Commit graph

1079 commits

Author SHA1 Message Date
Krrish Dholakia
29d0fcf34a feat(proxy_server.py): supports /audio/transcription endpoint on proxy 2024-03-08 14:28:07 -08:00
ishaan-jaff
b316b49c32 (feat) read passed api_version 2024-03-08 13:16:12 -08:00
Krrish Dholakia
b81c94e94f fix(proxy_server.py): use argon2 for faster api key checking
0.04s latency boost on load test
2024-03-07 21:48:18 -08:00
Krrish Dholakia
3c414c6357 fix(proxy_server.py): fix model alias map + add back testing 2024-03-07 07:56:51 -08:00
Krrish Dholakia
7d2df12733 fix(proxy_server.py): support cost tracking if general_settings is none
works if database_url is in env
2024-03-06 21:27:41 -08:00
Krish Dholakia
ede9647e49 Merge pull request #2377 from BerriAI/litellm_team_level_model_groups
feat(proxy_server.py): team based model aliases
2024-03-06 21:03:53 -08:00
Krrish Dholakia
df0eb170e6 fix(proxy_server.py): fix sql query 2024-03-06 19:41:12 -08:00
Krish Dholakia
050a056e09 Merge pull request #2347 from BerriAI/litellm_retry_rate_limited_requests
feat(proxy_server.py): retry if virtual key is rate limited
2024-03-06 19:23:11 -08:00
Krrish Dholakia
7bfadc258e feat(proxy_server.py): team based model aliases
allow setting model aliases at a team level (e.g. route all 'gpt-3.5-turbo' requests from team-1 to model-deployment-group-2)
2024-03-06 17:42:08 -08:00
ishaan-jaff
b6f3eb1434 (fix) remove unuse endpoint 2024-03-06 15:40:22 -08:00
ishaan-jaff
b0575bdcf0 (fix) admin UI swagger 2024-03-06 14:01:39 -08:00
ishaan-jaff
086de85625 (fix) update team_id 2024-03-05 19:09:19 -08:00
ishaan-jaff
3ca856fe39 (fix) _update_team_db 2024-03-05 19:03:27 -08:00
Krrish Dholakia
c963e2761b feat(proxy_server.py): retry if virtual key is rate limited
currently for chat completions
2024-03-05 19:00:03 -08:00
ishaan-jaff
a513a05a7f (fix) fix batch update user db 2024-03-05 16:46:58 -08:00
ishaan-jaff
7a72aa8796 (feat) show /model/metrics on Admin UI 2024-03-04 16:25:35 -08:00
ishaan-jaff
d1a3899882 (feat) show model metrics on admin panel 2024-03-04 13:44:13 -08:00
Krrish Dholakia
a1ce24c5f0 fix(huggingface_restapi.py): fix huggingface streaming error raising 2024-03-04 09:32:41 -08:00
Krrish Dholakia
82bced7183 fix(proxy/utils.py): fix resetting budget logic 2024-03-02 20:52:54 -08:00
Krrish Dholakia
49ed001cdf fix(proxy_server.py): fix track cost callback 2024-03-02 19:52:45 -08:00
Krish Dholakia
cbeb65a442 Merge branch 'main' into litellm_slack_budget_alerting 2024-03-02 19:13:57 -08:00
Krrish Dholakia
6126deb7dd fix(proxy_server.py): fix budget creation 2024-03-02 19:11:37 -08:00
Krish Dholakia
46ec94ec3c Merge pull request #2300 from BerriAI/litellm_organization_table
feat(proxy_server.py): enable `/organizations/new`, `/organization/info` and `/budget/info` endpoints
2024-03-02 18:37:36 -08:00
Krrish Dholakia
5e37a24a36 fix(proxy_server.py): actual implementation of slack soft budget alerting 2024-03-02 18:34:18 -08:00
ishaan-jaff
32aa2b0168 (feat) improve test slack alert 2024-03-02 17:33:31 -08:00
ishaan-jaff
31108d3cde (fix) prisma test 2024-03-02 17:15:27 -08:00
ishaan-jaff
c64775302f (proxy) test budgets 2024-03-02 16:57:35 -08:00
Ishaan Jaff
76c07a41e7 Merge branch 'main' into litellm_test_slack_alerts 2024-03-02 16:49:12 -08:00
ishaan-jaff
8cb342ab6a (feat) improve error for testing slack 2024-03-02 16:46:20 -08:00
Krish Dholakia
84e45b385d Merge branch 'main' into litellm_organization_table 2024-03-02 16:09:28 -08:00
Krrish Dholakia
52efd985ed refactor(proxy_server.py): format the message for slack budget alerts 2024-03-02 16:04:36 -08:00
Krrish Dholakia
1bba73bb6c fix(proxy_server.py): raise 422 error if no slack connection setup when calling /health/services 2024-03-02 15:56:42 -08:00
Krrish Dholakia
6d87c9bb7d feat: enable user to test slack budget alerting when creating a key 2024-03-02 15:54:46 -08:00
Krrish Dholakia
56f1d5454b feat(proxy_server.py): exposes /organization/info and /budget/info endpoints 2024-03-02 15:07:33 -08:00
ishaan-jaff
30dadf4214 (feat) set soft_budget with /key/generate 2024-03-02 14:43:01 -08:00
Krrish Dholakia
b5af007676 fix(proxy_server.py): enable admin to create new budget if none set for org 2024-03-02 14:38:42 -08:00
ishaan-jaff
ad496aac10 (docs) setting soft budgets 2024-03-02 13:05:00 -08:00
ishaan-jaff
8b8cba64aa (feat) create soft budget 2024-03-02 12:52:09 -08:00
Krrish Dholakia
72897b0ba9 fix(proxy_server.py): fix pydantic versioning issue 2024-03-02 12:01:05 -08:00
Krrish Dholakia
2c7807c56e feat(proxy_server.py): enable /organizations/new endpoint
allows admins to create organizations which can own teams
2024-03-02 11:55:16 -08:00
ishaan-jaff
5d7bd2961e (feat) cleanup 2024-03-02 11:09:40 -08:00
Krrish Dholakia
cce4effa77 build(ui): enable seeing top spending end users for a given api key 2024-03-01 20:47:19 -08:00
Krish Dholakia
e1fbb871fb Merge pull request #2287 from BerriAI/litellm_end_user_per_key_spend
feat(proxy_server.py): return top 100 end users for a given key
2024-03-01 19:51:56 -08:00
Krrish Dholakia
e8d8c18520 feat(proxy_server.py): return top 100 end users for a given key 2024-03-01 19:13:24 -08:00
Krish Dholakia
22c01afa1c Merge pull request #2277 from BerriAI/litellm_team_member_delete
feat(proxy_server.py): add new team_member delete endpoint
2024-03-01 11:50:16 -08:00
ishaan-jaff
3580fdb08e (feat) predict spend 2024-03-01 09:28:22 -08:00
Krrish Dholakia
a60ff95011 feat(proxy_server.py): add new team_member delete endpoint 2024-03-01 09:14:08 -08:00
ishaan-jaff
be53e27c50 (feat) /predict/spend endpoint 2024-03-01 08:20:35 -08:00
Krish Dholakia
cd33e318c8 Merge branch 'main' into litellm_end_user_spend_tracking 2024-02-29 19:31:19 -08:00
ishaan-jaff
842f3cf89c (feat) use daily spend metric 2024-02-29 18:18:40 -08:00