37 Commits

Author SHA1 Message Date
2781172724 use yaml instead of yml 2026-03-05 15:51:59 +08:00
26ca06d50d remove pipeline_id and set_id since using LLMNodeConfig 2026-02-12 15:05:26 +08:00
9363bd3442 use LLMNodeConfig 2026-02-12 14:54:27 +08:00
c2cc2628dd use LLMKeyConfig 2026-02-12 14:35:27 +08:00
4def81efbf add inference time 2026-01-19 22:10:33 +08:00
74bded469c use qwen-plus for eval 2026-01-19 20:43:56 +08:00
e8c696269b save explanation 2026-01-19 16:07:49 +08:00
c1070df725 update default evaluator dataset 2026-01-19 15:09:47 +08:00
9b03bad0f2 remove import 2026-01-19 14:45:30 +08:00
f9ac34498c add explanation 2026-01-14 13:31:07 +08:00
a0ad19449a change default dataset 2026-01-09 15:05:43 +08:00
6d9f7fe5b9 better formatting 2026-01-08 19:56:11 +08:00
985fd41f54 make string 2026-01-08 18:11:11 +08:00
91177cc5e0 use xiao_zhan dataset as default 2025-10-30 15:31:05 +08:00
fcc8888449 change direction, support 'or' 2025-10-30 15:22:58 +08:00
468284939c return true if None 2025-10-30 15:00:37 +08:00
d054aaccbc save config 2025-10-30 11:42:41 +08:00
c6872199d6 fix exp name 2025-10-29 22:19:58 +08:00
30a5421fd7 save results 2025-10-29 19:06:28 +08:00
d93c72f24d save results locally 2025-10-29 18:53:58 +08:00
3d5fb89283 pass in uuid 2025-10-29 18:25:58 +08:00
4d4a4a7803 remove comments 2025-10-29 16:18:10 +08:00
285f8975c6 add tool use for default eval 2025-10-29 16:17:20 +08:00
df7468ea9f support conversation 2025-10-29 16:08:58 +08:00
703e429293 change metric 2025-10-29 14:42:12 +08:00
e9d13878c9 change to simple datset 2025-10-27 16:45:57 +08:00
51ac83401b validate tool use 2025-10-27 16:39:20 +08:00
880a573c42 return default if not specified 2025-10-27 15:21:12 +08:00
c81a4ed6d4 return list 2025-10-24 17:19:58 +08:00
c5a6583d80 add notes 2025-10-24 16:17:42 +08:00
2056dc3d75 use get_inp 2025-10-24 16:14:36 +08:00
f61554bcac add input func 2025-10-24 16:14:20 +08:00
dbaf65d617 not passing in dataset name 2025-10-23 21:21:35 +08:00
bb5880a767 typing correction 2025-10-23 21:20:23 +08:00
80ef5e7216 eval __init__ 2025-10-23 21:19:06 +08:00
055c670bef evaluator 2025-10-23 21:15:41 +08:00
c0ec4e7a2a validator 2025-10-23 21:15:37 +08:00