1950 commits

Author	SHA1	Message	Date
Ishaan Jaff	39ed7dfa5d	fix return service config to get/config/callbacks	2024-04-13 14:34:51 -07:00
Ishaan Jaff	885ae139b8	fix - testing lagfuse service	2024-04-13 13:44:17 -07:00
Ishaan Jaff	ffb1393b94	feat - test langfuse /health/service	2024-04-13 13:42:49 -07:00
Ishaan Jaff	28cc9a11c4	feat - load proxy models on proxy startup events	2024-04-13 13:28:58 -07:00
Ishaan Jaff	d849810445	ui - new build	2024-04-13 12:58:37 -07:00
zJ	a5153377a0	set model_id in db correctly on add	2024-04-13 19:23:14 +02:00
Ishaan Jaff	f0ebadbb6f	test - /health endpoints	2024-04-13 10:09:18 -07:00
Krish Dholakia	fd7760d3db	Merge pull request #2996 from BerriAI/litellm_semaphores ... fix(router.py): initial commit for semaphores on router	2024-04-12 23:23:36 -07:00
Ishaan Jaff	081adf87e3	fix - proxy /health checks	2024-04-12 20:30:15 -07:00
Ishaan Jaff	91d89a7b9b	fix - use copy.deepcopy on /model/info endpoints	2024-04-12 20:17:11 -07:00
Krrish Dholakia	8179596ebc	fix(lowest_tpm_rpm_v2.py): don't fail calls if redis fails to connect	2024-04-12 19:36:59 -07:00
Krrish Dholakia	a4e415b23c	fix(router.py): initial commit for semaphores on router	2024-04-12 17:59:05 -07:00
Krrish Dholakia	74aa230eac	fix(main.py): automatically infer mode for text completion models	2024-04-12 14:16:21 -07:00
Krrish Dholakia	e407ff7ee7	build(ui): allow deleting models from UI + show correct provider in model list	2024-04-12 12:53:22 -07:00
Krrish Dholakia	dc2f57e060	build(ui): allow multi select models when adding them to a model group	2024-04-12 11:48:07 -07:00
Krrish Dholakia	7ee17c97e7	build(ui): dropdown for known provider models	2024-04-12 11:17:09 -07:00
Krrish Dholakia	bdb32a0f42	build(ui): allow setting openai org id when creating new models	2024-04-12 09:34:09 -07:00
Krrish Dholakia	f4c7f4f901	fix(proxy_server.py): support tracking org spend ... currently works when org set for jwt auth	2024-04-11 23:01:21 -07:00
Krish Dholakia	d89644d46c	Merge pull request #2970 from BerriAI/litellm_keys ... fix(handle_jwt.py): User cost tracking via JWT Auth	2024-04-11 21:44:15 -07:00
Krrish Dholakia	77097f8e7d	test(test_jwt.py): add testing to make sure user api key auth returns the expected values	2024-04-11 20:18:55 -07:00
Krrish Dholakia	67b5634417	fix(auth_checks.py): raise error if user doesn't exist in db	2024-04-11 19:55:04 -07:00
Krrish Dholakia	36ff593c02	feat(proxy_server.py): support cost tracking on user id via JWT-Auth ... allows admin to track cost for LiteLLM_UserTable via JWT	2024-04-11 18:47:46 -07:00
Krrish Dholakia	e413191493	fix(handle_jwt.py): support firebase public key format ... adds support for when the public keys are a json instead of nested inside a json	2024-04-11 18:07:13 -07:00
Ishaan Jaff	beabec620e	fix - delete updated keys from cache	2024-04-11 17:21:44 -07:00
Ishaan Jaff	68e0c93246	fix - better debugging for adding new models	2024-04-11 14:49:00 -07:00
Ishaan Jaff	fc832f2196	fix - issue when loading models through ui	2024-04-11 13:06:10 -07:00
Ishaan Jaff	5f95260cf5	ui - show fallback login	2024-04-11 11:48:40 -07:00
Ishaan Jaff	7cb40d3b35	UI - add /fallback/login route	2024-04-11 11:20:41 -07:00
Krrish Dholakia	84d43484c6	fix(router.py): make sure pre call rpm check runs even when model not in model cost map	2024-04-11 09:27:46 -07:00
Ishaan Jaff	96cd038a73	security fix - disable demo accounts	2024-04-11 07:40:34 -07:00
Krish Dholakia	6749306239	Merge pull request #2945 from ushuz/hotfix ... Fix image generation pre call hook call type	2024-04-10 21:53:00 -07:00
Krrish Dholakia	f4d34673d0	fix: update gitignore	2024-04-10 20:56:39 -07:00
Krish Dholakia	83e7ed94ce	Merge pull request #2942 from BerriAI/litellm_fix_router_loading ... Router Async Improvements	2024-04-10 20:16:53 -07:00
Ishaan Jaff	e90645bd5d	fix - setting env vars on proxy	2024-04-10 17:50:28 -07:00
John HU	c9b05828ff	Fix image generation pre call hook call type	2024-04-11 00:18:35 +00:00
Ishaan Jaff	8bc02b34c2	test -base64 cache hits	2024-04-10 16:46:56 -07:00
Krrish Dholakia	180cf9bd5c	feat(lowest_tpm_rpm_v2.py): move to using redis.incr and redis.mget for getting model usage from redis ... makes routing work across multiple instances	2024-04-10 14:56:23 -07:00
Ishaan Jaff	c86213ac98	fix - error on setting env vars	2024-04-10 14:15:40 -07:00
Ishaan Jaff	89ff90bceb	new ui build	2024-04-10 14:06:19 -07:00
Ishaan Jaff	f6fc21e917	fix- user not allowed to access key info	2024-04-10 14:01:03 -07:00
Ishaan Jaff	195840b761	fix - error user not allowed to access info	2024-04-10 13:34:22 -07:00
Krrish Dholakia	b2741933dc	fix(proxy_cli.py): don't double load the router config ... was causing callbacks to be instantiated twice - double couting usage in cache	2024-04-10 13:23:56 -07:00
Ishaan Jaff	a374e83d52	ui - new build	2024-04-10 12:11:12 -07:00
Ishaan Jaff	4bd1aebf8f	Merge pull request #2934 from BerriAI/litellm_ui_setup_sso ... ui - setup sso on admin ui	2024-04-10 12:09:24 -07:00
Ishaan Jaff	25347b1f6f	feat - set env vars on proxy	2024-04-10 11:44:27 -07:00
Krrish Dholakia	5271202a84	build(ui): fix ui runtime error when sso is turned on	2024-04-10 08:54:08 -07:00
Krrish Dholakia	8857c9b978	test(test_key_generate_prisma.py): add better unit testing for spend logs on proxy server	2024-04-09 17:58:18 -07:00
Krrish Dholakia	28940c3b71	fix(proxy_server.py): fixes logging to spend logs db url	2024-04-09 17:38:48 -07:00
Krrish Dholakia	4096118bf5	build(ui): make sure total spend and api keys sum up	2024-04-09 16:20:26 -07:00
Krrish Dholakia	dbbf605653	fix(proxy_server.py): fix sso callback check to work for user email	2024-04-09 14:50:39 -07:00