Commit Graph

3307 Commits

Author SHA1 Message Date
alan.cl
dc2e994fa0 docs: add v0.7.4 upgrade schema sql 2025-10-23 13:20:00 +08:00
alan.cl
f0de20662b docs: update benchmark doc 2025-10-22 16:48:26 +08:00
alan.cl
f3263c86f8 docs: update benchmark doc 2025-10-22 16:44:47 +08:00
alan.cl
81cee7702d docs: update image 2025-10-22 16:29:51 +08:00
alan.cl
61bbba3f9c docs: add dataset benchmark docs 2025-10-21 17:22:27 +08:00
alan.cl
59e39b20ef chore: update falcon repo url 2025-10-21 17:20:27 +08:00
yaoyifan-yyf
3beb28123a Merge branch 'feat_dataset_benchmark' of github.com:eosphoros-ai/DB-GPT into feat_dataset_benchmark 2025-10-21 16:56:55 +08:00
yaoyifan-yyf
6904d026d7 fix: answer adjustment 2025-10-21 16:56:28 +08:00
alan.cl
8c1bfedd76 Merge remote-tracking branch 'origin/feat_dataset_benchmark' into feat_dataset_benchmark 2025-10-21 14:32:36 +08:00
alan.cl
2cd22a2c22 chore: update ignore 2025-10-21 14:27:30 +08:00
alan.cl
2caa3171eb fix(benchmark): fix download result url 2025-10-21 14:19:52 +08:00
alan.cl
9ada90bcbc chore: web build file 2025-10-20 16:17:34 +08:00
alan.cl
48aa2043c0 feat(benchmark): show task name 2025-10-20 15:09:26 +08:00
yaoyifan-yyf
48a37986aa fix: table error fix 2025-10-20 13:50:17 +08:00
yaoyifan-yyf
3f0d63baad Merge branch 'feat_dataset_benchmark' of github.com:eosphoros-ai/DB-GPT into feat_dataset_benchmark 2025-10-20 13:50:08 +08:00
yaoyifan-yyf
e69a4e587f fix: table error fix 2025-10-20 13:48:40 +08:00
iterminatorheart
cfdb1dba99 feat: multi language for models evaluation (#2912)
Co-authored-by: VLADIMIR KOBZEV <vladimir.kobzev@improvado.io>
Co-authored-by: Aries-ckt <916701291@qq.com>
Co-authored-by: xiandu.wl <xiandu.wl@antgroup.com>
2025-10-20 11:43:05 +08:00
alan.cl
9de988f0fe fix(benchmark): custom model temperature and max token 2025-10-19 16:44:24 +08:00
iterminatorheart
19bbc6fa8d feat: evaluation dataset info pages (#2911)
Co-authored-by: VLADIMIR KOBZEV <vladimir.kobzev@improvado.io>
Co-authored-by: Aries-ckt <916701291@qq.com>
Co-authored-by: xiandu.wl <xiandu.wl@antgroup.com>
2025-10-19 12:40:48 +08:00
iterminatorheart
d2e92e9382 feat: add datasets evaluation page (#2908)
Co-authored-by: VLADIMIR KOBZEV <vladimir.kobzev@improvado.io>
Co-authored-by: Aries-ckt <916701291@qq.com>
Co-authored-by: xiandu.wl <xiandu.wl@antgroup.com>
2025-10-17 18:13:59 +08:00
alan.cl
b410e85071 fix(benchmark): remove useless code 2025-10-17 16:19:03 +08:00
alan.cl
ed59a715d0 fix(benchmark): fix sql query db timeout for blocking thread 2025-10-17 11:26:29 +08:00
alan.cl
cda5b74329 fix(benchmark): process sql query timeout 2025-10-16 20:58:38 +08:00
alan.cl
39ac73dd59 fix(benchmark): execute benchmark with model param 2025-10-16 20:02:28 +08:00
alan.cl
8f0b2c3715 fix: fix page list request 2025-10-16 19:09:37 +08:00
alan.cl
8e025c8323 feat(benchmark): update benchmark task status & benchmark task info list 2025-10-16 16:21:04 +08:00
yaoyifan-yyf
2a823ee25c feat: support multi benchmark datasets 2025-10-16 14:56:25 +08:00
yaoyifan-yyf
ba80df5485 opt: api name adjuest 2025-10-16 14:12:10 +08:00
yaoyifan-yyf
fb83e30a84 opt: benchmark result api output adjust 2025-10-16 14:10:03 +08:00
yaoyifan-yyf
41da1b3063 fix: benchmark compare summary write to db 2025-10-16 14:04:33 +08:00
yaoyifan-yyf
ff3406487f fix: benchmark compare summary write to db 2025-10-16 10:59:11 +08:00
yaoyifan-yyf
05b1fb6163 fix: col name sanitize modification 2025-10-15 17:54:39 +08:00
yaoyifan-yyf
24064d7b49 fix: ant_icube table mapping correct 2025-10-15 17:38:04 +08:00
alan.cl
65fd87bfe0 fix(benchmark): update standard anwser result field 2025-10-15 11:51:15 +08:00
alan.cl
92243cb6bc fix(benchmark): parse multi standard anwser 2025-10-15 10:23:27 +08:00
alan.cl
5df8d94f43 feat(benchmark): benchmark result file download 2025-10-14 14:43:00 +08:00
yaoyifan-yyf
838bc359ad Merge remote-tracking branch 'origin/feat_dataset_benchmark' into feat_dataset_benchmark 2025-10-13 16:59:18 +08:00
yaoyifan-yyf
ab96ebb785 opt: add standard result col to output excel 2025-10-13 16:58:58 +08:00
alan.cl
c14b68d061 feat(benchmark): query benchmark task list 2025-10-13 16:56:53 +08:00
yaoyifan-yyf
8d8d455310 opt: multi model compare write result 2025-10-13 15:55:42 +08:00
alan.cl
87f11b574d feat(benchmark): multi model post process 2025-10-13 14:38:45 +08:00
yaoyifan-yyf
9b81a10866 opt: compare result write to excel not db 2025-10-13 10:53:17 +08:00
alan.cl
33a4e047ed fix(benchmark): fix post dispatch param 2025-10-13 09:42:27 +08:00
alan.cl
5b27b6e939 Merge remote-tracking branch 'origin/feat_dataset_benchmark' into feat_dataset_benchmark 2025-10-11 15:43:21 +08:00
alan.cl
8217408af0 feat(benchmark): create benchmark task 2025-10-11 15:43:05 +08:00
yaoyifan-yyf
81e2a1c18d fix: add table mapping 2025-10-11 14:02:51 +08:00
alan.cl
f6351aeec7 feat(benchmark): optimize benchmark task and write evaluate result rows offset 2025-10-10 20:00:31 +08:00
alan.cl
0330dd32b8 chore: resolve confict 2025-10-10 10:34:37 +08:00
alan.cl
61e350f4b5 Merge remote-tracking branch 'origin/feat_dataset_benchmark' into feat_dataset_benchmark
# Conflicts:
#	packages/dbgpt-serve/src/dbgpt_serve/evaluate/api/endpoints.py
#	packages/dbgpt-serve/src/dbgpt_serve/evaluate/api/schemas.py
#	packages/dbgpt-serve/src/dbgpt_serve/evaluate/service/benchmark/file_parse_service.py
#	packages/dbgpt-serve/src/dbgpt_serve/evaluate/service/benchmark/user_input_execute_service.py
2025-10-10 10:27:03 +08:00
yaoyifan-yyf
c923e6444c feat: add benchmark result query api 2025-10-09 17:25:30 +08:00