Commit graph

6281 commits

Author SHA1 Message Date
林义章
a94e282e7f Merge branch 'feature/mermaid_font' into 'mgx_ops'
feat: mermaid + font

See merge request pub/MetaGPT!372
2024-09-10 08:48:22 +00:00
seehi
5d21d255e4 update 2024-09-10 16:44:22 +08:00
duyipan
923109e882 add aide.py update README 2024-09-10 16:27:29 +08:00
莘权 马
832494706e feat: mermaid + font 2024-09-10 16:24:04 +08:00
Yizhou Chi
a373e684ae update di instruction 2024-09-10 16:05:22 +08:00
Yizhou Chi
b776c7309b add random tree search 2024-09-10 15:30:23 +08:00
Rayhao
e3663f2322 implement autuglu exp 2024-09-09 23:21:56 -07:00
Yizhou Chi
d34a482faf give dev label 2024-09-10 14:11:47 +08:00
Yizhou Chi
60e8e3eab8 fix hfdataset; make dirs when save notebook 2024-09-10 13:51:54 +08:00
didi
0b0a49d772 更新 hotpotqa Baseline 2024-09-10 12:48:28 +08:00
黄伟韬
3de17e5067 remove .html file 2024-09-10 11:01:29 +08:00
didi
c7c34cda7d Update human Eval 2024-09-10 10:58:39 +08:00
didi
62ffa730e0 update humaneval baseline & hotpotqa baseline 2024-09-10 10:57:21 +08:00
林义章
6896c34d23 Merge branch 'run_swe_agent_benchmark_script' into 'mgx_ops'
更新engineer2的在swe_bench上的测评脚本

See merge request pub/MetaGPT!370
2024-09-10 02:22:29 +00:00
黄伟韬
6365995f71 remove requirements_constraints 2024-09-09 20:48:42 +08:00
duyipan
af41f1f1cf Update README.md add aide setup and run 2024-09-09 11:26:23 +00:00
黄伟韬
a34394e66f Reinforce the default programming languages. 2024-09-09 19:00:52 +08:00
didi
7ffe68b499 重构了Evaluator 2024-09-09 18:19:22 +08:00
黄伟韬
dbefcb9e44 remove requirement analyze 2024-09-09 17:39:30 +08:00
didi
4e0a896bdc 提交baseline例子;修改context-fill 格式识别方式 2024-09-09 17:17:15 +08:00
Yizhou Chi
294d0fe709 fix nbclient 2024-09-09 16:59:39 +08:00
Yizhou Chi
9ba0d217fc update mcts logic 2024-09-09 14:52:25 +08:00
seehi
31dbff5474 Keep user and AI messages are paired 2024-09-09 14:24:03 +08:00
林义章
e3fccce73d Merge branch 'experimenter' into 'expo'
Experimenter Update

See merge request agents/exp_optimizer!5
2024-09-09 06:13:07 +00:00
seehi
047f1e429d Keep user and AI messages are paired 2024-09-09 14:02:26 +08:00
Yizhou Chi
401ca97846 update dataset.py 2024-09-09 13:54:09 +08:00
Yizhou Chi
93ff1f8f2b update datasets.yaml 2024-09-09 13:50:36 +08:00
Yizhou Chi
72dd44ae32 add ds agent's datasets 2024-09-09 13:47:59 +08:00
Yizhou Chi
9728b3a891 add greedy to run_experiment; add save_notebook to experimenter.py 2024-09-09 13:44:38 +08:00
seehi
e2600c0a64 update comment 2024-09-09 11:17:41 +08:00
seehi
1797fdc1f8 fix conflict 2024-09-09 11:01:30 +08:00
黄伟韬
5eb3a2120e update run_swe_agent_benchmark 2024-09-09 10:53:50 +08:00
张雷
fdf2a0edf6 Merge branch 'feature/rfc258_editor' into 'mgx_ops'
feat: +Editor Index Repo search api

See merge request pub/MetaGPT!366
2024-09-09 02:25:37 +00:00
didi
ca560a844f 合入Eval与Optimize
当前问题
1. eval 存在部分参数差异(path,csv测试)
2. optimize 尝试新流程(优化后的optimize曲线);optimize 模版书写
3. optimize 在各个数据集上跑通
4. 创建baseline folder
5. 创建experiment data收集方法
6. 从ags中移出
2024-09-08 23:04:01 +08:00
黄伟韬
d4841827b3 Merge branch 'add_swe_agent_ablilities_to_engineer2' into run_swe_agent_benchmark_script 2024-09-06 20:01:12 +08:00
黄伟韬
78bfc9b289 update run_swe_agent_benchmark 2024-09-06 20:00:24 +08:00
Yizhou Chi
df6fe9854d fix dataset bug 2024-09-06 19:27:36 +08:00
Yizhou Chi
c0262bcd8f 1. add support to hf dataset
2. add support to datasets that have both train and test
3. create data folder
4. fix new instruction bug
2024-09-06 19:05:10 +08:00
莘权 马
85c1d07990 refactor: cross_repo_search 2024-09-06 18:31:11 +08:00
黄伟韬
291615bac6 update swe_bench script 2024-09-06 18:13:48 +08:00
Yizhou Chi
376d1b7661 allow new instruction even if there's no insights 2024-09-06 17:02:49 +08:00
林义章
8d93f5750c Merge branch 'add_swe_agent_ablilities_to_engineer2' into 'mgx_ops'
Add swe agent ablilities to engineer2

See merge request pub/MetaGPT!356
2024-09-06 08:52:49 +00:00
莘权 马
6a57cb5e0a feat: search_index_repo path or filename 2024-09-06 15:35:47 +08:00
黄伟韬
6e49c2475f update comment 2024-09-06 14:33:09 +08:00
Yizhou Chi
6d40ec463f update result key 2024-09-06 14:18:04 +08:00
黄伟韬
a68f9efce5 Remove duplicate '_act' in engineer. 2024-09-06 14:08:04 +08:00
Yizhou Chi
a6f71f4498 1. avoid circular reference
2. add greedy
2024-09-06 13:09:18 +08:00
黄伟韬
4063186836 update run_swe_bechmark script 2024-09-06 12:04:40 +08:00
seehi
53ef7be68c update comment 2024-09-06 11:30:49 +08:00
莘权 马
95bf4c3e22 feat: search时不必设置IndexRepo的min/max_token_count 2024-09-06 11:07:31 +08:00