Commit graph

1644 commits

Author SHA1 Message Date
Ishaan Jaff
fcaa4408c0 feat - spend by provider on UI 2024-05-25 08:36:53 -07:00
Ishaan Jaff
b78ddfc5e4 feat - backend - view spend by provider 2024-05-25 08:13:48 -07:00
Ishaan Jaff
d3a8306952 Merge branch 'main' into litellm_send_alerts_making_new_key 2024-05-24 20:42:17 -07:00
Krrish Dholakia
d2d5e2d389 feat(ui): settings.tsx
enable/disable outage alerts on admin ui
2024-05-24 20:04:15 -07:00
Krish Dholakia
40791ee1f8 Merge pull request #3828 from BerriAI/litellm_outage_alerting
fix(slack_alerting.py): support region based outage alerting
2024-05-24 19:13:17 -07:00
Krrish Dholakia
4536ed6f6e feat(slack_alerting.py): refactor region outage alerting to do model based alerting instead
Unable to extract azure region from api base, makes sense to start with model alerting and then move to region
2024-05-24 19:10:33 -07:00
Ishaan Jaff
b7888bac36 feat - send email on api key created 2024-05-24 18:14:45 -07:00
Ishaan Jaff
35b38bad4c feat - email alerts on /key/generate 2024-05-24 17:33:15 -07:00
Ishaan Jaff
bc47ec4c86 fix - user_id_information 2024-05-24 15:37:36 -07:00
Ishaan Jaff
35a767d52c fix - send email alert when token crossed it's budget 2024-05-24 15:22:28 -07:00
Krrish Dholakia
c441232c62 feat(proxy_server.py): add setup instructions for UI 2024-05-24 08:15:44 -07:00
Krrish Dholakia
c50074a0b7 feat(ui/model_dashboard.tsx): add databricks models via admin ui 2024-05-23 20:28:54 -07:00
Ishaan Jaff
fd0bc03109 feat - enfore enterprise checks 2024-05-23 16:11:30 -07:00
Ishaan Jaff
3e7ec4714d Merge pull request #3803 from BerriAI/litellm_add_lakera_ai
[Feat] Add Lakera AI Prompt Injection Detection
2024-05-23 16:01:24 -07:00
Ishaan Jaff
bd2bdfa01e Merge pull request #3797 from BerriAI/litellm_fix_post_call_streaming_hooks
[Fix]  async_post_call_streaming_hook not triggered on proxy server
2024-05-23 15:35:47 -07:00
Ishaan Jaff
60d2778d69 feat - add lakera ai prompt injection detection 2024-05-23 15:16:46 -07:00
Ishaan Jaff
759852b1b8 feat - add open ai moderations check 2024-05-23 13:08:06 -07:00
Ishaan Jaff
56c2d63d1f feat - async_post_call_streaming_hook 2024-05-23 09:30:53 -07:00
Krrish Dholakia
7eeb8d6251 fix(proxy_server.py): fix admin allowed routes 2024-05-22 20:55:21 -07:00
Ishaan Jaff
0738ffca5b feat - raise exception when creating team_id for exiting team_id 2024-05-22 20:26:56 -07:00
Ishaan Jaff
e2fa0cf79f Merge pull request #3790 from BerriAI/litellm_set_team_member_budgets
[Feat] Set Budgets for Users within a Team
2024-05-22 19:44:04 -07:00
Krrish Dholakia
5571b9f4a3 fix(time_to_first_token.tsx): require enterprise license for usage 2024-05-22 19:20:30 -07:00
Ishaan Jaff
2a5e654b1a feat - update existing_team_member_spend in memory 2024-05-22 18:44:44 -07:00
Ishaan Jaff
181675c6b7 feat - check team member spend, budget 2024-05-22 18:36:39 -07:00
Krish Dholakia
f5ddc5440a Merge pull request #3787 from BerriAI/litellm_set_budgets_ui_2
feat(proxy_server.py): enable admin to set tpm/rpm limits for end-users via UI
2024-05-22 18:22:51 -07:00
Krish Dholakia
8e0825295f Merge pull request #3789 from BerriAI/litellm_ttft_ui
feat(schema.prisma): store model id + model group as part of spend logs allows precise model metrics
2024-05-22 18:22:39 -07:00
Krrish Dholakia
9c6eb643f8 fix(proxy_server.py): fix model metrics to return slow responses based on model group 2024-05-22 18:21:27 -07:00
Krrish Dholakia
06606dc01b feat(ui/time_to_first_token.tsx): add time to first token card to model metrics 2024-05-22 18:09:53 -07:00
Ishaan Jaff
5a013fb7be feat - update team+user_id spend 2024-05-22 17:49:54 -07:00
Ishaan Jaff
e22cfa55c4 feat - create budgets when team/member_add 2024-05-22 17:16:19 -07:00
Krrish Dholakia
5c0cb8c326 feat(proxy_server.py): enable admin to create/delete budgets for end-users 2024-05-22 16:20:06 -07:00
Ishaan Jaff
b391755c43 fix - run tpm / rpm checks on proxy admin keys too 2024-05-22 16:15:09 -07:00
Ishaan Jaff
6aa41e1698 feat - enforce end user tpm / rpm limits 2024-05-22 15:45:30 -07:00
Krrish Dholakia
7da614f3b7 feat(proxy_server.py): new 'add budget' endpoint
create a budget object (max budget, tpm /rpm limits, etc.) and assign that to a user/team/etc.
2024-05-22 13:16:37 -07:00
Ishaan Jaff
77cd332115 feat -add failure callbacks from DB to proxy 2024-05-21 22:00:36 -07:00
Ishaan Jaff
087e68c690 feat - create keys with permissions 2024-05-21 18:04:17 -07:00
Ishaan Jaff
383c928d59 Merge pull request #3750 from BerriAI/litellm_raise_exception_when_deleting_updating_team
[Fix] - raise Exception when trying to update/delete a non-existent team
2024-05-20 18:42:27 -07:00
Krish Dholakia
f3a47e4b1a Merge branch 'main' into litellm_webhook_support 2024-05-20 18:41:58 -07:00
Ishaan Jaff
f1dd893e83 Merge pull request #3749 from BerriAI/litellm_raise_404_when_team_not_exist
[Fix] - raise 404 from `/team/info`  when team does not exist
2024-05-20 17:52:43 -07:00
Krish Dholakia
db77e41833 Merge pull request #3740 from BerriAI/litellm_return_rejected_response
feat(proxy_server.py): allow admin to return rejected response as string to user
2024-05-20 17:48:21 -07:00
Krrish Dholakia
c6b4ad247b fix(proxy_server.py): fix error string 2024-05-20 17:37:41 -07:00
Ishaan Jaff
df89da8573 fix - raise Exception when trying to update/delete a non-existtent team 2024-05-20 17:36:08 -07:00
Ishaan Jaff
f94349297c fix - raise 404 when team does not exist 2024-05-20 17:14:03 -07:00
Krrish Dholakia
fd13a830ab fix(slack_alerting.py): cleanup webhook event 2024-05-20 16:55:01 -07:00
Ishaan Jaff
508bff13ab fix - revert check_request_disconnection 2024-05-20 15:43:29 -07:00
Krrish Dholakia
c0d5e83570 feat(slack_alerting.py): support webhook for budget alerts
Closes https://github.com/BerriAI/litellm/issues/3743
2024-05-20 15:30:56 -07:00
Ishaan Jaff
4f3a90bb2e Merge pull request #3742 from BerriAI/litellm_enforce_sso
[Feat] Enforce user has a valid license when using SSO on LiteLLM Proxy
2024-05-20 14:07:23 -07:00
Ishaan Jaff
9d2f60079d fix error on enforce sso 2024-05-20 13:02:56 -07:00
Ishaan Jaff
77ac6d9b74 feat - enforce sso on Admin UI 2024-05-20 12:54:08 -07:00
Ishaan Jaff
44c998293d only run check_request_disconnection logic for 10 mins 2024-05-20 12:39:03 -07:00