topdog/supersonic
1
0
Fork 0
mirror of https://github.com/tencentmusic/supersonic.git synced 2025-12-11 03:58:14 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
1,446 Commits 3 Branches 16 Tags
267cb6506dd29233b01b47ee349e3660fc0cf4a8
Commit Graph

478 Commits

Author SHA1 Message Date
Jun Zhang
85552fb73a [improvement][chat]Merge RuleTool and LLMTool.#1766 (#1768) 2024-10-10 14:53:54 +08:00
jerryjzhang
809898e786 [improvement][launcher]Clean code structure of system demos. 2024-10-09 19:54:32 +08:00
jerryjzhang
5fcec320ba [improvement][chat]Do not create duplication memory for exactly the same question. 2024-10-09 18:12:44 +08:00
jerryjzhang
cd57d2344e [fix][chat]Model provider is case sensitive.#1739 2024-10-09 17:48:42 +08:00
jerryjzhang
248f4f83f6 [feature][chat]Refactor chat model config related codes.#1739 2024-10-09 17:27:07 +08:00
jerryjzhang
9ffe67c962 [feature][chat]Add API to get ChatModelType list.#1739 2024-10-09 14:56:34 +08:00
jerryjzhang
7b9ff2e281 [feature][chat]Introduce dedicated LLM management.#1739 2024-10-09 12:00:24 +08:00
jerryjzhang
aa32a2a640 [improvement][headless-chat]Rename methods of ChatQuery and ChatLayer service. 2024-10-08 17:48:28 +08:00
jerryjzhang
8bf5d395a7 [improvement][headless-chat]Demo queries only use rule-based parser. 2024-10-08 15:49:23 +08:00
lexluo09
71a9954be5 (improvement)[build] Use Spotless to customize the code formatting (#1750) 2024-10-04 00:05:04 +08:00
lexluo09
de2385cd2c [improvement][headless] Backend uniformly supports other types of databases. (#1745) 2024-09-30 15:02:58 +08:00
LXW
6c2553ab8f (improvement)(Chat) Optimize memory management (#1741) 
Co-authored-by: lxwcodemonkey
 2024-09-29 17:13:06 +08:00
jerryjzhang
bfdf9004ea [fix][launcher]Enable multi-turn conversation in S2VisitsDemo. 2024-09-29 14:31:59 +08:00
jerryjzhang
ae3e9f142b [improvement][headless]Rename METRIC query type enum to AGGREGATE. 2024-09-27 15:19:26 +08:00
lexluo09
23489a6c06 (improvement)(chat) Optimize memory recall to enable few-shot recall within the Agent level (#1696) 2024-09-23 10:56:24 +08:00
jerryjzhang
cd08cf51c5 [improvement][project]Use DatePeriodEnum to replace DAY/MONTH/YEAR period constants. 2024-09-22 17:14:55 +08:00
LXW
4193b84e83 (fix)(chat) fix the issue that front-end filter time re-query does not take effect, when the partition time field name is not imp_date #1638 (#1694) 
Co-authored-by: lxwcodemonkey
 2024-09-21 13:24:38 +08:00
LXW
79dc6c04ce (improvement)(chat) Avoid occasional npe when obtaining recommended dimensions (#1693) 
Co-authored-by: lxwcodemonkey
 2024-09-21 12:27:32 +08:00
jerryjzhang
e0a2ed557d [improvement][chat-server]Iterate LLM prompt in the MemoryReviewTask. 2024-09-20 18:21:43 +08:00
jerryjzhang
c045b34328 [improvement][chat]Expose default prompt template to facilitate customization. 2024-09-20 16:57:21 +08:00
jerryjzhang
6ac7949a18 [fix][chat]Fix illegal argument exception. 2024-09-14 14:30:04 +08:00
jipeli
5f4d24348a [improvement][headless] fix queryData by dimension error (#1666) 2024-09-13 14:37:14 +08:00
lexluo09
879696e493 [improvement](chat) Optimize the Schema Mapping rules (#1649) 2024-09-10 22:58:34 +08:00
lexluo09
5f59e89eea (improvement)(build) Add spotless during the build process. (#1639) 2024-09-07 00:36:17 +08:00
lexluo09
7dbd23d751 (improvement)(chat) Fixed the issue where setting an incorrect embeddingStore address in the system settings caused the service to fail to start (#1631) 2024-09-05 16:10:45 +08:00
lexluo09
1b6277e53f (improvement)(chat) Fixed the NullPointerException issue in DimensionRecommendProcessor (#1629) 2024-09-04 22:46:38 +08:00
xiuzhu9527
5606633481 (fix)(chat)Remove spaces when obtaining a MemoryReviewResult (#1594) 2024-08-26 10:27:08 +08:00
yudong
3915d90eec (improvement)(chat)多轮对话增加rewrittenQuery的MapInfo (#1599) 2024-08-26 10:20:52 +08:00
lexluo09
7150f19def (improvement)(chat) Vector retrieval supports filtering by modelId collection during query. (#1576) 2024-08-16 21:31:07 +08:00
yudong
1608317ab3 [fix][chat]修复对话丢失问题 (#1539) 2024-08-08 18:05:38 +08:00
lexluo09
3d1ca6ac1d (improvement)(chat) Optimize the code for the queryData and queryDimensionValue interfaces. (#1529) 2024-08-07 20:56:13 +08:00
jerryjzhang
4a5bb9e457 (fix)(headless)Fix multi-turn conversation issue, recalling history ChatQuery instead of ChatParse. 2024-07-30 21:57:44 +08:00
jerryjzhang
2472ce2461 (improvement)(chat)Opt rewritten error message prompt. 2024-07-30 09:26:18 +08:00
jerryjzhang
ccd79e4830 [improvement][headless]Optimize code structure and code style. 2024-07-28 10:06:16 +08:00
jerryjzhang
e5504473a4 [improvement][headless&chat]Move EntityInfoProcessor from chat to headless module and optimize code. 
[improvement][headless&chat]Move `EntityInfoProcessor` from `chat` to `headless` module and optimize code.
 2024-07-27 18:10:06 +08:00
jerryjzhang
2425067091 (improvement)(common)Rename SqlExemplar to Text2SQLExemplar. 2024-07-18 14:19:56 +08:00
jerryjzhang
2eac301076 (improvement)(headless)Introduce side_information to the prompt and exemplar. 2024-07-18 11:29:07 +08:00
jerryjzhang
782b768950 (improvement)(headless&chat)The Chat module only references facade service of the Headless module. 2024-07-16 17:53:01 +08:00
jerryjzhang
1c0b8f8161 (improvement)(headless)Restructure facade and expose only ChatLayerService and SemanticLayerService. 2024-07-16 17:41:20 +08:00
lexluo09
4eb6193699 (improvement)(chat) Integrate llm configuration into system settings. (#1403) 2024-07-14 14:47:17 +08:00
LXW
407c8d4702 (improvement)(Headless) Refactor ChatLayerService and SemanticLayerService (#1404) 
Co-authored-by: lxwcodemonkey
 2024-07-14 11:23:47 +08:00
jerryjzhang
baff30550e (improvement)(headless&chat)Move ChatContext from Headless module to Chat module. 2024-07-12 19:50:12 +08:00
jerryjzhang
e365a36749 (improvement)(headless)Remove mapper related configs from system configuration UI. 2024-07-12 15:16:01 +08:00
jerryjzhang
5bf4a4160d (fix)(chat&headless)Agent references ChatModelConfig instead of ModelConfig. 2024-07-12 14:15:54 +08:00
jerryjzhang
37da1ac2ae (improvement)(chat)Enable memory directly if the review result by LLM is positive. 2024-07-12 09:59:58 +08:00
jerryjzhang
d6c5702b5a (feature)(chat)Rewrite error message to make it more understandable to the user. #1320 2024-07-11 20:33:32 +08:00
jerryjzhang
9bb95ca4be (feature)(chat)Add switch to enable LLM-based memory review, as it leads to more token costs. #1385 2024-07-10 21:08:02 +08:00
jerryjzhang
ea4aa3eacf (improvement)(headless)Remove unnecessary performExecution method from ChatQueryService. 2024-07-09 17:37:36 +08:00
jerryjzhang
f0b4eb46cf (improvement)(headless)Remove unnecessary TranslateSqlReq, use SemanticQueryReq instead. 2024-07-09 11:28:43 +08:00
jerryjzhang
efd617b2e5 (improvement)(headless)Rename QueryTextReq to QueryNLReq to explicitly reflect natural language concept. 2024-07-08 10:20:20 +08:00