element.chen/ai-g3sb-backman2.0
1
0
Fork 0
Code Pull Requests Activity
Files
70c8e90f2eaefc3584994de04ed7d8ec2e3eaa22
ai-g3sb-backman2.0/__pycache__/api_server.cpython-312.pyc
T

308 lines
52 KiB
Plaintext
Raw Normal View History

0.1.1 暂存
2026-04-14 10:28:22 +08:00
Ë
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
†àisŸãóî
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
—dZddlmZddlZddlZddlZddlZddlZddlm Z ddl
m Z m Z m
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Z
0.1.1 暂存
2026-04-14 10:28:22 +08:00
mZmZddlmZddlmZmZmZm ZddlmZdd lmZmZdd
lmZmZmZm Z dd l!m"Z"e e#«jI«jJZ&e&d z Z'e(e'«ejRvr"ejRjUde(e'««dd
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
l+m,Z,e,e&«ddl-m.Z.m/Z/m0Z0m1Z1ddl2m3Z3ddl4m5Z5ddl6m7Z7m8Z8ddl9m:Z:m;Z;m<Z<ejze>«Z?ej€«ZAd~d„ZBeB«ZCeCj‰«re"eC«e?j‹deC›�«ne?j�deC›�«daGdaHd„ZIGd„de«ZJGd„de«ZKGd„de«ZLGd„de«ZMGd„d e«ZNGd!„d"e«ZOGd#„d$e«ZPGd%„d&e«ZQGd'„d(e«ZRGd)„d*e«ZSGd+„d,e«ZTdd-„ZUeVej®d.d/««ZXdd0œ d€d1„ZYd�d2„ZZd‚d3„Z[dƒd4„Z\d„d5„Z]d…d6„Z^d†d7„Z_d†d8„Z`d‡d9„Zad‡d:„Zbd‡d;„Zc dˆd<„Zded‰d=„«Ze dŠd>„Zfd‹d?„ZgdŒd@„Zh d� dŽdA„Zid�dB„Zjed�dC„«ZkedDdEdFek¬G«ZleljÛedHgdIdHgdHg¬J«eljÝdK«dL„«ZoeljádM«d‰dN„«ZqeljádO«d‰dP„«ZreljádQ«d‘dR„«ZseljÝdQ« d’ d“dS„«ZteljÝdT«edUdV¬W«dddXdf d”dY„«ZueljídZ«d•d[„«Zweljíd\« d–d]„«Zxeljód^« d— d˜d_„«Zzeljád`«d™da„«Z{eljádb«edU«fdšdc„«Z|eljÝdb« d› dœdd„«Z}eljÝde« d— d�df„«Z~eljáde«dždg„«Zeljídh«ee€¬i«ddf dŸdj„«Z�eljódh« d— d dk„«Z‚eljÝdl« d¡ d¢dm„«Zƒeljádn«do„«Z„eljÝdp«dq„«Z…e>drk(r�ddl†Z†ddl‡Z‡eVej®dsdt««Zˆej®dudv«Z‰e?j‹dwe‰›dxeˆ›�«e?j‹dye‰›dxeˆ›dz�«e‡�j«e†�jele‰eˆd{d|d¬}«yy)£uo
加入日志管理
2026-04-16 10:53:10 +08:00
FastAPI �务入� - Text2SQL NL Chat API
包装 Text2SQLOrchestrator 为 REST API �务，供�端调用
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
é)Ú annotationsN)ÚPath)ÚOptionalÚListÚDictÚAnyÚ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
AsyncIterator)Úasynccontextmanager)ÚFastAPIÚ
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
2026-04-15 09:49:18 +08:00
HTTPExceptionÚBodyr)ÚCORSMiddleware)ÚStreamingResponseÚ JSONResponse)Ú AliasChoicesÚ BaseModelÚ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
ConfigDictÚField)Ú load_dotenvÚbackend)Úconfigure_text2sql_api_logging)Úsetup_environmentÚ load_schemaÚcreate_orchestratorÚresolve_sql_dialect)ÚGenerationResult)Ú
加入日志管理
2026-04-16 10:53:10 +08:00
lite_nl_store)Ú DialogIntentÚclassify_dialog)Úlast_assistant_was_data_queryÚmessages_to_text2sql_contextÚis_likely_follow_upcóì—ddl}tj«dz }|j«r|St |dd«r6t |d«r*t|j «dz }|j«r|St |dd«r8t|j«j}|dz }|j«r|S|Stt«j«j}|dz }|j«r|S|S)u-查找 .env 文件，支æŒ�多ç§�è¿�行环境rNz.envÚfrozenFÚ_MEIPASS) ÚsysrÚcwdÚexistsÚgetattrÚhasattrr%Ú
0.1.1 暂存
2026-04-14 10:28:22 +08:00
executableÚparentÚ__file__Úresolve)r&Úcwd_envÚ meipass_envÚexe_dirÚenv_pathÚ
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
2026-04-15 09:49:18 +08:00
script_dirs ú2C:\Users\24019\Desktop\backman-camel\api_server.pyÚ_find_env_filer52sÞ€ãô�h‰h‹j˜6Ñ!€G؇~�~Ô؈ôˆs�H˜eÔ$¬°°jÔ)Aܘ3Ÿ<™<Ó(¨6Ñ1ˆ Ø × Ñ Ô ØÐ ôˆs�H˜eÔ$ä�s—~‘~Ó&×-Ñ-ˆØ˜VÑ#ˆØ �?‰?Ô ØˆOð €Nô
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
œ(“^×+Ñ+Ó-×4Ñ4ˆ
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
2026-04-15 09:49:18 +08:00
Ø Ñ&ˆØ �?‰?Ô ØˆOð €Nóu[OK] 已加载é…�置文件: u[WARN] 未找到 .env 文件: có(—t�tSt«s td«‚tjdd«}tjdd«}t ||«aGd„d«}tt |««atjd«tS) u获å�–或åˆ�始化 orchestratorNuºçŽ¯å¢ƒæ£€æŸ¥å¤±è´¥ï¼ˆè¯·æŸ¥çœ‹ä¸Šæ–¹ WARNING/INFO，常è§�原因：未é…�好 OPENAI_* / MODELSCOPE_* / DASHSCOPE_* 远程 Embedding；或 Schema 文件路径ä¸�对ã€�LLM Key æœªè®¾ç½®ï¼‰Ú SCHEMA_PATHz9./data/schemas/G3SB_MCDataDictionary_table_structure.jsonÚSCHEMA_META_PATHcó"—eZdZejd«Zejdd«Zeejdd««Ze ejdd««Z
0.1.1 暂存
2026-04-14 10:28:22 +08:00
e ejdd ««Z ejd
d «Z d Z
加入日志管理
2026-04-16 10:53:10 +08:00
ejd
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
d«j«dvZe ejdd««Ze ejdd««Zejdd«j%«j«dvZy)úget_orchestrator.<locals>.ArgsÚDEEPSEEK_API_KEYÚ
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
2026-04-15 09:49:18 +08:00
MODEL_PRIMARYú
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
deepseek-chatÚ TEMPERATUREz0.3Ú
MAX_TOKENSÚ4096Ú MAX_RETRYÚ2ÚVECTOR_DB_PATHz./data/embeddings/chromaFÚFEWSHOT_ENABLEDÚtrue)rFÚ1ÚyesÚ
FEWSHOT_TOP_KÚ3ÚFEWSHOT_MIN_RATINGÚ7ÚTRANSLATE_EN_TO_ZH)Ú0ÚfalseÚnoÚoffN)Ú__name__Ú
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
__module__Ú __qualname__ÚosÚgetenvÚapi_keyÚmodelÚfloatÚ temperatureÚintÚ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
max_tokensÚ max_retryÚ vector_dbÚno_vector_searchÚlowerÚ
no_fewshotÚ
fewshot_top_kÚfewshot_min_ratingÚstripÚno_translate_en©r6r4ÚArgsr;ps„à�"—)‘)Ð.Ó/ˆØ�— ‘ ˜/¨?Ó;ˆÙ˜I˜BŸI™I m°UÓ;Ó<ˆ Ù˜˜Ÿ™ <°Ó8Ó9ˆ
Ù˜ ˜Ÿ ™  +¨sÓ3Ó4ˆ Ø�B—I‘IÐ.Ð0JÓKˆ Ø ÐØ"˜Ÿ™Ð#4°fÓ=×CÑCÓEÐI]Ð]ˆ
Ù˜I˜BŸI™I o°sÓ;Ó<ˆ
Ù   §¡Ð+?ÀÓ!EÓFÐØ#˜"Ÿ)™)Ð$8¸&ÓA×GÑGÓI×OÑOÓQðV
ð
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
‰r6rgu![OK] Orchestrator åˆ�始化完æˆ�)
Ú orchestratorrÚ RuntimeErrorrUrVrÚschema_managerrÚloggerÚinfo)Ú schema_pathÚschema_meta_pathrgs r4Úget_orchestratorro]sˆ€ôÐÜÐä Ô Üð
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
Có
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
ð
ô —)‘)˜MÐ+fÓg€KÜ—y‘yÐ!3°TÓ:Ðä  Ð.>Ó?€N÷
0.1.1 暂存
2026-04-14 10:28:22 +08:00
ñ
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
ô&'¤~±t³vÓ>€LÜ
‡K�KÐ3Ô4ä Ðr6có —eZdZUed¬«Zedd¬«Zded<edd ¬«Zd
ed <edd ¬«Z d
ed
0.1.1 暂存
2026-04-14 10:28:22 +08:00
<ede
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
dd«d¬«Z d
ed<edd¬«Z d
ed<edd¬«Z
d
0.1.1 暂存
2026-04-14 10:28:22 +08:00
ed<edd¬«Zd
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
ed<edd¬«Zd
ed<y)Ú
0.1.1 暂存
2026-04-14 10:28:22 +08:00
NLChatRequestT)Úpopulate_by_name.u!用户输入的自然语言问题©Ú descriptionÚstrÚmessageNu模型路由: openai | deepseekú
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
Optional[str]Ú service_codeu-模型å��称（å�¯é€‰ï¼Œè¦†ç›–默认模型）rXÚautoÚ lang_codeÚlangCodeuD语言：zh=简体中文，tc=ç¹�体中文，en=英语；auto=自动)Úvalidation_aliasrtu任务IDÚtaskIdõ会è¯�IDÚ
session_idu访客业务IDÚvisitor_biz_idu用户IDÚuser_id)rRrSrTrÚ model_configrrvÚ__annotations__rxrXrrzr}rr€r�rfr6r4rqrq‰sª…Ù¨tÔ4€Lá˜Ð*MÔN€GˆSÓNÙ"'¨Ð:[Ô"\€L�-Ó\Ù  Ð3bÔc€Eˆ=Ócá$ØÙ% k°:Ó>ØZô €Iˆ}óñ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
" $°JÔ?€FˆMÓ?Ù % d¸
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Ô C€J�
ÓCÙ$)¨$Ð<LÔ$M€N�MÓMÙ" 4°ZÔ@€Gˆ]Ô@r6rqcó4—eZdZUded<dZded<dZded<y)Ú
IntentPayloadruÚintentNzOptional[float]Ú
confidencerwÚreason)rRrSrTrƒr‡rˆrfr6r4r…r…›s…Ø ƒKØ"&€J�Ó&Ø €FˆMÔ r6r…cóX—eZdZUedd¬«Zded<eed¬«Zded <eed
¬«Zd ed <ed
d¬«Z ded<edd¬«Z
ded<edd¬«Z ded<edd¬«Z ded<edd¬«Z
ded<edd ¬«Zded!<edd"¬«Zded#<edd$¬«Zded%<y)&ÚDataQueryResult.u生æˆ�çš„SQL语å�¥rsruÚsqlu查询结果列å��)Údefault_factoryrtz List[str]Úcolumnsu查询结果行数æ�®zList[Dict[str, Any]]Úrowsru 结果行数r[Ú row_countFu 是å�¦æˆªæ–­ÚboolÚ truncatedNuSQL自然语言说明rwÚ sql_explainTu是å�¦å…�许导出zOptional[bool]Ú
can_exportu_库探针：1=有数æ�®è¡Œï¼Œ0=无行需追问补充，-1=执行失败(é‡�试)，None=未探针ú
Optional[int]Údb_execution_statusu7探针0时的无行说明与追问（å�«é—®é¢˜åˆ†æž�）Údb_empty_feedbackuNTrue 表示探针为0：需用户补充æ�¡ä»¶å�Žé‡�æ–°æ��问以é‡�新生æˆ�SQLÚfollow_up_requiredu4探针为1æ—¶LLM生æˆ�çš„é�¢å�‘用户SQL交付说明Úsql_delivery_message)rRrSrTrr‹rƒÚlistr�rŽr�r‘r’r“r•r–r—r˜rfr6r4rŠrŠ¡så…Ù�SÐ&:Ô;€CˆÓ;Ù¨tÐAUÔV€GˆYÓVÙ!&°tÐI`Ô!a€DÐ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
ÓaÙ˜1¨.Ô9€IˆsÓ9Ù˜E¨~Ô>€IˆtÓ>Ù!& tÐ9PÔ!Q€K�ÓQÙ!& tÐ9MÔ!N€J�ÓNÙ).Ø Øuô*Иóñ(-Ø ÐSô(Ð�}óñ %Ø
Ødô Иóñ+0Ø ÐPô+И-ôr6rŠcó^—eZdZUded<ded<edd¬«Zded <edd
¬«Zded <y) ÚNLChatSuccessDatar…r†rŠÚ
branch_resultNu$æµ�å¼�å�™è¿°ï¼ˆSQLå�—上方说明）rsrwÚstream_narrativeu$æµ�å¼�å�™è¿°ï¼ˆSQLå�—下方说明）Ústream_narrative_after)rRrSrTrƒrr�ržrfr6r4r›r›¹s4…Ø ÓØ"Ó"Ù&+¨DÐ>dÔ&eÐ�mÓeÙ,1°$ÐDjÔ,kИMÔkr6r›cóh—eZdZUedd¬«Zded<edd¬«Zded <ed
d ¬«Zd ed
加入日志管理
2026-04-16 10:53:10 +08:00
<y
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
)Ú ApiEnvelopeéÈu状æ€�ç �，200表示æˆ�功rsr[ÚcodeÚu消æ�¯ruÚmsgNu å“�应数æ�®zOptional[NLChatSuccessData]Údata)rRrSrTrr¢rƒr¤r¥rfr6r4r r Às7…Ù�cÐ'DÔE€Dˆ#ÓEÙ�R XÔ.€CˆÓ.Ù(-¨dÀÔ(O€DÐ
%ÔOr6r có0—eZdZUded<ded<dZded<y)Ú
ErrorResponser[r¢rur¤Nz
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Optional[Any]r¥)rRrSrTrƒr¥rfr6r4r§r§Æs…Ø
ƒIØ ƒHØ€Dˆ-Ôr6r§có8—eZdZUdZded<dZded<dZded<y)ÚSessionCreateBodyNrwÚtitler�r€©rRrSrTrªrƒr�r€rfr6r4r©r©Ìó …Ø€Eˆ=ÓØ!€Gˆ]Ó!Ø$(€N�MÔ(r6r©có8—eZdZUdZded<dZded<dZded<y)ÚSessionTitlePatchBodyNrwrªr�r€r«rfr6r4r®r®Òr¬r6r®có4—eZdZUded<dZded<dZded<y)ÚSessionMessagePatchBodyruÚcontentNrwr�r€)rRrSrTrƒr�r€rfr6r4r°r°Øs…Ø
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
ƒLØ!€Gˆ]Ó!Ø$(€N�MÔ(r6r°có^—eZdZUded<dZded<dZded<dZded<dZded <dZded
<y) ÚSqlExecuteBodyrur‹Nr”Úmax_rowsrwr�r€Úchat_session_idÚchat_message_id) rRrSrTrƒr´r�r€rµr¶rfr6r4r³r³Þs9…Ø ƒHØ"€HˆmÓ"Ø!€Gˆ]Ó!Ø$(€N�MÓ(Ø%)€O�]Ó)Ø%)€O�]Ô)r6r³cóª—eZdZUedd¬«Zded<dZded<dZd ed
<dZd ed <dZ d ed <dZ
d ed
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
<dZ d ed<dZ d ed<dZ
d ed<dZd ed<y)ÚFavoriteCreateBody.zsql | function | reportrsruÚfav_typer£ÚnameNrwÚdescr�r€r‹r’ÚpathÚ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
reportPathÚparams)rRrSrTrr¹rƒrºr»r�r€r‹r’r¼r½r¾rfr6r4r¸r¸çsm…Ù˜#Ð+DÔE€HˆcÓEØ€Dˆ#ƒNØ€Dˆ-ÓØ!€Gˆ]Ó!Ø$(€N�MÓ(Ø€CˆÓØ!%€K�Ó%Ø€Dˆ-ÓØ $€J�
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Ó$Ø €FˆMÔ r6r¸cóV—dtj|d¬«›d�jd«S)Nzdata: F©Ú ensure_asciiz
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
zutf-8)ÚjsonÚdumpsÚencode)Úobjs r4Ú _sse_datarÆôs(€Ø
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
”D—J‘J˜s°Ô7Ð8¸Ð =× DÑ DÀWÓ MÐMr6ÚSSE_STREAM_CHUNK_CHARSÚ64)Ú
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
chunk_sizec óÞK—|sytd|xst«}tdt|«|«D]7}t |d||||zdœ«­–—t j d«ƒd{–—†Œ9y7Œ­w)uI将长文本拆æˆ�多段 SSE，便于æµ�览器é€�段渲染（æµ�å¼�）。Nérr±©ÚstageÚ stream_kindr±)ÚmaxÚ_DEFAULT_SSE_CHUNK_CHARSÚrangeÚlenrÆÚasyncioÚsleep)rÍr±rÉÚsizeÚis r4Ú_sse_stream_text_chunksr×üssèø€ñ ØÜ ˆq�*Ò8Ô 8Ó 9€DÜ
�1”c˜'“l DÖ
)ˆÜبIÀ'È!ÈaÐRVÉhÐBWÑ Xó
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
ó
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
ô�m‰m˜AÓ×Ññ *ð ús‚A!A-Á#A+Á$A-cóH—|xsdj«xsd}ddddœd|idœS) uP寒暄/元问题等：与å‰�端 BUSINESS_MANUAL + branch_result.answer 一致。r£u 您好。ÚBUSINESS_MANUALçð?Ú conversation©r†r‡rˆÚanswer©r†rœ)rd)ÚreplyÚrs r4Ú_conversation_nl_dictrá
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
s4€à Š�"×ÑÓÒ, €Aà.¸cÈ^Ñ\Ø" A˜ñ ðr6có—t|j«}t|j|«}|}|dk(rt «s t «rd}|dk(rt «s t «rd}|}|�œ|xsdj
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
«j«dk(r#d|j
«j«vrd}nT|xsdj
«j«dk(r/|j
«j«jd«rd}||dœS)u°
计算“本次请求实际使用的 LLM 路由信��（用于�端�调回显）。
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
注�：此处仅回显路由结果，�包�密钥等�感信�。
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
ÚdeepseekÚopenaiNr£Úgpt)rxrX) Ú_normalize_model_labelrXÚ_infer_service_coderxÚ_has_deepseek_keyÚ_has_openai_keyrdr`Ú
startswith)ÚrequestrXÚscÚsc2Úeffective_models r4Ú!_effective_llm_route_from_requestrïs÷€ô
# 7§=¡=Ó 1€EÜ ˜W×1Ñ1°5Ó 9€Bà
€CØ
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
ˆjÒÔ!2Ô!4Ü Ô ØˆCØ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
ˆh‚œÔ0Ü Ô ØˆCð€OØÐ"Ø ŠI�2× Ñ Ó × $Ñ $Ó &¨(Ò 2°zÀ_×EZÑEZÓE\×EbÑEbÓEdÑ7dØ"‰OØŠi�R×
Ñ
Ó
×
&Ñ
&Ó
(¨JÒ
6¸?×;PÑ;PÓ;R×;XÑ;XÓ;Z×;eÑ;eÐfkÔ;lØ"ˆOðØ ñ ðr6cóº—|xsdj«}|sy|dvry|dvry|dvry|j«jdd «}|d
vr|S|d vry|d vry|d
vryy)Nry)u 简体中文u简体u中文（简体）Úzh)u ç¹�体中文u ç¹�體中文uç¹�体uç¹�é«”Útc)u英语u英文u英語ÚenÚ_Ú-)rñròróry)Úenglishzen-uszen-gb)zzh-cnzzh-hanszzh-sg)zzh-twzzh-hantzzh-hkÚ traditionalztraditional-chinese©rdr`Úreplace)r¢ÚrawÚcs r4Ú_normalize_lang_coderü4s�€Ø Š>�6×
Ñ
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Ó
"€CÙ Øà
Ð>Ñ>ØØ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
ÐBÑBØØ
Ð,Ñ,Øà � ‰ ‹ ×јC Ó%€AØÐ &Ñ&؈ð Ð )Ñ)ØØÐ )Ñ)ØØÐ OÑOØØ r6có—|xsdj«}|sy|j«j«}|jdd«jdd«}d|vr|jdd«}d|vrŒ|dvry|d vry
|d vry |d
vr|S|S)u©
�端�能传展示文案（如 'GPT-4o mini' / 'DeepSeek V3'）。
Implement follow-up detection in dialog context to prevent context pollution in multi-topic conversations. Introduce is_likely_follow_up function to determine when to inject session history based on user input. Adjust _load_session_text2sql_context to conditionally include context based on follow-up status, enhancing SQL generation accuracy. Update relevant API endpoints to pass user text for improved context handling.
2026-04-15 17:33:07 +08:00
这里统一映射到真实模型�（openai/deepseek �自�用的 model id）。
r£NrôrõÚ z--)ú gpt-4o-miniz
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
gpt4o-minirÿrÿ)úgpt-4oÚgpt4or)ú deepseek-v3Ú
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
deepseekv3z
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
deepseek-v3.0z deepseekv3.0rr>)r>zdeepseek-reasonerrø)rXrúÚms r4ræræNs¨€ð
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
Š;�B×
Ñ
Implement follow-up detection in dialog context to prevent context pollution in multi-topic conversations. Introduce is_likely_follow_up function to determine when to inject session history based on user input. Adjust _load_session_text2sql_context to conditionally include context based on follow-up status, enhancing SQL generation accuracy. Update relevant API endpoints to pass user text for improved context handling.
2026-04-15 17:33:07 +08:00
Ó
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
€CÙ ØØ � ‰ ‹ ×ÑÓ€AØ � ‰ �#�sÓ×#Ñ# C¨Ó-€AØ
0.1.1 暂存
2026-04-14 10:28:22 +08:00
�!‰)Ø
�I‰I�d˜CÓ ˆð �!Š)ð Ð 8Ñ8ØØÐ ÑØð Ð YÑYØØÐ 2Ñ2Øˆà €Jr6cóâ—|xsdj«j«}|r|dvr|S|dvryd|vry|xsdj«j«}|rd|vry|jd«ryy)Nr£)rärã)råÚchatgpträrãrå)rdr`rê)rxÚ
model_namerìrs r4rçrçjs�€Ø
Ò
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
˜"× #Ñ #Ó %× +Ñ +Ó -€BÙ Ø
0.1.1 暂存
2026-04-14 10:28:22 +08:00
Ð'Ñ '؈IØ
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
Ð#Ñ #ØØ ˜Ñ Øà Ò �r× Ñ Ó"×(Ñ(Ó*€AÙØ ˜‰?ØØ �<‰<˜Ô ØØ r6cób—ttjd«xsdj««S)NÚOPENAI_API_KEYr£©r�rUrVrdrfr6r4réré}s%€Ü ”—‘Ð+Ó,Ò2°×9Ñ9Ó;Ó <Ð<r6cób—ttjd«xsdj««S)Nr<r£r
rfr6r4rèrè�s%€Ü ”—‘Ð-Ó.Ò4°"×;Ñ;Ó=Ó >Ð>r6có"—|dk(r y|dk(r y y)NrózÎHello, I'm the Text2SQL assistant.
Describe what you want to query or aggregate in natural language (e.g., available balance of an account; summarize unsettled trades by broker).
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
Type quit or exit to leave.ròuØ您好，我是業務庫 Text2SQL 助手。
請用自然語言�述�查詢或統計的內容（例如：查詢�帳戶�用餘��按經紀商匯總未�算交易筆數）。
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
輸入 quit 或 exit å�¯é€€å‡ºã€‚uØ您好，我是业务库 Text2SQL 助手。
0.1.1 暂存
2026-04-14 10:28:22 +08:00
请用自然语言�述�查询或统计的内容（例如：查询�账户�用余��按�纪商汇总未结算交易笔数）。
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
输入 quit 或 exit å�¯é€€å‡ºã€‚rf©rzs r4Ú_localized_conversation_replyr…s2€Ø�DÒð
0.1.1 暂存
2026-04-14 10:28:22 +08:00
*ð
ð �DÒð
0ð
ð ,ðr6có—|dk(ry|dk(ryy)Nróz=Please enter a concrete business query, or type quit to exit.ròu?請輸入具體的業務查詢å•�題，或輸入 quit 退出。u?请输入具体的业务查询问题，或输入 quit 退出。rfr
s r4Ú_localized_empty_input_replyr›s€Ø�DÒØNØ�DÒØPØ Lr6có—|dk(ry|dk(ryy)NróÚEnglishròzTraditional ChinesezSimplified Chineserfr
s r4Ú _lang_labelr£s€Ø�DÒØØ�DÒØ$Ø r6cƒó2‡‡K—|xsdj«}|s|S|dvr|St|«}dd|›d�dœd|dœgŠd ˆˆfd„ } tj|«ƒd {–—†}|xs|S7Œ
#t$r"}t
j
d
|«|cYd }~Sd }~wwxYw­w) uÓ
将“说明类�文本翻译到 lang_code（仅用于 sql_delivery_message / db_empty_feedback / sql_explain）。
zh 直接返回；en/tc 使用 LLM 翻译（短输出，��引入格�）。
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
r£)ryrñÚsystemzAYou are a translation assistant.
Translate the following text to z³.
Rules:
- Keep the meaning identical; do not add new information.
- Keep SQL keywords/code unchanged if present.
- Output plain text only (no Markdown, no code fences, no JSON).
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
)Úroler±Úusercó~•—‰jj‰ddd¬«}|jxsdj«S)NçrÚi@)rZÚtop_pÚmax_completion_tokensr£)rãÚchatr±rd)r¤ÚmessagesÚorchs €€r4Ú_callz&_translate_explain_text.<locals>._callÊs9ø€Ø�m‰m× Ñ  °sÀ#Ð]`Ð ÓaˆØ— ‘ Ò!˜r×(Ñ(Ó*Ð*r6Nz%[API] explain translation skipped: %s)Úreturnru)rdrrÓÚ to_threadÚ ExceptionrkÚwarning) rÚtextrzÚtÚtargetrÚoutÚers ` @r4Ú_translate_explain_textr)«sºùèø€ð
Š�×ÑÓ€A٠؈ Ø�NÑ"؈ Ü
加入日志管理
2026-04-16 10:53:10 +08:00
˜Ó
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
#€Fðð3Ø39°(ð;UðUñ
ð AÑ&ð
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
€Hö+ðÜ×%Ñ% eÓ,×,ˆØŠ{�dÐð-ùä òÜ�‰Ð>ÀÔBØ� ûðüsG„?BÁA)ÁA'Á A)Á&BÁ'A)Á) BÁ2B BÂ
加入日志管理
2026-04-16 10:53:10 +08:00
BÂBÂBcólK—t|j«}t|j|«}t |j
«}|duxs |duxs|dk(}|s|­–—yddlm}d}|€|��
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
|}|dk(r+t«s!t«rtjd«d}|dk(r+t«s!t«rtjd«d}i} |�ž|xsd j«j«dk(r!d|j«j«vrnX|xsd j«j«dk(r.|j«j«jd
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
«rn|| d <||fi| ¤Ž}t4ƒd{–—†t!|dd«}
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
t!|d d«} |�||_|dk(rt%|d «rd
|_ |­–—|�|
|_| �t%|d «r| |_ ddd«ƒd{–—†y7Œu#|�|
|_| �t%|d «r| |_wwwxYw7Œ,#1ƒd{–—†7swYyxYw­w)u—
若请求传 service_code / model，则临时覆盖 orchestrator.deepseek；
使用����一时刻仅一个请求修改该引用。
Nrór)Úcreate_llm_clientrãz<[API] deepseek requested but key missing, fallback to openairäz<[API] openai requested but key missing, fallback to deepseekr£rårÚtranslate_english_to_zhF)rærXrçrxrürzÚ
加入日志管理
2026-04-16 10:53:10 +08:00
llm.routerr+rèrérkr#rdr`rêÚ_ORCH_LLM_LOCKr)rãr*r,) rrërXrìÚlangÚneeds_overrider+ÚtmpríÚ
llm_kwargsÚoldÚ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
old_translates r4Ú_maybe_override_orch_llmr5Ösèø€ô
# 7§=¡=Ó 1€EÜ ˜W×1Ñ1°5Ó 9€BÜ  × 1Ñ 1Ó 2€DØ �nÒN¨%°tÐ*;ÒNÀÈÁ€NÙ Ø‹
加入日志管理
2026-04-16 10:53:10 +08:00
Øå,à
€CØ €~˜Ñ*àˆØ �*Ò Ô%6Ô%8ÜÔ Ü—‘Ð]Ô^Ø�Ø �(Š?¤?Ô#4Ü Ô"Ü—‘Ð]Ô^Ø �à%'ˆ
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Ø Ð à’ �r× Ñ Ó"×(Ñ(Ó*¨hÒ6¸:ÈÏÉË×I\ÑI\ÓI^Ñ;^ØØ’)˜×"Ñ"Ó$×*Ñ*Ó,°
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
Ò:¸u¿{¹{»}×?RÑ?RÓ?T×?_Ñ?_Ð`eÔ?fØà+0�
˜<Ñ(á Ñ2 zÑ2ˆçŽ~Ü�d˜J¨Ó-ˆÜ Ð&?ÀÓFˆ
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
Ø ˆ?؈DŒMà �4Š<œG DÐ*CÔDØ+0ˆDÔ (ð =Ø‹JàˆØ #�”
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
ØÐ(¬W°TÐ;TÔ-UØ/<�Õ,÷�~‰~ùðˆØ #�”
0.1.1 暂存
2026-04-14 10:28:22 +08:00
ØÐ(¬W°TÐ;TÔ-UØ/<�Õ,ð.VÐ(úðø�~�~‰~üs`‚E>H4ÆG6ÆH4Æ<HÇG8ÇHÇ% H4Ç0HÇ1H4Ç8"HÈHÈH4ÈH1È%H( È&H1È-H4cƒóNK—|jxsdj«}|sytj|j|j
|dd¬«ƒd{–—†}|sy|j
d«xsg}|syt|«}t|«rdnd}t||¬ «\}}||fS7ŒM­w)
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
u}
在写入本轮之�读�会�历�，构造 Text2SQL 上文，并判断上一轮助手是�为数�查询。
r£)r£Fr¡r)ÚlimitÚoffsetNÚitemsé)Ú max_pairs)
rrdrÚ get_messagesr�r€Úgetr r"r!) rëÚ user_textÚsidr¥r9Ú last_datar;ÚblockÚ_ns r4Ú_load_session_text2sql_contextrCs®èø€ð × Ñ Ò # ×
0.1.1 暂存
2026-04-14 10:28:22 +08:00
*Ñ
*Ó
,€CÙ ØÜ×+Ñ+Ø�‰Ø×ÑØ ØØô ÷ €Dñ ØØ �H‰H�WÓ Ò # €EÙ ØÜ-¨eÓ4€Iä(¨Ô3‘¸€IÜ,¨U¸iÔH�I€Eˆ2Ø �)Ð Ðð! ús‚AB%ÁB#ÁAB%cƒó„K—|jr|jj«sy tj|d¬«}t j
|j |j|jj«||«ƒd{–—†y7Œ#t$r"}tjd|›�«Yd}~yd}~wwxYw­w)NFrÀu[API] 会è¯�è�½åº“跳过: ) rrdrÂrÃrÚappend_exchanger�r€r"rkr#)rër>r¥Úassistant_jsonr(s r4Ú_append_session_if_neededrG-s èø€Ø × Ò  7×#5Ñ#5×#;Ñ#;Ô#=Øð
9ÜŸ™ D°uÔ=ˆÜ×+Ñ+Ø �O‰OØ × "Ñ "Ø × Ñ × $Ñ $Ó &Ø Ø ó 
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
÷
ò
ùô ò9Ü�‰Ð3°A°3Ð7×8Ñ8ûð9üsA‚(C«ABÂ
B BÂCÂB B=ÂB8Â3CÂ8B=Â=CcóÌ—|jxsdj«}g}|jjd«r'|j t |jd««|j r"|jd„|j D««|jr"|jd„|jD««|rdj|«nd}|ggdddœ}|r||d <|jjd
«}|�||d
<|jjd«}|r||d<t|jxr|dk(«|d <|jjd «}|rt |«|d <|jrd
nd}|jrdt|j«›d�} n|jr|jdnd} d|| dœ|dœ}
|jjd«} |jjd«} | r
| r| | dœ|
d<|jjd«r:|jjd«|jjd«dœ|
d<|
S)Nr£r–c3ó2K—|]}t|«–—Œy­w©N©ru)Ú.0Úws r4Ú <genexpr>z+_nl_dict_from_generation.<locals>.<genexpr>Csèø€Ð=©_¨œS ŸV©_ùó‚c3ó2K—|]}t|«–—Œy­wrJrK)rLr(s r4rNz+_nl_dict_from_generation.<locals>.<genexpr>Esèø€Ð;©]¨œS ŸV©]ùrOz; rF)r‹r�rŽr�r‘r’r•r—r˜rÚru
使用了 u 张表uSQL生æˆ�未通过验è¯�Ú
DATA_QUERYrÜrÞÚquestion_originalÚquestion_zh_normalized)ÚoriginalrñÚquery_normalizationÚfewshot_golden_reuseÚfewshot_golden_qidÚfewshot_golden_score)ÚqidÚscoreÚfewshot_golden)r‹rdÚmetadatar=ÚappendruÚwarningsÚextendÚerrorsÚjoinr�ÚvalidrÒÚ tables_used)
Úresultr‹Ú
explain_partsÚexplainrœÚdbsÚdbeÚsdmÚconfrˆÚpayloadÚqoÚqzs
r4Ú_nl_dict_from_generationrn=s6€Ø �:‰:Ò ˜×
0.1.1 暂存
2026-04-14 10:28:22 +08:00
"Ñ
"Ó
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
$€CØ!€MØ
‡�×ÑÐ.Ô/Ø×ÑœS §¡Ð1DÑ!EÓFÔGØ
0.1.1 暂存
2026-04-14 10:28:22 +08:00
‡‚Ø×ÑÑ=¨V¯_ª_Ó=Ô=Ø
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
‡}‚}Ø×ÑÑ;¨V¯]ª]Ó;Ô;Ù*7ˆd�i‰i˜
Ô&¸T€GàØØØØñ %€MñØ'.ˆ
�mÑ$Ø
0.1.1 暂存
2026-04-14 10:28:22 +08:00
�/‰/×
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
Ñ
Ð3Ó
0.1.1 暂存
2026-04-14 10:28:22 +08:00
4€CØ
加入日志管理
2026-04-16 10:53:10 +08:00
€Ø/2ˆ
0.1.1 暂存
2026-04-14 10:28:22 +08:00
Ð+Ñ,Ø
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
�/‰/×
0.1.1 暂存
2026-04-14 10:28:22 +08:00
Ñ
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Ð1Ó
0.1.1 暂存
2026-04-14 10:28:22 +08:00
2€CÙ
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Ø-0ˆ
Ð)Ñ*Ü*.¨v¯|©|Ò/HÀÀqÁÓ*I€MÐ&Ñ'Ø
�/‰/×
Ñ
Ð4Ó
0.1.1 暂存
2026-04-14 10:28:22 +08:00
5€CÙ
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
Ü03°C³ˆ
0.1.1 暂存
2026-04-14 10:28:22 +08:00
Ð,Ñ-Ø—,’,‰3 C€DØ
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
‡|‚|Øœc &×"4Ñ"4Ó5Ð6°gÐ>‰à%+§]¢]�—‘˜qÒ!Ð8Rˆà)¸ÈÑPØ&ñ€Gð
�‰× Ñ Ð0Ó 1€BØ �‰× Ñ Ð5Ó 6€BÙ ‰bØ68ÀÑ)CˆÐ%Ñ&Ø
‡�×ÑÐ1Ô2à—?‘?×&Ñ&Ð';Ó<Ø—_‘_×(Ñ(Ð)?Ó@ñ%
ˆÐ Ñ!ð €Nr6c ƒó‡‡‡‡ K—t«}ttjdd««Š |xsdj «xsdŠ‰j «}t
加入日志管理
2026-04-16 10:53:10 +08:00
j
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
d‰ ‰‰r t‰«ndt|«|ddt|«dkDrdndz«d ˆˆ ˆˆfd„ }|€||«ƒd{–—†St||«4ƒd{–—†}||«ƒd{–—†cddd«ƒd{–—†S7Œ:7Œ'7Œ7Œ #1ƒd{–—†7swYyxYw­w)
NÚTEXT2SQL_DIALECTÚ sqlserverr£zP[GEN/API] dialect=%s top_k=%s dialog_context_chars=%s question_len=%s preview=%rré,õ…c“ó`•‡K—dˆˆˆˆˆfd„ }tj|«ƒd{–—†S7Œ­w)NcóJ•—‰j‰j«‰‰‰¬«S)N)ÚquestionÚdialectÚtop_k_candidatesÚdialog_context)Úgeneraterd)ÚdcrwÚorvÚtop_ks€€€€€r4rz5_run_generate.<locals>._call_with_orch.<locals>._callƒs,ø€Ø—:‘:Ø!Ÿ™Ó)ØØ!&Ø!ð óð
r6©r r)rÓr!)r|rr{rwrvr}s` €€€€r4Ú_call_with_orchz&_run_generate.<locals>._call_with_orch‚s*ùèø€÷ ñ ô×&Ñ& uÓ-×-Ð-Ð-ús „#.§,¨.r~) rorrUrVrdrkrlrÒr5)
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
rvr}ryrërÚqrr|r{rws
0.1.1 暂存
2026-04-14 10:28:22 +08:00
`` @@r4Ú
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
_run_generater�osíûèø€ô Ó €DÜ!¤"§)¡)Ð,>À Ó"LÓM€GØ
0.1.1 暂存
2026-04-14 10:28:22 +08:00
Ò
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
˜B× %Ñ %Ó 'Ò /¨4€BØ�‰Ó€AÜ
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
‡K�KØZØØ
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
2026-04-15 09:49:18 +08:00
ÙŒˆBŒ˜1Ü ˆA‹Ø ˆ$ˆ3ˆœC ›F SšL‘5¨bÑ1ô
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
÷ .ð .ð€Ù$ TÓ*×*Ð*Ü'¨¨g×6Ô6¸!Ù$ QÓ'×'÷7×6Ñ6ð+øØ6øØ'øð7ø×6×6Ñ6üsl†B.D Â4C/Â5D à C1Ã
0.1.1 暂存
2026-04-14 10:28:22 +08:00
D Ã
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
C7ÃC3ÃC7à D Ã)C5Ã*D Ã1D Ã3C7Ã5D Ã7D Ã=D Ã>D ÄD cóî ‡‡‡‡‡‡‡‡K—|jr|jj«s1t|j«}t dt |«ddœ«­–—y|jj«Št
«}t|‰«ƒd{–—†\}}tjd|j|j|j|j|j|jt‰«‰ddt‰«dkDrdndz|r t|«nd|« t|j«}t!||«4ƒd{–—†Št#j$t&‰||xsd‰j(¬«ƒd{–—†}ddd«ƒd{–—†j*t,j.k(rŽ|j0xsdj«}|s t3|«}tjdt|«|dd t|«d kDrdndz«t d
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
d d d
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
2026-04-16 13:48:44 +08:00
œ«­–—t5d|«23d{–—†}|­–—Œt d
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
d dd
0.1.1 暂存
2026-04-14 10:28:22 +08:00
œ«­–—t=t?j@dd««Š|xsdj«xsdŠdŠt#jB«Štjd‰‰‰r t‰«ndt‰«‰ddt‰«dkDrdndz« t!||«4ƒd{–—†Št#jD«ŠiŠd%ˆˆˆˆˆˆˆˆfd„ } t#jFt#j$| ««}
‰jI«ƒd{–—†} | €n| rt dd | d
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
œ«­–—Œ0|
Refactor SQL streaming behavior in API server to default to LLM native delta transmission without secondary splitting. Update NLChatRequest to clarify optional parameters for SQL stream granularity and streaming throttle. Adjust _sse_stream_text_chunks and _chat_stream_events methods to streamline content handling and improve performance. Revise impact analysis documentation to reflect these changes.
2026-04-16 14:29:24 +08:00
ƒd{–—†‰jId«r‰d‚‰d} ddd«ƒd{–—† jPxsdj«}tjd| jR| jT| jVt|«|dd t|«d kDrdndz«| jXr tj[d | jX«| j\r tjd!| j\« t_| j`tb«r¦| j`jId"«r8te|tO| j`d"«|«ƒd{–—†| j`d"<| j`jId#«r8te|tO| j`d#«|«ƒd{–—†| j`d#<tg| «}t9|«|d<| jRrdnd$}t d||dœ«­–—t;|‰|«ƒd{–—†y7�Œó7�ŒB7�Œ7�Œ#1ƒd{–—†7swY�ŒxYw7�Œx6t7|«}t9|«|d<t dd|dœ«­–—t;|‰|«ƒd{–—†7y7�Œý7�Œœ7�Œ}7�ŒU#1ƒd{–—†7swY�ŒfxYw#tJ$r?}
0.1.1 暂存
2026-04-14 10:28:22 +08:00
tjMd|
›�d¬«t d tO|
«ddœ«­–—Yd}
~
yd}
~
wwxYw7�Œ‹7�Œ;#tJ$rY�Œ8wxYw7Œð­w)&Né�©r¢r¤r¥u±[API/stream] 开始: user_id=%r visitor_biz_id=%r session_id=%r service_code=%r model=%r lang_code=%r msg_chars=%s preview=%r dialog_context_chars=%s last_turn_was_data_query=%srsr£r©Úlast_turn_was_data_queryryÚ
llm_clientu\[API/stream] 对è¯�æ„�图 conversation（跳过 Text2SQL）: reply_chars=%s reply_preview=%réôrhr±ÚCHATrÌrÚllmr¡ÚsuccessrQrprqézW[GEN/API/stream] dialect=%s top_k=%s dialog_context_chars=%s question_len=%s preview=%rrrcó•— ‰j‰j«‰‰‰ˆˆfd„¬«‰d<‰j‰jd«y#t$r}|‰d<Yd}~Œ0d}~wwxYw#‰j‰jd«wxYw)Ncó<•—‰j‰j|«SrJ)Úcall_soon_threadsafeÚ
put_nowait)rûÚ chunk_queueÚloops €€r4Ú<lambda>zA_chat_stream_events.<locals>._run_generate_sync.<locals>.<lambda>Ýsø€°d×6OÑ6OØ'×2Ñ2°Aô7r6)rvrwrxryÚsql_stream_callbackrdÚerror)rzrdr"r�r�) r(r‘Údc_ctxrwÚholderr’r|r$r}s €€€€€€€€r4Ú_run_generate_syncz/_chat_stream_events.<locals>._run_generate_syncÖs„ø€ð
LØ'(§z¡zØ!%§¡£Ø 'Ø).Ø'-ô-ð (2ó(�F˜8Ñ$ð×-Ñ-¨k×.DÑ.DÀdÕKøô!ò(Ø&'�F˜7–Oûð(ûð×-Ñ-¨k×.DÑ.DÀdÕKús)ƒ+A Á A#ÁAÁA&ÁA#Á#A&Á&BTÚsql_genr•rduPI/stream] 生æˆ�异常: )Úexc_infouZ[API/stream] Text2SQL 完æˆ�: valid=%s attempts=%s tables_used=%s sql_chars=%s sql_head=%ru[API/stream] 错误列表: %su[API/stream] 警告列表: %sr˜r–Úpartial)r ÚNone)4rvrdrürzrÆrrorCrkrlr�r€rrxrXrÒr5rÓr!rrãr†rÚ CONVERSATIONÚreply_suggestionrr×rárïrGrrUrVÚget_running_loopÚQueueÚ create_taskr=r"r•rur‹rbÚattemptsrcr`r#r^Ú
isinstancer\Údictr)rn)rër/rÚ dialog_blockr@Ú
classifiedrßÚpktÚ data_dictr˜Úgen_taskÚpiecerdr(Úsql_outr¤r‘r–rwr—r’r|r$r}s @@@@@@@@r4Ú_chat_stream_eventsr¬“s¢ÿèø€Ø �?Š? '§/¡/×"7Ñ"7Ô"9Ü# G×$5Ñ$5Ó6ˆÜ Ô-IÈ$Ó-OÐY]Ñ^Ó_Ó_ØØ �?‰?× Ñ Ó "€DÜ Ó €DÜ$BÀ7ÈDÓ$Q×QÑ€L�)Ü
‡K�Kð cà�‰Ø×ÑØ×ÑØ×ÑØ�
‰
Ø×ÑÜ ˆD‹ Ø ˆTˆcˆ
œs 4›y¨3š‘e°BÑ7Ù)ŒˆLÔ¨qØô
ô  × 1Ñ 1Ó 2€DÜ'¨¨g×6Ô6¸!Ü"×,Ñ,Ü Ø Ø%.Ø'Ò/¨4Ø—z‘zô 
÷
ˆ
÷7×6ð×ÑœL×5Ñ5Ò5Ø×,Ñ,Ò2°×9Ñ9Ó;ˆÙÜ1°$Ó7ˆEÜ� ‰ Ø jÜ �‹JØ �$�3ˆK¤C¨£J°Ò$4™5¸"Ñ =ô
ô
 .ÀÐW]Ñ^Ó_Ó_Ü0°¸Ô?÷ �#ØŒIô ˜n¸YÐS_Ñ`Ó
aÓaÜ!¤"§)¡)Ð,>À Ó"LÓM€GØÒ ˜b×
'Ñ
'Ó
)Ò
1¨T€FØ €EÜ × #Ñ #Ó %€DÜ
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
2026-04-15 09:49:18 +08:00
‡K�KØaØØ
0.1.1 暂存
2026-04-14 10:28:22 +08:00
ÙŒˆFŒ  1Ü ˆD‹ Ø ˆTˆcˆ
加入日志管理
2026-04-16 10:53:10 +08:00
œs 4›y¨3š‘e°BÑ7ô
Copy Permalink