Commit Graph

9514 Commits

Author SHA1 Message Date
Ishaan Jaff f2dfd1ebe8 fix stable releases 2024-04-03 15:03:54 -07:00
Ishaan Jaff ca77766a58 fix -stable releases 2024-04-03 15:00:37 -07:00
Ishaan Jaff 47fceb9e5d fix main-stable 2024-04-03 14:59:39 -07:00
Ishaan Jaff 79441d01c0 use original deploy 2024-04-03 14:48:51 -07:00
Ishaan Jaff f37322ed10 use -stable in releases 2024-04-03 14:39:19 -07:00
Ishaan Jaff 1f39acb569 use -stable in releases 2024-04-03 14:37:11 -07:00
Ishaan Jaff 7ad4752b87 fix use main-stable 2024-04-03 14:30:11 -07:00
Ishaan Jaff 42bba87839 fix use main-stable correctly 2024-04-03 14:30:03 -07:00
Ishaan Jaff 4005cfd098 use stable releases 2024-04-03 14:27:33 -07:00
Krrish Dholakia 24d9fcb32c fix(lunary.py): move parse_version to inside lunarylogger v1.34.21-stable 2024-04-03 13:52:42 -07:00
Krrish Dholakia fcaa452ccd feat(prometheus.py): track team based metrics on prometheus 2024-04-03 13:43:21 -07:00
Krrish Dholakia cbe4aa386b docs(token_auth.md): update links 2024-04-03 13:23:30 -07:00
Krrish Dholakia 06b7d2608e docs(token_auth.md): update docs 2024-04-03 13:21:25 -07:00
Krrish Dholakia 15e0099948 fix(proxy_server.py): return original model response via response headers - /v1/completions
to help devs with debugging
2024-04-03 13:05:43 -07:00
Krrish Dholakia f17dd68df3 test(test_text_completion.py): unit testing for text completion pydantic object 2024-04-03 12:26:51 -07:00
Krish Dholakia 4a1b2704c2 Merge pull request #2711 from YiShiYiYuan/main
🐞 fix: djl vllm support
2024-04-03 09:41:46 -07:00
Krrish Dholakia 6d32323e3d fix(proxy_cli.py): revert db timeout change - user-controllable param
db timeout is a user controllable param, not necessary to change defaults
2024-04-03 09:37:57 -07:00
Krrish Dholakia f07500c5ea fix(proxy_server.py): bump default db timeouts 2024-04-03 09:35:08 -07:00
Krrish Dholakia 2559d46c9d fix(_types.py): make /metrics public 2024-04-03 09:17:40 -07:00
Krrish Dholakia 2dee6cdd87 bump: version 1.34.22 → 1.34.23 2024-04-03 08:01:42 -07:00
Krrish Dholakia a26732e710 refactor(main.py): trigger new build 2024-04-03 08:01:26 -07:00
Krrish Dholakia 88e8f14b69 fix(main.py): support async calls from azure_text 2024-04-03 07:59:32 -07:00
Ishaan Jaff d7fda60889 Merge pull request #2816 from BerriAI/litellm_ui_fix_viewing_spend
UI Bug fix - Unable to generate keys / start UI
2024-04-03 07:57:58 -07:00
Krrish Dholakia 8f24202c83 fix(proxy_server.py): support calling public endpoints when jwt_auth is enabled 2024-04-03 07:56:53 -07:00
Ishaan Jaff 51d6e94cee new ui build 2024-04-03 07:56:29 -07:00
Ishaan Jaff 4439367fc5 fix bug when viewing spend on ui 2024-04-03 07:55:07 -07:00
Ishaan Jaff 7079fb382c bump: version 1.34.21 → 1.34.22 v1.34.22 2024-04-02 21:50:47 -07:00
Ishaan Jaff 2d2f570847 new ui build 2024-04-02 21:49:36 -07:00
Ishaan Jaff 326f95244a Merge pull request #2809 from BerriAI/ui_use_token_id_in_key_gen
[UI] QA Fix Edit Key flow - return `token_id` in /key/generate respose
2024-04-02 21:48:40 -07:00
Ishaan Jaff 4d76ec43ac Merge pull request #2808 from BerriAI/litellm_use_all_proxy_team_models_auth
[feat] use `all-proxy-models` and `all-team-models` with Admin UI
2024-04-02 21:48:30 -07:00
Ishaan Jaff 8a8233e428 fix safe use token id 2024-04-02 21:40:35 -07:00
Ishaan Jaff 20b479725d fix edit key flow on admin ui 2024-04-02 21:38:18 -07:00
Ishaan Jaff b28109e891 ui fix 2024-04-02 21:33:28 -07:00
Ishaan Jaff 15685a8f53 v0 use token_in /key_generate 2024-04-02 21:31:24 -07:00
Krrish Dholakia b5ca4cc235 test(test_update_spend.py): fix test with right init 2024-04-02 21:11:26 -07:00
Krish Dholakia 91005e0a5a Merge pull request #2806 from foragerr/fix/model_list2
(fix) Include gemini models in `model_list`
2024-04-02 20:55:31 -07:00
Ishaan Jaff afd81f1609 test new team request 2024-04-02 20:52:16 -07:00
Ishaan Jaff 1aeccf3f0a proxy test all-tea-models 2024-04-02 20:50:47 -07:00
yishiyiyuan 5faa493d35 🐞 fix: djl vllm support
support vllm response format on sagemaker, which only return one choice.
2024-04-03 11:00:51 +08:00
Krrish Dholakia d7601a4844 perf(proxy_server.py): batch write spend logs
reduces prisma client errors, by batch writing spend logs - max 1k logs at a time
2024-04-02 18:46:55 -07:00
Ishaan Jaff c35b4c9b80 (ui) allow settig all proxy models 2024-04-02 18:02:23 -07:00
Ishaan Jaff 203a91864c Merge pull request #2807 from BerriAI/litellm_support_all_team_models_as_ui_alias
UI - use all-team-models as an alias
2024-04-02 17:53:59 -07:00
Ishaan Jaff 21379eb56d Merge pull request #2801 from BerriAI/litellm_support_all_models_as_a_ui_alias
[UI] use all_models alias
2024-04-02 17:53:25 -07:00
Ishaan Jaff 1d2d38b580 ui show all team models 2024-04-02 17:46:07 -07:00
Ishaan Jaff df043eb1fb ui neatly show all proxy models 2024-04-02 17:38:10 -07:00
Ishaan Jaff 6e3ec361ae show all models in red on ui 2024-04-02 17:20:00 -07:00
RaGe c16833e73c (fix) add vertex_language_models to model_list 2024-04-02 20:02:46 -04:00
RaGe a250aedf71 (fix) restore missing comma 2024-04-02 20:02:28 -04:00
Krish Dholakia e453a96c67 Merge pull request #2799 from BerriAI/litellm_fix_text_completion_response
fix(openai.py): return logprobs for text completion calls
2024-04-02 16:23:35 -07:00
Ishaan Jaff 3245d8cdce support all-proxy-models for teams 2024-04-02 16:04:09 -07:00