. 

  298. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    299. 

  299. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    300. 

  300. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    301. 

  301. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    302. 

  302. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    303. 

  303. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    304. 

  304. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    305. 

  305. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    306. 

  306. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    307. 

  307. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    308. 

  308. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001438FDA3080>
    309. 

  309. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    310. 

  310. 2025-07-22 13:32:20 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    311. 

  311. 2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    312. 

  312. 2025-07-22 13:32:21 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    313. 

  313. 2025-07-22 17:38:36 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    314. 

  314. 2025-07-22 17:38:36 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    315. 

  315. 2025-07-22 17:38:36 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    316. 

  316. 2025-07-22 17:38:36 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
    317. 

  317. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    318. 

  318. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    319. 

  319. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    320. 

  320. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    321. 

  321. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    322. 

  322. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    323. 

  323. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    324. 

  324. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    325. 

  325. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    326. 

  326. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    327. 

  327. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    328. 

  328. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000023E05F45FA0>
    329. 

  329. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    330. 

  330. 2025-07-22 17:38:36 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    331. 

  331. 2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    332. 

  332. 2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    333. 

  333. 2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    334. 

  334. 2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    335. 

  335. 2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    336. 

  336. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    337. 

  337. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    338. 

  338. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    339. 

  339. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    340. 

  340. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    341. 

  341. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    342. 

  342. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    343. 

  343. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    344. 

  344. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    345. 

  345. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    346. 

  346. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    347. 

  347. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000023E07CF30B0>
    348. 

  348. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    349. 

  349. 2025-07-22 17:38:38 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    350. 

  350. 2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    351. 

  351. 2025-07-22 17:38:39 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    352. 

  352. 2025-07-22 20:45:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
    353. 

  353. 2025-07-22 20:45:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    354. 

  354. 2025-07-22 20:45:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
    355. 

  355. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
    356. 

  356. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
    357. 

  357. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
    358. 

  358. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
    359. 

  359. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
    360. 

  360. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
    361. 

  361. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
    362. 

  362. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
    363. 

  363. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
    364. 

  364. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
    365. 

  365. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
    366. 

  366. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000023E09531AF0>
    367. 

  367. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
    368. 

  368. 2025-07-22 20:45:56 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
    369. 

  369. 2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
    370. 

  370. 2025-07-22 20:45:57 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
    371. 

  371. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: 请问系统中哪个服务区档口最多？
    372. 

  372. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近一周哪个服务区总车流量最高？取前5名。 | similarity: 0.6381
    373. 

  373. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。 | similarity: 0.6209
    374. 

  374. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 找出2023年4月平均每日订单数最高的服务区TOP3？ | similarity: 0.6178
    375. 

  375. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 昨日车流量最低的服务区是哪一个？ | similarity: 0.6156
    376. 

  376. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月订单数环比增长最快的服务区（相比3月）？ | similarity: 0.6115
    377. 

  377. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月1日各服务区总收入排名前5的明细（包含订单总数）？ | similarity: 0.6092
    378. 

  378. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
    379. 

  379. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - SQL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 0, 强制保留: 3)
    380. 

  380. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.6381 ✗
    381. 

  381. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.6209 ✗
    382. 

  382. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.6178 ✗
    383. 

  383. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日经营数据统计表
    384. 

  384. -- 描述: 高速公路服务区每日经营数据统计表，记... | similarity: 0.5484
    385. 

  385. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路路线与服务区关联表
    386. 

  386. -- 描述: 高速公路路线与服务区关联表，用于管理各路段... | similarity: 0.5339
    387. 

  387. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区信息映射表
    388. 

  388. -- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与... | similarity: 0.5318
    389. 

  389. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区基础信息表
    390. 

  390. -- 描述: 高速公路服务区基础信息表，存储服务区名称、编... | similarity: 0.5285
    391. 

  391. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线信息表
    392. 

  392. -- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速... | similarity: 0.5115
    393. 

  393. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日车辆流量统计表
    394. 

  394. -- 描述: 高速公路服务区每日车辆流量统计表，记... | similarity: 0.4766
    395. 

  395. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
    396. 

  396. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 5 条, 过滤掉 1 条 (全部满足阈值)
    397. 

  397. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.5484 ✓
    398. 

  398. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.5339 ✓
    399. 

  399. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.5318 ✓
    400. 

  400. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.5285 ✓
    401. 

  401. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.5115 ✓
    402. 

  402. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area_mapper（服务区信息映射表）
    403. 

  403. bss_service_a... | similarity: 0.5681
    404. 

  404. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（高速公路路线与服务区关联表）
    405. 

  405. bss_... | similarity: 0.5468
    406. 

  406. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_business_day_data（高速公路服务区每日经营数据统计表）
    407. 

  407. bss_bus... | similarity: 0.5467
    408. 

  408. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（高速公路服务区基础信息表）
    409. 

  409. bss_service_area... | similarity: 0.5392
    410. 

  410. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route（路段路线信息表）
    411. 

  411. bss_section_route 表路... | similarity: 0.5061
    412. 

  412. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
    413. 

  413. bss_car_day... | similarity: 0.5058
    414. 

  414. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
    415. 

  415. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
    416. 

  416. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.5681 ✓
    417. 

  417. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.5468 ✓
    418. 

  418. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.5467 ✓
    419. 

  419. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.5392 ✓
    420. 

  420. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.5061 ✓
    421. 

  421. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.5058 ✓
    422. 

  422. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: 请问系统中哪个服务区档口最多？
    423. 

  423. 2025-07-22 20:45:57 [WARNING] [vanna.BaseLLMChat] pgvector.py:666 - 向量查询未找到任何相关的错误SQL示例，问题: 请问系统中哪个服务区档口最多？
    424. 

  424. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
    425. 

  425. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
    426. 

  426. Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
    427. 

  427. 

  428. ===Tables 
    429. 

  429. -- 中文名: 高速公路服务区每日经营数据统计表
    430. 

  430. -- 描述: 高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
    431. 

  431. create table public.bss_business_day_data (
    432. 

  432.   id varchar(32) not null     -- 主键ID，主键,
    433. 

  433.   version integer not null    -- 数据版本号,
    434. 

  434.   create_ts timestamp         -- 创建时间,
    435. 

  435.   created_by varchar(50)      -- 创建人,
    436. 

  436.   update_ts timestamp         -- 更新时间,
    437. 

  437.   updated_by varchar(50)      -- 更新人,
    438. 

  438.   delete_ts timestamp         -- 删除时间,
    439. 

  439.   deleted_by varchar(50)      -- 删除人,
    440. 

  440.   oper_date date              -- 统计日期,
    441. 

  441.   service_no varchar(255)     -- 服务区编码,
    442. 

  442.   service_name varchar(255)   -- 服务区名称,
    443. 

  443.   branch_no varchar(255)      -- 档口编码,
    444. 

  444.   branch_name varchar(255)    -- 档口名称,
    445. 

  445.   wx numeric(19,4)            -- 微信支付金额,
    446. 

  446.   wx_order integer            -- 微信订单数量,
    447. 

  447.   zfb numeric(19,4)           -- 支付宝支付金额,
    448. 

  448.   zf_order integer            -- 支付宝订单数量,
    449. 

  449.   rmb numeric(19,4)           -- 现金支付金额,
    450. 

  450.   rmb_order integer           -- 现金订单数量,
    451. 

  451.   xs numeric(19,4)            -- 行吧支付金额,
    452. 

  452.   xs_order integer            -- 行吧支付订单数,
    453. 

  453.   jd numeric(19,4)            -- 金豆支付金额,
    454. 

  454.   jd_order integer            -- 金豆支付订单数,
    455. 

  455.   order_sum integer           -- 订单总数,
    456. 

  456.   pay_sum numeric(19,4)       -- 总支付金额,
    457. 

  457.   source_type integer         -- 数据来源类型,
    458. 

  458.   primary key (id)
    459. 

  459. )
    460. 

  460. 

  461. -- 中文名: 高速公路路线与服务区关联表
    462. 

  462. -- 描述: 高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
    463. 

  463. create table public.bss_section_route_area_link (
    464. 

  464.   section_route_id varchar(32) not null -- 路段路线唯一标识，主键,
    465. 

  465.   service_area_id varchar(32) not null -- 服务区唯一标识，主键,
    466. 

  466.   primary key (section_route_id, service_area_id)
    467. 

  467. )
    468. 

  468. 

  469. -- 中文名: 服务区信息映射表
    470. 

  470. -- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
    471. 

  471. create table public.bss_service_area_mapper (
    472. 

  472.   id varchar(32) not null     -- 唯一标识符，主键,
    473. 

  473.   version integer not null    -- 数据版本号,
    474. 

  474.   create_ts timestamp         -- 创建时间,
    475. 

  475.   created_by varchar(50)      -- 创建人,
    476. 

  476.   update_ts timestamp         -- 更新时间,
    477. 

  477.   updated_by varchar(50)      -- 更新人,
    478. 

  478.   delete_ts timestamp         -- 删除时间,
    479. 

  479.   deleted_by varchar(50)      -- 删除人,
    480. 

  480.   service_name varchar(255)   -- 服务区名称,
    481. 

  481.   service_no varchar(255)     -- 服务区编码,
    482. 

  482.   service_area_id varchar(32) -- 服务区业务ID,
    483. 

  483.   source_system_type varchar(50) -- 数据来源系统,
    484. 

  484.   source_type integer         -- 来源系统类型ID,
    485. 

  485.   primary key (id)
    486. 

  486. )
    487. 

  487. 

  488. -- 中文名: 高速公路服务区基础信息表
    489. 

  489. -- 描述: 高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
    490. 

  490. create table public.bss_service_area (
    491. 

  491.   id varchar(32) not null     -- 唯一标识符，主键,
    492. 

  492.   version integer not null    -- 数据版本号,
    493. 

  493.   create_ts timestamp         -- 创建时间,
    494. 

  494.   created_by varchar(50)      -- 创建人,
    495. 

  495.   update_ts timestamp         -- 更新时间,
    496. 

  496.   updated_by varchar(50)      -- 更新人,
    497. 

  497.   delete_ts timestamp         -- 删除时间,
    498. 

  498.   deleted_by varchar(50)      -- 删除人,
    499. 

  499.   service_area_name varchar(255) -- 服务区名称,
    500. 

  500.   service_area_no varchar(255) -- 服务区编码,
    501. 

  501.   company_id varchar(32)      -- 所属公司ID,
    502. 

  502.   service_position varchar(255) -- 经纬度坐标,
    503. 

  503.   service_area_type varchar(50) -- 服务区类型,
    504. 

  504.   service_state varchar(50)   -- 运营状态,
    505. 

  505.   primary key (id)
    506. 

  506. )
    507. 

  507. 

  508. -- 中文名: 路段路线信息表
    509. 

  509. -- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
    510. 

  510. create table public.bss_section_route (
    511. 

  511.   id varchar(32) not null     -- 主键ID，主键,
    512. 

  512.   version integer not null    -- 数据版本号,
    513. 

  513.   create_ts timestamp         -- 创建时间,
    514. 

  514.   created_by varchar(50)      -- 创建人,
    515. 

  515.   update_ts timestamp         -- 更新时间,
    516. 

  516.   updated_by varchar(50)      -- 更新人,
    517. 

  517.   delete_ts timestamp         -- 删除时间,
    518. 

  518.   deleted_by varchar(50)      -- 删除人,
    519. 

  519.   section_name varchar(255)   -- 路段名称,
    520. 

  520.   route_name varchar(255)     -- 路线名称,
    521. 

  521.   code varchar(255)           -- 路段编号,
    522. 

  522.   primary key (id)
    523. 

  523. )
    524. 

  524. 

  525. 

  526. ===Additional Context 
    527. 

  527. 

  528. ## bss_service_area_mapper（服务区信息映射表）
    529. 

  529. bss_service_area_mapper 表服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
    530. 

  530. 字段列表：
    531. 

  531. - id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 00e1e893909211ed8ee6fa163eaf653f, 013867f5962211ed8ee6fa163eaf653f]
    532. 

  532. - version (integer) - 数据版本号 [非空] [示例: 1]
    533. 

  533. - create_ts (timestamp) - 创建时间 [示例: 2023-01-10 10:54:03, 2023-01-17 12:47:29]
    534. 

  534. - created_by (varchar(50)) - 创建人 [示例: admin]
    535. 

  535. - update_ts (timestamp) - 更新时间 [示例: 2023-01-10 10:54:07, 2023-01-17 12:47:32]
    536. 

  536. - updated_by (varchar(50)) - 更新人
    537. 

  537. - delete_ts (timestamp) - 删除时间
    538. 

  538. - deleted_by (varchar(50)) - 删除人
    539. 

  539. - service_name (varchar(255)) - 服务区名称 [示例: 信丰西服务区, 南康北服务区]
    540. 

  540. - service_no (varchar(255)) - 服务区编码 [示例: 1067, 1062]
    541. 

  541. - service_area_id (varchar(32)) - 服务区业务ID [示例: 97cd6cd516a551409a4d453a58f9e170, fdbdd042962011ed8ee6fa163eaf653f]
    542. 

  542. - source_system_type (varchar(50)) - 数据来源系统 [示例: 驿美, 驿购]
    543. 

  543. - source_type (integer) - 来源系统类型ID [示例: 3, 1]
    544. 

  544. 字段补充说明：
    545. 

  545. - id 为主键
    546. 

  546. - source_system_type 为枚举字段，包含取值：司乘管理、商业管理、驿购、驿美、手工录入
    547. 

  547. - source_type 为枚举字段，包含取值：5、0、1、3、4
    548. 

  548. 

  549. ## bss_section_route_area_link（高速公路路线与服务区关联表）
    550. 

  550. bss_section_route_area_link 表高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
    551. 

  551. 字段列表：
    552. 

  552. - section_route_id (varchar(32)) - 路段路线唯一标识 [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
    553. 

  553. - service_area_id (varchar(32)) - 服务区唯一标识 [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
    554. 

  554. 字段补充说明：
    555. 

  555. - 复合主键：section_route_id, service_area_id
    556. 

  556. 

  557. ## bss_business_day_data（高速公路服务区每日经营数据统计表）
    558. 

  558. bss_business_day_data 表高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
    559. 

  559. 字段列表：
    560. 

  560. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 00827DFF993D415488EA1F07CAE6C440, 00e799048b8cbb8ee758eac9c8b4b820]
    561. 

  561. - version (integer) - 数据版本号 [非空] [示例: 1]
    562. 

  562. - create_ts (timestamp) - 创建时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
    563. 

  563. - created_by (varchar(50)) - 创建人 [示例: xingba]
    564. 

  564. - update_ts (timestamp) - 更新时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
    565. 

  565. - updated_by (varchar(50)) - 更新人
    566. 

  566. - delete_ts (timestamp) - 删除时间
    567. 

  567. - deleted_by (varchar(50)) - 删除人
    568. 

  568. - oper_date (date) - 统计日期 [示例: 2023-04-01]
    569. 

  569. - service_no (varchar(255)) - 服务区编码 [示例: 1028, H0501]
    570. 

  570. - service_name (varchar(255)) - 服务区名称 [示例: 宜春服务区, 庐山服务区]
    571. 

  571. - branch_no (varchar(255)) - 档口编码 [示例: 1, H05016]
    572. 

  572. - branch_name (varchar(255)) - 档口名称 [示例: 宜春南区, 庐山鲜徕客东区]
    573. 

  573. - wx (numeric(19,4)) - 微信支付金额 [示例: 4790.0000, 2523.0000]
    574. 

  574. - wx_order (integer) - 微信订单数量 [示例: 253, 133]
    575. 

  575. - zfb (numeric(19,4)) - 支付宝支付金额 [示例: 229.0000, 0.0000]
    576. 

  576. - zf_order (integer) - 支付宝订单数量 [示例: 15, 0]
    577. 

  577. - rmb (numeric(19,4)) - 现金支付金额 [示例: 1058.5000, 124.0000]
    578. 

  578. - rmb_order (integer) - 现金订单数量 [示例: 56, 12]
    579. 

  579. - xs (numeric(19,4)) - 行吧支付金额 [示例: 0.0000, 40.0000]
    580. 

  580. - xs_order (integer) - 行吧支付订单数 [示例: 0, 1]
    581. 

  581. - jd (numeric(19,4)) - 金豆支付金额 [示例: 0.0000]
    582. 

  582. - jd_order (integer) - 金豆支付订单数 [示例: 0]
    583. 

  583. - order_sum (integer) - 订单总数 [示例: 324, 146]
    584. 

  584. - pay_sum (numeric(19,4)) - 总支付金额 [示例: 6077.5000, 2687.0000]
    585. 

  585. - source_type (integer) - 数据来源类型 [示例: 1, 0, 4]
    586. 

  586. 字段补充说明：
    587. 

  587. - id 为主键
    588. 

  588. - source_type 为枚举字段，包含取值：0、4、1、2、3
    589. 

  589. 

  590. ## bss_service_area（高速公路服务区基础信息表）
    591. 

  591. bss_service_area 表高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
    592. 

  592. 字段列表：
    593. 

  593. - id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
    594. 

  594. - version (integer) - 数据版本号 [非空] [示例: 3, 6]
    595. 

  595. - create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
    596. 

  596. - created_by (varchar(50)) - 创建人 [示例: admin]
    597. 

  597. - update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
    598. 

  598. - updated_by (varchar(50)) - 更新人 [示例: admin]
    599. 

  599. - delete_ts (timestamp) - 删除时间
    600. 

  600. - deleted_by (varchar(50)) - 删除人 [示例: ]
    601. 

  601. - service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
    602. 

  602. - service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
    603. 

  603. - company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
    604. 

  604. - service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
    605. 

  605. - service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
    606. 

  606. - service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
    607. 

  607. 字段补充说明：
    608. 

  608. - id 为主键
    609. 

  609. - service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
    610. 

  610. - service_state 为枚举字段，包含取值：开放、关闭、上传数据
    611. 

  611. 

  612. ## bss_section_route（路段路线信息表）
    613. 

  613. bss_section_route 表路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
    614. 

  614. 字段列表：
    615. 

  615. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 04ri3j67a806uw2c6o6dwdtz4knexczh, 0g5mnefxxtukql2cq6acul7phgskowy7]
    616. 

  616. - version (integer) - 数据版本号 [非空] [示例: 1, 0]
    617. 

  617. - create_ts (timestamp) - 创建时间 [示例: 2021-10-29 19:43:50, 2022-03-04 16:07:16]
    618. 

  618. - created_by (varchar(50)) - 创建人 [示例: admin]
    619. 

  619. - update_ts (timestamp) - 更新时间
    620. 

  620. - updated_by (varchar(50)) - 更新人
    621. 

  621. - delete_ts (timestamp) - 删除时间
    622. 

  622. - deleted_by (varchar(50)) - 删除人
    623. 

  623. - section_name (varchar(255)) - 路段名称 [示例: 昌栗, 昌宁]
    624. 

  624. - route_name (varchar(255)) - 路线名称 [示例: 昌栗, 昌韶]
    625. 

  625. - code (varchar(255)) - 路段编号 [示例: SR0001, SR0002]
    626. 

  626. 字段补充说明：
    627. 

  627. - id 为主键
    628. 

  628. - created_by 为枚举字段，包含取值：admin
    629. 

  629. 

  630. ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
    631. 

  631. bss_car_day_count 表高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
    632. 

  632. 字段列表：
    633. 

  633. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 00022c1c99ff11ec86d4fa163ec0f8fc, 00022caa99ff11ec86d4fa163ec0f8fc]
    634. 

  634. - version (integer) - 数据版本号 [非空] [示例: 1]
    635. 

  635. - create_ts (timestamp) - 创建时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
    636. 

  636. - created_by (varchar(50)) - 创建人
    637. 

  637. - update_ts (timestamp) - 更新时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
    638. 

  638. - updated_by (varchar(50)) - 更新人
    639. 

  639. - delete_ts (timestamp) - 删除时间
    640. 

  640. - deleted_by (varchar(50)) - 删除人
    641. 

  641. - customer_count (bigint) - 车辆数量 [示例: 1114, 295]
    642. 

  642. - car_type (varchar(100)) - 车辆类别 [示例: 其他]
    643. 

  643. - count_date (date) - 统计日期 [示例: 2022-03-02, 2022-02-02]
    644. 

  644. - service_area_id (varchar(32)) - 服务区ID [示例: 17461166e7fa3ecda03534a5795ce985, 81f4eb731fb0728aef17ae61f1f1daef]
    645. 

  645. 字段补充说明：
    646. 

  646. - id 为主键
    647. 

  647. - car_type 为枚举字段，包含取值：其他、危化品、城际、过境
    648. 

  648. 

  649. ===Response Guidelines 
    650. 

  650. **IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
    651. 

  651. 

  652. 1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
    653. 

  653. 2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
    654. 

  654. 3. If the provided context is insufficient, please explain why it can't be generated. 
    655. 

  655. 4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
    656. 

  656.    - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
    657. 

  657.      interpret it as 'How many dining stalls does Nancheng Service Area have?'
    658. 

  658. 5. Please use the most relevant table(s). 
    659. 

  659. 6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
    660. 

  660. 7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
    661. 

  661. 8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
    662. 

  662. 9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
    663. 

  663.    - Every column MUST use AS with a Chinese alias
    664. 

  664.    - Raw column names without aliases are NOT acceptable
    665. 

  665.    - Examples: 
    666. 

  666.      * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
    667. 

  667.      * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
    668. 

  668.      * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
    669. 

  669.    - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
    670. 

  670. 

  671. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    672. 

  672. user_content: 最近一周哪个服务区总车流量最高？取前5名。
    673. 

  673. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name AS 服务区名称, SUM(c.customer_count) AS 总车流量 FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - 7 AND c.delete_ts IS NULL AND s.delete_ts IS NULL GROUP BY s.service_area_name ORDER BY 总车流量 DESC LIMIT 5;
    674. 

  674. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    675. 

  675. user_content: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。
    676. 

  676. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sr.route_name AS 路线名称, COUNT(DISTINCT link.service_area_id) AS 服务区数量 FROM bss_section_route sr JOIN bss_section_route_area_link link ON sr.id = link.section_route_id WHERE sr.delete_ts IS NULL GROUP BY sr.route_name ORDER BY 服务区数量 DESC;
    677. 

  677. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    678. 

  678. user_content: 找出2023年4月平均每日订单数最高的服务区TOP3？
    679. 

  679. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_name AS 服务区名称, AVG(order_sum) AS 日均订单数 FROM bss_business_day_data WHERE oper_date BETWEEN '2023-04-01' AND '2023-04-30' AND delete_ts IS NULL GROUP BY service_name ORDER BY 日均订单数 DESC LIMIT 3;
    680. 

  680. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    681. 

  681. user_content: 请问系统中哪个服务区档口最多？
    682. 

  682. 2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': "You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
    683. 

  683. 2025-07-22 20:45:57 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
    684. 

  684. Using model qwen-plus-latest for 2957.0 tokens (approx)
    685. 

  685. 2025-07-22 20:45:57 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
    686. 

  686. 2025-07-22 20:45:57 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
    687. 

  687. 2025-07-22 20:46:00 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT service_name AS 服务区名称, COUNT(DISTINCT branch_no) AS 档口数量 FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name ORDER BY 档口数量 DESC LIMIT 1;
    688. 

  688. 2025-07-22 20:46:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT service_name AS 服务区名称, COUNT(DISTINCT branch_no) AS 档口数量 FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name ORDER BY 档口数量 DESC LIMIT 1;
    689. 

  689. 2025-07-22 20:46:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
    690. 

  690.  SELECT service_name AS 服务区名称, COUNT(DISTINCT branch_no) AS 档口数量 FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name ORDER BY 档口数量 DESC LIMIT 1;
    691. 

  691. 2025-07-22 20:54:14 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: Previous conversation context:
    692. 

  692. human: 请问系统中哪个服务区档口最多？
    693. 

  693. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    694. 

  694. 

  695. Current user question:
    696. 

  696. human: 请问这个服务区有几个餐饮档口？
    697. 

  697. 

  698. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    699. 

  699. 2025-07-22 20:54:16 [DEBUG] [vanna.EmbeddingFunction] embedding_function.py:169 - 成功生成embedding向量，维度: 1024
    700. 

  700. 2025-07-22 20:54:19 [DEBUG] [vanna.EmbeddingFunction] embedding_function.py:169 - 成功生成embedding向量，维度: 1024
    701. 

  701. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。 | similarity: 0.6985
    702. 

  702. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？ | similarity: 0.6528
    703. 

  703. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近一周哪个服务区总车流量最高？取前5名。 | similarity: 0.6383
    704. 

  704. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月1日各服务区总收入排名前5的明细（包含订单总数）？ | similarity: 0.636
    705. 

  705. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 找出2023年4月平均每日订单数最高的服务区TOP3？ | similarity: 0.6116
    706. 

  706. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 计算每个服务区的“状态影响指数”=日均营收 × 平均车流量，并按此指数排序TOP 10？ | similarity: 0.6106
    707. 

  707. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
    708. 

  708. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - SQL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 2, 强制保留: 1)
    709. 

  709. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.6985 ✓
    710. 

  710. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.6528 ✓
    711. 

  711. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.6383 ✗
    712. 

  712. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日经营数据统计表
    713. 

  713. -- 描述: 高速公路服务区每日经营数据统计表，记... | similarity: 0.6253
    714. 

  714. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路路线与服务区关联表
    715. 

  715. -- 描述: 高速公路路线与服务区关联表，用于管理各路段... | similarity: 0.5987
    716. 

  716. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区基础信息表
    717. 

  717. -- 描述: 高速公路服务区基础信息表，存储服务区名称、编... | similarity: 0.5917
    718. 

  718. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区信息映射表
    719. 

  719. -- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与... | similarity: 0.574
    720. 

  720. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线信息表
    721. 

  721. -- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速... | similarity: 0.5615
    722. 

  722. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日车辆流量统计表
    723. 

  723. -- 描述: 高速公路服务区每日车辆流量统计表，记... | similarity: 0.5517
    724. 

  724. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
    725. 

  725. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
    726. 

  726. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.6253 ✓
    727. 

  727. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.5987 ✓
    728. 

  728. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.5917 ✓
    729. 

  729. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.574 ✓
    730. 

  730. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.5615 ✓
    731. 

  731. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 6: similarity=0.5517 ✓
    732. 

  732. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_business_day_data（高速公路服务区每日经营数据统计表）
    733. 

  733. bss_bus... | similarity: 0.6161
    734. 

  734. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area_mapper（服务区信息映射表）
    735. 

  735. bss_service_a... | similarity: 0.6125
    736. 

  736. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（高速公路服务区基础信息表）
    737. 

  737. bss_service_area... | similarity: 0.6007
    738. 

  738. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（高速公路路线与服务区关联表）
    739. 

  739. bss_... | similarity: 0.5907
    740. 

  740. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
    741. 

  741. bss_car_day... | similarity: 0.5816
    742. 

  742. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route（路段路线信息表）
    743. 

  743. bss_section_route 表路... | similarity: 0.5589
    744. 

  744. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
    745. 

  745. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
    746. 

  746. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.6161 ✓
    747. 

  747. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.6125 ✓
    748. 

  748. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.6007 ✓
    749. 

  749. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.5907 ✓
    750. 

  750. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.5816 ✓
    751. 

  751. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.5589 ✓
    752. 

  752. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: Previous conversation context:
    753. 

  753. human: 请问系统中哪个服务区档口最多？
    754. 

  754. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    755. 

  755. 

  756. Current user question:
    757. 

  757. human: 请问这个服务区有几个餐饮档口？
    758. 

  758. 

  759. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    760. 

  760. 2025-07-22 20:54:19 [WARNING] [vanna.BaseLLMChat] pgvector.py:666 - 向量查询未找到任何相关的错误SQL示例，问题: Previous conversation context:
    761. 

  761. human: 请问系统中哪个服务区档口最多？
    762. 

  762. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    763. 

  763. 

  764. Current user question:
    765. 

  765. human: 请问这个服务区有几个餐饮档口？
    766. 

  766. 

  767. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    768. 

  768. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
    769. 

  769. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
    770. 

  770. Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
    771. 

  771. 

  772. ===Tables 
    773. 

  773. -- 中文名: 高速公路服务区每日经营数据统计表
    774. 

  774. -- 描述: 高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
    775. 

  775. create table public.bss_business_day_data (
    776. 

  776.   id varchar(32) not null     -- 主键ID，主键,
    777. 

  777.   version integer not null    -- 数据版本号,
    778. 

  778.   create_ts timestamp         -- 创建时间,
    779. 

  779.   created_by varchar(50)      -- 创建人,
    780. 

  780.   update_ts timestamp         -- 更新时间,
    781. 

  781.   updated_by varchar(50)      -- 更新人,
    782. 

  782.   delete_ts timestamp         -- 删除时间,
    783. 

  783.   deleted_by varchar(50)      -- 删除人,
    784. 

  784.   oper_date date              -- 统计日期,
    785. 

  785.   service_no varchar(255)     -- 服务区编码,
    786. 

  786.   service_name varchar(255)   -- 服务区名称,
    787. 

  787.   branch_no varchar(255)      -- 档口编码,
    788. 

  788.   branch_name varchar(255)    -- 档口名称,
    789. 

  789.   wx numeric(19,4)            -- 微信支付金额,
    790. 

  790.   wx_order integer            -- 微信订单数量,
    791. 

  791.   zfb numeric(19,4)           -- 支付宝支付金额,
    792. 

  792.   zf_order integer            -- 支付宝订单数量,
    793. 

  793.   rmb numeric(19,4)           -- 现金支付金额,
    794. 

  794.   rmb_order integer           -- 现金订单数量,
    795. 

  795.   xs numeric(19,4)            -- 行吧支付金额,
    796. 

  796.   xs_order integer            -- 行吧支付订单数,
    797. 

  797.   jd numeric(19,4)            -- 金豆支付金额,
    798. 

  798.   jd_order integer            -- 金豆支付订单数,
    799. 

  799.   order_sum integer           -- 订单总数,
    800. 

  800.   pay_sum numeric(19,4)       -- 总支付金额,
    801. 

  801.   source_type integer         -- 数据来源类型,
    802. 

  802.   primary key (id)
    803. 

  803. )
    804. 

  804. 

  805. -- 中文名: 高速公路路线与服务区关联表
    806. 

  806. -- 描述: 高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
    807. 

  807. create table public.bss_section_route_area_link (
    808. 

  808.   section_route_id varchar(32) not null -- 路段路线唯一标识，主键,
    809. 

  809.   service_area_id varchar(32) not null -- 服务区唯一标识，主键,
    810. 

  810.   primary key (section_route_id, service_area_id)
    811. 

  811. )
    812. 

  812. 

  813. -- 中文名: 高速公路服务区基础信息表
    814. 

  814. -- 描述: 高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
    815. 

  815. create table public.bss_service_area (
    816. 

  816.   id varchar(32) not null     -- 唯一标识符，主键,
    817. 

  817.   version integer not null    -- 数据版本号,
    818. 

  818.   create_ts timestamp         -- 创建时间,
    819. 

  819.   created_by varchar(50)      -- 创建人,
    820. 

  820.   update_ts timestamp         -- 更新时间,
    821. 

  821.   updated_by varchar(50)      -- 更新人,
    822. 

  822.   delete_ts timestamp         -- 删除时间,
    823. 

  823.   deleted_by varchar(50)      -- 删除人,
    824. 

  824.   service_area_name varchar(255) -- 服务区名称,
    825. 

  825.   service_area_no varchar(255) -- 服务区编码,
    826. 

  826.   company_id varchar(32)      -- 所属公司ID,
    827. 

  827.   service_position varchar(255) -- 经纬度坐标,
    828. 

  828.   service_area_type varchar(50) -- 服务区类型,
    829. 

  829.   service_state varchar(50)   -- 运营状态,
    830. 

  830.   primary key (id)
    831. 

  831. )
    832. 

  832. 

  833. -- 中文名: 服务区信息映射表
    834. 

  834. -- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
    835. 

  835. create table public.bss_service_area_mapper (
    836. 

  836.   id varchar(32) not null     -- 唯一标识符，主键,
    837. 

  837.   version integer not null    -- 数据版本号,
    838. 

  838.   create_ts timestamp         -- 创建时间,
    839. 

  839.   created_by varchar(50)      -- 创建人,
    840. 

  840.   update_ts timestamp         -- 更新时间,
    841. 

  841.   updated_by varchar(50)      -- 更新人,
    842. 

  842.   delete_ts timestamp         -- 删除时间,
    843. 

  843.   deleted_by varchar(50)      -- 删除人,
    844. 

  844.   service_name varchar(255)   -- 服务区名称,
    845. 

  845.   service_no varchar(255)     -- 服务区编码,
    846. 

  846.   service_area_id varchar(32) -- 服务区业务ID,
    847. 

  847.   source_system_type varchar(50) -- 数据来源系统,
    848. 

  848.   source_type integer         -- 来源系统类型ID,
    849. 

  849.   primary key (id)
    850. 

  850. )
    851. 

  851. 

  852. -- 中文名: 路段路线信息表
    853. 

  853. -- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
    854. 

  854. create table public.bss_section_route (
    855. 

  855.   id varchar(32) not null     -- 主键ID，主键,
    856. 

  856.   version integer not null    -- 数据版本号,
    857. 

  857.   create_ts timestamp         -- 创建时间,
    858. 

  858.   created_by varchar(50)      -- 创建人,
    859. 

  859.   update_ts timestamp         -- 更新时间,
    860. 

  860.   updated_by varchar(50)      -- 更新人,
    861. 

  861.   delete_ts timestamp         -- 删除时间,
    862. 

  862.   deleted_by varchar(50)      -- 删除人,
    863. 

  863.   section_name varchar(255)   -- 路段名称,
    864. 

  864.   route_name varchar(255)     -- 路线名称,
    865. 

  865.   code varchar(255)           -- 路段编号,
    866. 

  866.   primary key (id)
    867. 

  867. )
    868. 

  868. 

  869. -- 中文名: 高速公路服务区每日车辆流量统计表
    870. 

  870. -- 描述: 高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
    871. 

  871. create table public.bss_car_day_count (
    872. 

  872.   id varchar(32) not null     -- 主键ID，主键,
    873. 

  873.   version integer not null    -- 数据版本号,
    874. 

  874.   create_ts timestamp         -- 创建时间,
    875. 

  875.   created_by varchar(50)      -- 创建人,
    876. 

  876.   update_ts timestamp         -- 更新时间,
    877. 

  877.   updated_by varchar(50)      -- 更新人,
    878. 

  878.   delete_ts timestamp         -- 删除时间,
    879. 

  879.   deleted_by varchar(50)      -- 删除人,
    880. 

  880.   customer_count bigint       -- 车辆数量,
    881. 

  881.   car_type varchar(100)       -- 车辆类别,
    882. 

  882.   count_date date             -- 统计日期,
    883. 

  883.   service_area_id varchar(32) -- 服务区ID,
    884. 

  884.   primary key (id)
    885. 

  885. )
    886. 

  886. 

  887. 

  888. ===Additional Context 
    889. 

  889. 

  890. ## bss_business_day_data（高速公路服务区每日经营数据统计表）
    891. 

  891. bss_business_day_data 表高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
    892. 

  892. 字段列表：
    893. 

  893. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 00827DFF993D415488EA1F07CAE6C440, 00e799048b8cbb8ee758eac9c8b4b820]
    894. 

  894. - version (integer) - 数据版本号 [非空] [示例: 1]
    895. 

  895. - create_ts (timestamp) - 创建时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
    896. 

  896. - created_by (varchar(50)) - 创建人 [示例: xingba]
    897. 

  897. - update_ts (timestamp) - 更新时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
    898. 

  898. - updated_by (varchar(50)) - 更新人
    899. 

  899. - delete_ts (timestamp) - 删除时间
    900. 

  900. - deleted_by (varchar(50)) - 删除人
    901. 

  901. - oper_date (date) - 统计日期 [示例: 2023-04-01]
    902. 

  902. - service_no (varchar(255)) - 服务区编码 [示例: 1028, H0501]
    903. 

  903. - service_name (varchar(255)) - 服务区名称 [示例: 宜春服务区, 庐山服务区]
    904. 

  904. - branch_no (varchar(255)) - 档口编码 [示例: 1, H05016]
    905. 

  905. - branch_name (varchar(255)) - 档口名称 [示例: 宜春南区, 庐山鲜徕客东区]
    906. 

  906. - wx (numeric(19,4)) - 微信支付金额 [示例: 4790.0000, 2523.0000]
    907. 

  907. - wx_order (integer) - 微信订单数量 [示例: 253, 133]
    908. 

  908. - zfb (numeric(19,4)) - 支付宝支付金额 [示例: 229.0000, 0.0000]
    909. 

  909. - zf_order (integer) - 支付宝订单数量 [示例: 15, 0]
    910. 

  910. - rmb (numeric(19,4)) - 现金支付金额 [示例: 1058.5000, 124.0000]
    911. 

  911. - rmb_order (integer) - 现金订单数量 [示例: 56, 12]
    912. 

  912. - xs (numeric(19,4)) - 行吧支付金额 [示例: 0.0000, 40.0000]
    913. 

  913. - xs_order (integer) - 行吧支付订单数 [示例: 0, 1]
    914. 

  914. - jd (numeric(19,4)) - 金豆支付金额 [示例: 0.0000]
    915. 

  915. - jd_order (integer) - 金豆支付订单数 [示例: 0]
    916. 

  916. - order_sum (integer) - 订单总数 [示例: 324, 146]
    917. 

  917. - pay_sum (numeric(19,4)) - 总支付金额 [示例: 6077.5000, 2687.0000]
    918. 

  918. - source_type (integer) - 数据来源类型 [示例: 1, 0, 4]
    919. 

  919. 字段补充说明：
    920. 

  920. - id 为主键
    921. 

  921. - source_type 为枚举字段，包含取值：0、4、1、2、3
    922. 

  922. 

  923. ## bss_service_area_mapper（服务区信息映射表）
    924. 

  924. bss_service_area_mapper 表服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
    925. 

  925. 字段列表：
    926. 

  926. - id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 00e1e893909211ed8ee6fa163eaf653f, 013867f5962211ed8ee6fa163eaf653f]
    927. 

  927. - version (integer) - 数据版本号 [非空] [示例: 1]
    928. 

  928. - create_ts (timestamp) - 创建时间 [示例: 2023-01-10 10:54:03, 2023-01-17 12:47:29]
    929. 

  929. - created_by (varchar(50)) - 创建人 [示例: admin]
    930. 

  930. - update_ts (timestamp) - 更新时间 [示例: 2023-01-10 10:54:07, 2023-01-17 12:47:32]
    931. 

  931. - updated_by (varchar(50)) - 更新人
    932. 

  932. - delete_ts (timestamp) - 删除时间
    933. 

  933. - deleted_by (varchar(50)) - 删除人
    934. 

  934. - service_name (varchar(255)) - 服务区名称 [示例: 信丰西服务区, 南康北服务区]
    935. 

  935. - service_no (varchar(255)) - 服务区编码 [示例: 1067, 1062]
    936. 

  936. - service_area_id (varchar(32)) - 服务区业务ID [示例: 97cd6cd516a551409a4d453a58f9e170, fdbdd042962011ed8ee6fa163eaf653f]
    937. 

  937. - source_system_type (varchar(50)) - 数据来源系统 [示例: 驿美, 驿购]
    938. 

  938. - source_type (integer) - 来源系统类型ID [示例: 3, 1]
    939. 

  939. 字段补充说明：
    940. 

  940. - id 为主键
    941. 

  941. - source_system_type 为枚举字段，包含取值：司乘管理、商业管理、驿购、驿美、手工录入
    942. 

  942. - source_type 为枚举字段，包含取值：5、0、1、3、4
    943. 

  943. 

  944. ## bss_service_area（高速公路服务区基础信息表）
    945. 

  945. bss_service_area 表高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
    946. 

  946. 字段列表：
    947. 

  947. - id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
    948. 

  948. - version (integer) - 数据版本号 [非空] [示例: 3, 6]
    949. 

  949. - create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
    950. 

  950. - created_by (varchar(50)) - 创建人 [示例: admin]
    951. 

  951. - update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
    952. 

  952. - updated_by (varchar(50)) - 更新人 [示例: admin]
    953. 

  953. - delete_ts (timestamp) - 删除时间
    954. 

  954. - deleted_by (varchar(50)) - 删除人 [示例: ]
    955. 

  955. - service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
    956. 

  956. - service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
    957. 

  957. - company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
    958. 

  958. - service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
    959. 

  959. - service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
    960. 

  960. - service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
    961. 

  961. 字段补充说明：
    962. 

  962. - id 为主键
    963. 

  963. - service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
    964. 

  964. - service_state 为枚举字段，包含取值：开放、关闭、上传数据
    965. 

  965. 

  966. ## bss_section_route_area_link（高速公路路线与服务区关联表）
    967. 

  967. bss_section_route_area_link 表高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
    968. 

  968. 字段列表：
    969. 

  969. - section_route_id (varchar(32)) - 路段路线唯一标识 [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
    970. 

  970. - service_area_id (varchar(32)) - 服务区唯一标识 [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
    971. 

  971. 字段补充说明：
    972. 

  972. - 复合主键：section_route_id, service_area_id
    973. 

  973. 

  974. ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
    975. 

  975. bss_car_day_count 表高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
    976. 

  976. 字段列表：
    977. 

  977. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 00022c1c99ff11ec86d4fa163ec0f8fc, 00022caa99ff11ec86d4fa163ec0f8fc]
    978. 

  978. - version (integer) - 数据版本号 [非空] [示例: 1]
    979. 

  979. - create_ts (timestamp) - 创建时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
    980. 

  980. - created_by (varchar(50)) - 创建人
    981. 

  981. - update_ts (timestamp) - 更新时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
    982. 

  982. - updated_by (varchar(50)) - 更新人
    983. 

  983. - delete_ts (timestamp) - 删除时间
    984. 

  984. - deleted_by (varchar(50)) - 删除人
    985. 

  985. - customer_count (bigint) - 车辆数量 [示例: 1114, 295]
    986. 

  986. - car_type (varchar(100)) - 车辆类别 [示例: 其他]
    987. 

  987. - count_date (date) - 统计日期 [示例: 2022-03-02, 2022-02-02]
    988. 

  988. - service_area_id (varchar(32)) - 服务区ID [示例: 17461166e7fa3ecda03534a5795ce985, 81f4eb731fb0728aef17ae61f1f1daef]
    989. 

  989. 字段补充说明：
    990. 

  990. - id 为主键
    991. 

  991. - car_type 为枚举字段，包含取值：其他、危化品、城际、过境
    992. 

  992. 

  993. ## bss_section_route（路段路线信息表）
    994. 

  994. bss_section_route 表路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
    995. 

  995. 字段列表：
    996. 

  996. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 04ri3j67a806uw2c6o6dwdtz4knexczh, 0g5mnefxxtukql2cq6acul7phgskowy7]
    997. 

  997. - version (integer) - 数据版本号 [非空] [示例: 1, 0]
    998. 

  998. - create_ts (timestamp) - 创建时间 [示例: 2021-10-29 19:43:50, 2022-03-04 16:07:16]
    999. 

  999. - created_by (varchar(50)) - 创建人 [示例: admin]
    1000. 

  1000. - update_ts (timestamp) - 更新时间
    1001. 

  1001. - updated_by (varchar(50)) - 更新人
    1002. 

  1002. - delete_ts (timestamp) - 删除时间
    1003. 

  1003. - deleted_by (varchar(50)) - 删除人
    1004. 

  1004. - section_name (varchar(255)) - 路段名称 [示例: 昌栗, 昌宁]
    1005. 

  1005. - route_name (varchar(255)) - 路线名称 [示例: 昌栗, 昌韶]
    1006. 

  1006. - code (varchar(255)) - 路段编号 [示例: SR0001, SR0002]
    1007. 

  1007. 字段补充说明：
    1008. 

  1008. - id 为主键
    1009. 

  1009. - created_by 为枚举字段，包含取值：admin
    1010. 

  1010. 

  1011. ===Response Guidelines 
    1012. 

  1012. **IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
    1013. 

  1013. 

  1014. 1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
    1015. 

  1015. 2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
    1016. 

  1016. 3. If the provided context is insufficient, please explain why it can't be generated. 
    1017. 

  1017. 4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
    1018. 

  1018.    - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
    1019. 

  1019.      interpret it as 'How many dining stalls does Nancheng Service Area have?'
    1020. 

  1020. 5. Please use the most relevant table(s). 
    1021. 

  1021. 6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
    1022. 

  1022. 7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
    1023. 

  1023. 8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
    1024. 

  1024. 9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
    1025. 

  1025.    - Every column MUST use AS with a Chinese alias
    1026. 

  1026.    - Raw column names without aliases are NOT acceptable
    1027. 

  1027.    - Examples: 
    1028. 

  1028.      * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
    1029. 

  1029.      * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
    1030. 

  1030.      * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
    1031. 

  1031.    - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
    1032. 

  1032. 

  1033. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1034. 

  1034. user_content: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。
    1035. 

  1035. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sr.route_name AS 路线名称, COUNT(DISTINCT link.service_area_id) AS 服务区数量 FROM bss_section_route sr JOIN bss_section_route_area_link link ON sr.id = link.section_route_id WHERE sr.delete_ts IS NULL GROUP BY sr.route_name ORDER BY 服务区数量 DESC;
    1036. 

  1036. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1037. 

  1037. user_content: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？
    1038. 

  1038. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT branch_name AS 档口名称, ROUND(SUM(pay_sum)::numeric, 2) AS 收入总额 FROM bss_business_day_data WHERE service_name = '庐山服务区' AND oper_date BETWEEN '2023-04-01' AND '2023-04-30' AND delete_ts IS NULL GROUP BY branch_name ORDER BY 收入总额 DESC LIMIT 3;
    1039. 

  1039. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1040. 

  1040. user_content: 最近一周哪个服务区总车流量最高？取前5名。
    1041. 

  1041. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name AS 服务区名称, SUM(c.customer_count) AS 总车流量 FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - 7 AND c.delete_ts IS NULL AND s.delete_ts IS NULL GROUP BY s.service_area_name ORDER BY 总车流量 DESC LIMIT 5;
    1042. 

  1042. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1043. 

  1043. user_content: Previous conversation context:
    1044. 

  1044. human: 请问系统中哪个服务区档口最多？
    1045. 

  1045. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    1046. 

  1046. 

  1047. Current user question:
    1048. 

  1048. human: 请问这个服务区有几个餐饮档口？
    1049. 

  1049. 

  1050. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    1051. 

  1051. 2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': "You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
    1052. 

  1052. 2025-07-22 20:54:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
    1053. 

  1053. Using model qwen-plus-latest for 3195.75 tokens (approx)
    1054. 

  1054. 2025-07-22 20:54:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
    1055. 

  1055. 2025-07-22 20:54:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
    1056. 

  1056. 2025-07-22 20:54:23 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT 
    1057. 

  1057.     service_name AS 服务区名称,
    1058. 

  1058.     COUNT(*) AS 餐饮档口数量
    1059. 

  1059. FROM 
    1060. 

  1060.     bss_business_day_data
    1061. 

  1061. WHERE 
    1062. 

  1062.     service_name = '南城服务区'
    1063. 

  1063.     AND branch_name LIKE '%餐饮%'
    1064. 

  1064.     AND delete_ts IS NULL
    1065. 

  1065. GROUP BY 
    1066. 

  1066.     serv...
    1067. 

  1067. 2025-07-22 20:54:23 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT 
    1068. 

  1068.     service_name AS 服务区名称,
    1069. 

  1069.     COUNT(*) AS 餐饮档口数量
    1070. 

  1070. FROM 
    1071. 

  1071.     bss_business_day_data
    1072. 

  1072. WHERE 
    1073. 

  1073.     service_name = '南城服务区'
    1074. 

  1074.     AND branch_name LIKE '%餐饮%'
    1075. 

  1075.     AND delete_ts IS NULL
    1076. 

  1076. GROUP BY 
    1077. 

  1077.     service_name;
    1078. 

  1078. 2025-07-22 20:54:23 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
    1079. 

  1079.  SELECT 
    1080. 

  1080.     service_name AS 服务区名称,
    1081. 

  1081.     COUNT(*) AS 餐饮档口数量
    1082. 

  1082. FROM 
    1083. 

  1083.     bss_business_day_data
    1084. 

  1084. WHERE 
    1085. 

  1085.     service_name = '南城服务区'
    1086. 

  1086.     AND branch_name LIKE '%餐饮%'
    1087. 

  1087.     AND delete_ts IS NULL
    1088. 

  1088. GROUP BY 
    1089. 

  1089.     service_name;
    1090. 

  1090. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: Previous conversation context:
    1091. 

  1091. human: 请问系统中哪个服务区档口最多？
    1092. 

  1092. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    1093. 

  1093. 

  1094. Current user question:
    1095. 

  1095. human: 请问这个服务区有几个餐饮档口？
    1096. 

  1096. 

  1097. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    1098. 

  1098. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。 | similarity: 0.6985
    1099. 

  1099. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？ | similarity: 0.6528
    1100. 

  1100. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近一周哪个服务区总车流量最高？取前5名。 | similarity: 0.6383
    1101. 

  1101. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月1日各服务区总收入排名前5的明细（包含订单总数）？ | similarity: 0.636
    1102. 

  1102. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 找出2023年4月平均每日订单数最高的服务区TOP3？ | similarity: 0.6116
    1103. 

  1103. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 计算每个服务区的“状态影响指数”=日均营收 × 平均车流量，并按此指数排序TOP 10？ | similarity: 0.6106
    1104. 

  1104. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
    1105. 

  1105. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - SQL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 2, 强制保留: 1)
    1106. 

  1106. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.6985 ✓
    1107. 

  1107. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.6528 ✓
    1108. 

  1108. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.6383 ✗
    1109. 

  1109. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日经营数据统计表
    1110. 

  1110. -- 描述: 高速公路服务区每日经营数据统计表，记... | similarity: 0.6253
    1111. 

  1111. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路路线与服务区关联表
    1112. 

  1112. -- 描述: 高速公路路线与服务区关联表，用于管理各路段... | similarity: 0.5987
    1113. 

  1113. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区基础信息表
    1114. 

  1114. -- 描述: 高速公路服务区基础信息表，存储服务区名称、编... | similarity: 0.5917
    1115. 

  1115. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区信息映射表
    1116. 

  1116. -- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与... | similarity: 0.574
    1117. 

  1117. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线信息表
    1118. 

  1118. -- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速... | similarity: 0.5615
    1119. 

  1119. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日车辆流量统计表
    1120. 

  1120. -- 描述: 高速公路服务区每日车辆流量统计表，记... | similarity: 0.5517
    1121. 

  1121. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
    1122. 

  1122. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
    1123. 

  1123. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.6253 ✓
    1124. 

  1124. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.5987 ✓
    1125. 

  1125. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.5917 ✓
    1126. 

  1126. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.574 ✓
    1127. 

  1127. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.5615 ✓
    1128. 

  1128. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 6: similarity=0.5517 ✓
    1129. 

  1129. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_business_day_data（高速公路服务区每日经营数据统计表）
    1130. 

  1130. bss_bus... | similarity: 0.6161
    1131. 

  1131. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area_mapper（服务区信息映射表）
    1132. 

  1132. bss_service_a... | similarity: 0.6125
    1133. 

  1133. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（高速公路服务区基础信息表）
    1134. 

  1134. bss_service_area... | similarity: 0.6007
    1135. 

  1135. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（高速公路路线与服务区关联表）
    1136. 

  1136. bss_... | similarity: 0.5907
    1137. 

  1137. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
    1138. 

  1138. bss_car_day... | similarity: 0.5816
    1139. 

  1139. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route（路段路线信息表）
    1140. 

  1140. bss_section_route 表路... | similarity: 0.5589
    1141. 

  1141. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
    1142. 

  1142. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
    1143. 

  1143. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.6161 ✓
    1144. 

  1144. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.6125 ✓
    1145. 

  1145. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.6007 ✓
    1146. 

  1146. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.5907 ✓
    1147. 

  1147. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.5816 ✓
    1148. 

  1148. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.5589 ✓
    1149. 

  1149. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: Previous conversation context:
    1150. 

  1150. human: 请问系统中哪个服务区档口最多？
    1151. 

  1151. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    1152. 

  1152. 

  1153. Current user question:
    1154. 

  1154. human: 请问这个服务区有几个餐饮档口？
    1155. 

  1155. 

  1156. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    1157. 

  1157. 2025-07-22 20:54:40 [WARNING] [vanna.BaseLLMChat] pgvector.py:666 - 向量查询未找到任何相关的错误SQL示例，问题: Previous conversation context:
    1158. 

  1158. human: 请问系统中哪个服务区档口最多？
    1159. 

  1159. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    1160. 

  1160. 

  1161. Current user question:
    1162. 

  1162. human: 请问这个服务区有几个餐饮档口？
    1163. 

  1163. 

  1164. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    1165. 

  1165. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
    1166. 

  1166. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
    1167. 

  1167. Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
    1168. 

  1168. 

  1169. ===Tables 
    1170. 

  1170. -- 中文名: 高速公路服务区每日经营数据统计表
    1171. 

  1171. -- 描述: 高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
    1172. 

  1172. create table public.bss_business_day_data (
    1173. 

  1173.   id varchar(32) not null     -- 主键ID，主键,
    1174. 

  1174.   version integer not null    -- 数据版本号,
    1175. 

  1175.   create_ts timestamp         -- 创建时间,
    1176. 

  1176.   created_by varchar(50)      -- 创建人,
    1177. 

  1177.   update_ts timestamp         -- 更新时间,
    1178. 

  1178.   updated_by varchar(50)      -- 更新人,
    1179. 

  1179.   delete_ts timestamp         -- 删除时间,
    1180. 

  1180.   deleted_by varchar(50)      -- 删除人,
    1181. 

  1181.   oper_date date              -- 统计日期,
    1182. 

  1182.   service_no varchar(255)     -- 服务区编码,
    1183. 

  1183.   service_name varchar(255)   -- 服务区名称,
    1184. 

  1184.   branch_no varchar(255)      -- 档口编码,
    1185. 

  1185.   branch_name varchar(255)    -- 档口名称,
    1186. 

  1186.   wx numeric(19,4)            -- 微信支付金额,
    1187. 

  1187.   wx_order integer            -- 微信订单数量,
    1188. 

  1188.   zfb numeric(19,4)           -- 支付宝支付金额,
    1189. 

  1189.   zf_order integer            -- 支付宝订单数量,
    1190. 

  1190.   rmb numeric(19,4)           -- 现金支付金额,
    1191. 

  1191.   rmb_order integer           -- 现金订单数量,
    1192. 

  1192.   xs numeric(19,4)            -- 行吧支付金额,
    1193. 

  1193.   xs_order integer            -- 行吧支付订单数,
    1194. 

  1194.   jd numeric(19,4)            -- 金豆支付金额,
    1195. 

  1195.   jd_order integer            -- 金豆支付订单数,
    1196. 

  1196.   order_sum integer           -- 订单总数,
    1197. 

  1197.   pay_sum numeric(19,4)       -- 总支付金额,
    1198. 

  1198.   source_type integer         -- 数据来源类型,
    1199. 

  1199.   primary key (id)
    1200. 

  1200. )
    1201. 

  1201. 

  1202. -- 中文名: 高速公路路线与服务区关联表
    1203. 

  1203. -- 描述: 高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
    1204. 

  1204. create table public.bss_section_route_area_link (
    1205. 

  1205.   section_route_id varchar(32) not null -- 路段路线唯一标识，主键,
    1206. 

  1206.   service_area_id varchar(32) not null -- 服务区唯一标识，主键,
    1207. 

  1207.   primary key (section_route_id, service_area_id)
    1208. 

  1208. )
    1209. 

  1209. 

  1210. -- 中文名: 高速公路服务区基础信息表
    1211. 

  1211. -- 描述: 高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
    1212. 

  1212. create table public.bss_service_area (
    1213. 

  1213.   id varchar(32) not null     -- 唯一标识符，主键,
    1214. 

  1214.   version integer not null    -- 数据版本号,
    1215. 

  1215.   create_ts timestamp         -- 创建时间,
    1216. 

  1216.   created_by varchar(50)      -- 创建人,
    1217. 

  1217.   update_ts timestamp         -- 更新时间,
    1218. 

  1218.   updated_by varchar(50)      -- 更新人,
    1219. 

  1219.   delete_ts timestamp         -- 删除时间,
    1220. 

  1220.   deleted_by varchar(50)      -- 删除人,
    1221. 

  1221.   service_area_name varchar(255) -- 服务区名称,
    1222. 

  1222.   service_area_no varchar(255) -- 服务区编码,
    1223. 

  1223.   company_id varchar(32)      -- 所属公司ID,
    1224. 

  1224.   service_position varchar(255) -- 经纬度坐标,
    1225. 

  1225.   service_area_type varchar(50) -- 服务区类型,
    1226. 

  1226.   service_state varchar(50)   -- 运营状态,
    1227. 

  1227.   primary key (id)
    1228. 

  1228. )
    1229. 

  1229. 

  1230. -- 中文名: 服务区信息映射表
    1231. 

  1231. -- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
    1232. 

  1232. create table public.bss_service_area_mapper (
    1233. 

  1233.   id varchar(32) not null     -- 唯一标识符，主键,
    1234. 

  1234.   version integer not null    -- 数据版本号,
    1235. 

  1235.   create_ts timestamp         -- 创建时间,
    1236. 

  1236.   created_by varchar(50)      -- 创建人,
    1237. 

  1237.   update_ts timestamp         -- 更新时间,
    1238. 

  1238.   updated_by varchar(50)      -- 更新人,
    1239. 

  1239.   delete_ts timestamp         -- 删除时间,
    1240. 

  1240.   deleted_by varchar(50)      -- 删除人,
    1241. 

  1241.   service_name varchar(255)   -- 服务区名称,
    1242. 

  1242.   service_no varchar(255)     -- 服务区编码,
    1243. 

  1243.   service_area_id varchar(32) -- 服务区业务ID,
    1244. 

  1244.   source_system_type varchar(50) -- 数据来源系统,
    1245. 

  1245.   source_type integer         -- 来源系统类型ID,
    1246. 

  1246.   primary key (id)
    1247. 

  1247. )
    1248. 

  1248. 

  1249. -- 中文名: 路段路线信息表
    1250. 

  1250. -- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
    1251. 

  1251. create table public.bss_section_route (
    1252. 

  1252.   id varchar(32) not null     -- 主键ID，主键,
    1253. 

  1253.   version integer not null    -- 数据版本号,
    1254. 

  1254.   create_ts timestamp         -- 创建时间,
    1255. 

  1255.   created_by varchar(50)      -- 创建人,
    1256. 

  1256.   update_ts timestamp         -- 更新时间,
    1257. 

  1257.   updated_by varchar(50)      -- 更新人,
    1258. 

  1258.   delete_ts timestamp         -- 删除时间,
    1259. 

  1259.   deleted_by varchar(50)      -- 删除人,
    1260. 

  1260.   section_name varchar(255)   -- 路段名称,
    1261. 

  1261.   route_name varchar(255)     -- 路线名称,
    1262. 

  1262.   code varchar(255)           -- 路段编号,
    1263. 

  1263.   primary key (id)
    1264. 

  1264. )
    1265. 

  1265. 

  1266. -- 中文名: 高速公路服务区每日车辆流量统计表
    1267. 

  1267. -- 描述: 高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
    1268. 

  1268. create table public.bss_car_day_count (
    1269. 

  1269.   id varchar(32) not null     -- 主键ID，主键,
    1270. 

  1270.   version integer not null    -- 数据版本号,
    1271. 

  1271.   create_ts timestamp         -- 创建时间,
    1272. 

  1272.   created_by varchar(50)      -- 创建人,
    1273. 

  1273.   update_ts timestamp         -- 更新时间,
    1274. 

  1274.   updated_by varchar(50)      -- 更新人,
    1275. 

  1275.   delete_ts timestamp         -- 删除时间,
    1276. 

  1276.   deleted_by varchar(50)      -- 删除人,
    1277. 

  1277.   customer_count bigint       -- 车辆数量,
    1278. 

  1278.   car_type varchar(100)       -- 车辆类别,
    1279. 

  1279.   count_date date             -- 统计日期,
    1280. 

  1280.   service_area_id varchar(32) -- 服务区ID,
    1281. 

  1281.   primary key (id)
    1282. 

  1282. )
    1283. 

  1283. 

  1284. 

  1285. ===Additional Context 
    1286. 

  1286. 

  1287. ## bss_business_day_data（高速公路服务区每日经营数据统计表）
    1288. 

  1288. bss_business_day_data 表高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
    1289. 

  1289. 字段列表：
    1290. 

  1290. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 00827DFF993D415488EA1F07CAE6C440, 00e799048b8cbb8ee758eac9c8b4b820]
    1291. 

  1291. - version (integer) - 数据版本号 [非空] [示例: 1]
    1292. 

  1292. - create_ts (timestamp) - 创建时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
    1293. 

  1293. - created_by (varchar(50)) - 创建人 [示例: xingba]
    1294. 

  1294. - update_ts (timestamp) - 更新时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
    1295. 

  1295. - updated_by (varchar(50)) - 更新人
    1296. 

  1296. - delete_ts (timestamp) - 删除时间
    1297. 

  1297. - deleted_by (varchar(50)) - 删除人
    1298. 

  1298. - oper_date (date) - 统计日期 [示例: 2023-04-01]
    1299. 

  1299. - service_no (varchar(255)) - 服务区编码 [示例: 1028, H0501]
    1300. 

  1300. - service_name (varchar(255)) - 服务区名称 [示例: 宜春服务区, 庐山服务区]
    1301. 

  1301. - branch_no (varchar(255)) - 档口编码 [示例: 1, H05016]
    1302. 

  1302. - branch_name (varchar(255)) - 档口名称 [示例: 宜春南区, 庐山鲜徕客东区]
    1303. 

  1303. - wx (numeric(19,4)) - 微信支付金额 [示例: 4790.0000, 2523.0000]
    1304. 

  1304. - wx_order (integer) - 微信订单数量 [示例: 253, 133]
    1305. 

  1305. - zfb (numeric(19,4)) - 支付宝支付金额 [示例: 229.0000, 0.0000]
    1306. 

  1306. - zf_order (integer) - 支付宝订单数量 [示例: 15, 0]
    1307. 

  1307. - rmb (numeric(19,4)) - 现金支付金额 [示例: 1058.5000, 124.0000]
    1308. 

  1308. - rmb_order (integer) - 现金订单数量 [示例: 56, 12]
    1309. 

  1309. - xs (numeric(19,4)) - 行吧支付金额 [示例: 0.0000, 40.0000]
    1310. 

  1310. - xs_order (integer) - 行吧支付订单数 [示例: 0, 1]
    1311. 

  1311. - jd (numeric(19,4)) - 金豆支付金额 [示例: 0.0000]
    1312. 

  1312. - jd_order (integer) - 金豆支付订单数 [示例: 0]
    1313. 

  1313. - order_sum (integer) - 订单总数 [示例: 324, 146]
    1314. 

  1314. - pay_sum (numeric(19,4)) - 总支付金额 [示例: 6077.5000, 2687.0000]
    1315. 

  1315. - source_type (integer) - 数据来源类型 [示例: 1, 0, 4]
    1316. 

  1316. 字段补充说明：
    1317. 

  1317. - id 为主键
    1318. 

  1318. - source_type 为枚举字段，包含取值：0、4、1、2、3
    1319. 

  1319. 

  1320. ## bss_service_area_mapper（服务区信息映射表）
    1321. 

  1321. bss_service_area_mapper 表服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
    1322. 

  1322. 字段列表：
    1323. 

  1323. - id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 00e1e893909211ed8ee6fa163eaf653f, 013867f5962211ed8ee6fa163eaf653f]
    1324. 

  1324. - version (integer) - 数据版本号 [非空] [示例: 1]
    1325. 

  1325. - create_ts (timestamp) - 创建时间 [示例: 2023-01-10 10:54:03, 2023-01-17 12:47:29]
    1326. 

  1326. - created_by (varchar(50)) - 创建人 [示例: admin]
    1327. 

  1327. - update_ts (timestamp) - 更新时间 [示例: 2023-01-10 10:54:07, 2023-01-17 12:47:32]
    1328. 

  1328. - updated_by (varchar(50)) - 更新人
    1329. 

  1329. - delete_ts (timestamp) - 删除时间
    1330. 

  1330. - deleted_by (varchar(50)) - 删除人
    1331. 

  1331. - service_name (varchar(255)) - 服务区名称 [示例: 信丰西服务区, 南康北服务区]
    1332. 

  1332. - service_no (varchar(255)) - 服务区编码 [示例: 1067, 1062]
    1333. 

  1333. - service_area_id (varchar(32)) - 服务区业务ID [示例: 97cd6cd516a551409a4d453a58f9e170, fdbdd042962011ed8ee6fa163eaf653f]
    1334. 

  1334. - source_system_type (varchar(50)) - 数据来源系统 [示例: 驿美, 驿购]
    1335. 

  1335. - source_type (integer) - 来源系统类型ID [示例: 3, 1]
    1336. 

  1336. 字段补充说明：
    1337. 

  1337. - id 为主键
    1338. 

  1338. - source_system_type 为枚举字段，包含取值：司乘管理、商业管理、驿购、驿美、手工录入
    1339. 

  1339. - source_type 为枚举字段，包含取值：5、0、1、3、4
    1340. 

  1340. 

  1341. ## bss_service_area（高速公路服务区基础信息表）
    1342. 

  1342. bss_service_area 表高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
    1343. 

  1343. 字段列表：
    1344. 

  1344. - id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
    1345. 

  1345. - version (integer) - 数据版本号 [非空] [示例: 3, 6]
    1346. 

  1346. - create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
    1347. 

  1347. - created_by (varchar(50)) - 创建人 [示例: admin]
    1348. 

  1348. - update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
    1349. 

  1349. - updated_by (varchar(50)) - 更新人 [示例: admin]
    1350. 

  1350. - delete_ts (timestamp) - 删除时间
    1351. 

  1351. - deleted_by (varchar(50)) - 删除人 [示例: ]
    1352. 

  1352. - service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
    1353. 

  1353. - service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
    1354. 

  1354. - company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
    1355. 

  1355. - service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
    1356. 

  1356. - service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
    1357. 

  1357. - service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
    1358. 

  1358. 字段补充说明：
    1359. 

  1359. - id 为主键
    1360. 

  1360. - service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
    1361. 

  1361. - service_state 为枚举字段，包含取值：开放、关闭、上传数据
    1362. 

  1362. 

  1363. ## bss_section_route_area_link（高速公路路线与服务区关联表）
    1364. 

  1364. bss_section_route_area_link 表高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
    1365. 

  1365. 字段列表：
    1366. 

  1366. - section_route_id (varchar(32)) - 路段路线唯一标识 [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
    1367. 

  1367. - service_area_id (varchar(32)) - 服务区唯一标识 [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
    1368. 

  1368. 字段补充说明：
    1369. 

  1369. - 复合主键：section_route_id, service_area_id
    1370. 

  1370. 

  1371. ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
    1372. 

  1372. bss_car_day_count 表高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
    1373. 

  1373. 字段列表：
    1374. 

  1374. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 00022c1c99ff11ec86d4fa163ec0f8fc, 00022caa99ff11ec86d4fa163ec0f8fc]
    1375. 

  1375. - version (integer) - 数据版本号 [非空] [示例: 1]
    1376. 

  1376. - create_ts (timestamp) - 创建时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
    1377. 

  1377. - created_by (varchar(50)) - 创建人
    1378. 

  1378. - update_ts (timestamp) - 更新时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
    1379. 

  1379. - updated_by (varchar(50)) - 更新人
    1380. 

  1380. - delete_ts (timestamp) - 删除时间
    1381. 

  1381. - deleted_by (varchar(50)) - 删除人
    1382. 

  1382. - customer_count (bigint) - 车辆数量 [示例: 1114, 295]
    1383. 

  1383. - car_type (varchar(100)) - 车辆类别 [示例: 其他]
    1384. 

  1384. - count_date (date) - 统计日期 [示例: 2022-03-02, 2022-02-02]
    1385. 

  1385. - service_area_id (varchar(32)) - 服务区ID [示例: 17461166e7fa3ecda03534a5795ce985, 81f4eb731fb0728aef17ae61f1f1daef]
    1386. 

  1386. 字段补充说明：
    1387. 

  1387. - id 为主键
    1388. 

  1388. - car_type 为枚举字段，包含取值：其他、危化品、城际、过境
    1389. 

  1389. 

  1390. ## bss_section_route（路段路线信息表）
    1391. 

  1391. bss_section_route 表路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
    1392. 

  1392. 字段列表：
    1393. 

  1393. - id (varchar(32)) - 主键ID [主键, 非空] [示例: 04ri3j67a806uw2c6o6dwdtz4knexczh, 0g5mnefxxtukql2cq6acul7phgskowy7]
    1394. 

  1394. - version (integer) - 数据版本号 [非空] [示例: 1, 0]
    1395. 

  1395. - create_ts (timestamp) - 创建时间 [示例: 2021-10-29 19:43:50, 2022-03-04 16:07:16]
    1396. 

  1396. - created_by (varchar(50)) - 创建人 [示例: admin]
    1397. 

  1397. - update_ts (timestamp) - 更新时间
    1398. 

  1398. - updated_by (varchar(50)) - 更新人
    1399. 

  1399. - delete_ts (timestamp) - 删除时间
    1400. 

  1400. - deleted_by (varchar(50)) - 删除人
    1401. 

  1401. - section_name (varchar(255)) - 路段名称 [示例: 昌栗, 昌宁]
    1402. 

  1402. - route_name (varchar(255)) - 路线名称 [示例: 昌栗, 昌韶]
    1403. 

  1403. - code (varchar(255)) - 路段编号 [示例: SR0001, SR0002]
    1404. 

  1404. 字段补充说明：
    1405. 

  1405. - id 为主键
    1406. 

  1406. - created_by 为枚举字段，包含取值：admin
    1407. 

  1407. 

  1408. ===Response Guidelines 
    1409. 

  1409. **IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
    1410. 

  1410. 

  1411. 1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
    1412. 

  1412. 2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
    1413. 

  1413. 3. If the provided context is insufficient, please explain why it can't be generated. 
    1414. 

  1414. 4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
    1415. 

  1415.    - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
    1416. 

  1416.      interpret it as 'How many dining stalls does Nancheng Service Area have?'
    1417. 

  1417. 5. Please use the most relevant table(s). 
    1418. 

  1418. 6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
    1419. 

  1419. 7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
    1420. 

  1420. 8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
    1421. 

  1421. 9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
    1422. 

  1422.    - Every column MUST use AS with a Chinese alias
    1423. 

  1423.    - Raw column names without aliases are NOT acceptable
    1424. 

  1424.    - Examples: 
    1425. 

  1425.      * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
    1426. 

  1426.      * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
    1427. 

  1427.      * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
    1428. 

  1428.    - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
    1429. 

  1429. 

  1430. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1431. 

  1431. user_content: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。
    1432. 

  1432. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sr.route_name AS 路线名称, COUNT(DISTINCT link.service_area_id) AS 服务区数量 FROM bss_section_route sr JOIN bss_section_route_area_link link ON sr.id = link.section_route_id WHERE sr.delete_ts IS NULL GROUP BY sr.route_name ORDER BY 服务区数量 DESC;
    1433. 

  1433. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1434. 

  1434. user_content: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？
    1435. 

  1435. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT branch_name AS 档口名称, ROUND(SUM(pay_sum)::numeric, 2) AS 收入总额 FROM bss_business_day_data WHERE service_name = '庐山服务区' AND oper_date BETWEEN '2023-04-01' AND '2023-04-30' AND delete_ts IS NULL GROUP BY branch_name ORDER BY 收入总额 DESC LIMIT 3;
    1436. 

  1436. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1437. 

  1437. user_content: 最近一周哪个服务区总车流量最高？取前5名。
    1438. 

  1438. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name AS 服务区名称, SUM(c.customer_count) AS 总车流量 FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - 7 AND c.delete_ts IS NULL AND s.delete_ts IS NULL GROUP BY s.service_area_name ORDER BY 总车流量 DESC LIMIT 5;
    1439. 

  1439. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
    1440. 

  1440. user_content: Previous conversation context:
    1441. 

  1441. human: 请问系统中哪个服务区档口最多？
    1442. 

  1442. ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
    1443. 

  1443. 

  1444. Current user question:
    1445. 

  1445. human: 请问这个服务区有几个餐饮档口？
    1446. 

  1446. 

  1447. Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
    1448. 

  1448. 2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': "You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
    1449. 

  1449. 2025-07-22 20:54:40 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
    1450. 

  1450. Using model qwen-plus-latest for 3195.75 tokens (approx)
    1451. 

  1451. 2025-07-22 20:54:40 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
    1452. 

  1452. 2025-07-22 20:54:40 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
    1453. 

  1453. 2025-07-22 20:54:48 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT 
    1454. 

  1454.     service_name AS 服务区名称,
    1455. 

  1455.     COUNT(*) AS 餐饮档口数量
    1456. 

  1456. FROM 
    1457. 

  1457.     bss_business_day_data
    1458. 

  1458. WHERE 
    1459. 

  1459.     service_name = '南城服务区'
    1460. 

  1460.     AND branch_name LIKE '%餐饮%'
    1461. 

  1461.     AND delete_ts IS NULL
    1462. 

  1462. GROUP BY 
    1463. 

  1463.     serv...
    1464. 

  1464. 2025-07-22 20:54:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT 
    1465. 

  1465.     service_name AS 服务区名称,
    1466. 

  1466.     COUNT(*) AS 餐饮档口数量
    1467. 

  1467. FROM 
    1468. 

  1468.     bss_business_day_data
    1469. 

  1469. WHERE 
    1470. 

  1470.     service_name = '南城服务区'
    1471. 

  1471.     AND branch_name LIKE '%餐饮%'
    1472. 

  1472.     AND delete_ts IS NULL
    1473. 

  1473. GROUP BY 
    1474. 

  1474.     service_name;
    1475. 

  1475. 2025-07-22 20:54:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
    1476. 

  1476.  SELECT 
    1477. 

  1477.     service_name AS 服务区名称,
    1478. 

  1478.     COUNT(*) AS 餐饮档口数量
    1479. 

  1479. FROM 
    1480. 

  1480.     bss_business_day_data
    1481. 

  1481. WHERE 
    1482. 

  1482.     service_name = '南城服务区'
    1483. 

  1483.     AND branch_name LIKE '%餐饮%'
    1484. 

  1484.     AND delete_ts IS NULL
    1485. 

  1485. GROUP BY 
    1486. 

  1486.     service_name;
    1487.