1853 commits

Author	SHA1	Message	Date
Krish Dholakia	67973e5344	Merge pull request #3910 from BerriAI/litellm_fix_end_user_max_budget ... fix(proxy_server.py): fix end user object check when master key used	2024-05-29 18:04:56 -07:00
Ishaan Jaff	b7fcec8835	fix batch tags	2024-05-29 17:51:39 -07:00
Ishaan Jaff	ea30769190	Merge pull request #3897 from BerriAI/litellm_fix_latency_cal ... ui - fix latency analytics on `completion_tokens`	2024-05-29 17:32:17 -07:00
Ishaan Jaff	f9b98c57a2	Merge pull request #3894 from BerriAI/litellm_update_analytics_tab ... [Feat] UI update analytics tab to show human friendly usage vals	2024-05-29 17:31:21 -07:00
Krrish Dholakia	cfcf5969c8	fix(proxy_server.py): fix end user object check when master key used ... check if end user max budget exceeded for master key	2024-05-29 17:20:59 -07:00
Krrish Dholakia	f729370890	feat(proxy_server.py): emit webhook event whenever customer spend is tracked ... Closes https://github.com/BerriAI/litellm/issues/3903	2024-05-29 15:59:32 -07:00
Krrish Dholakia	8f0019c241	docs(customers.md): add customer cost tracking to docs	2024-05-29 14:55:33 -07:00
Ishaan Jaff	02598ae988	fix(proxy_server.py): fix latency calc for avg output token	2024-05-29 09:49:45 -07:00
Ishaan Jaff	e252daaf2b	ui - fix latency analytics completion_tokens	2024-05-29 09:39:53 -07:00
Ishaan Jaff	5958288ebb	fix /global/activity/model	2024-05-29 08:58:25 -07:00
Krish Dholakia	e838bd1c79	Merge branch 'main' into litellm_batch_completions	2024-05-28 22:38:05 -07:00
Ishaan Jaff	6e9cc26ca1	Merge pull request #3888 from BerriAI/litellm_add_files_proxy ... [Feat] LiteLLM Proxy Add `POST /v1/files` and `GET /v1/files`	2024-05-28 22:36:33 -07:00
Krrish Dholakia	1ebae6e7b0	fix(router.py): support comma-separated model list for batch completion fastest response	2024-05-28 21:34:37 -07:00
Krrish Dholakia	20106715d5	feat(proxy_server.py): enable batch completion fastest response calls on proxy ... introduces new `fastest_response` flag for enabling the call	2024-05-28 20:09:31 -07:00
Ishaan Jaff	37e18a42fc	feat - add file endpoints proxy	2024-05-28 20:03:13 -07:00
Krrish Dholakia	bffa79a8c5	feat(proxy_server.py): give request-level breakdown if ttft metric is selected for ju ... st that day	2024-05-28 18:09:22 -07:00
Ishaan Jaff	0020672c19	fear support GET /v1/batches{batch_id}	2024-05-28 17:58:34 -07:00
Ishaan Jaff	c2e24b4ed8	feat add v1/batches	2024-05-28 17:49:36 -07:00
Ishaan Jaff	e6789a0150	fix app mounting ui	2024-05-28 08:14:15 -07:00
Ishaan Jaff	2069e36d1d	Merge pull request #3874 from BerriAI/litellm_make_email_alerts_free ... [Feat] Add, Test Email Alerts on Admin UI	2024-05-28 08:09:14 -07:00
Krrish Dholakia	eee60b0686	fix(proxy_server.py): handle next js route serving on fastapi	2024-05-28 01:09:05 -07:00
Krrish Dholakia	293d5cf1f2	feat: e2e flow complete - admin can invite new users to proxy via invite links ... Completes https://github.com/BerriAI/litellm/issues/3863	2024-05-27 23:19:30 -07:00
Ishaan Jaff	24c80e6bc7	fix - testing email alerting	2024-05-27 22:46:45 -07:00
Krish Dholakia	bcbc250a12	Merge branch 'main' into litellm_invite_users_via_link	2024-05-27 20:36:43 -07:00
Krrish Dholakia	86b66c13a4	feat(proxy_server.py): allow admin to invite users via invite link ... Closes https://github.com/BerriAI/litellm/issues/3863	2024-05-27 20:32:25 -07:00
Ishaan Jaff	e1b46d4b6e	Merge pull request #3870 from BerriAI/litellm_rename_end_user ... [Feat] Rename `/end/user/new` -> `/customer/new` (maintain backwards compatibility)	2024-05-27 19:42:14 -07:00
Ishaan Jaff	0feeb53868	fix - working customer/delete	2024-05-27 19:24:20 -07:00
Krish Dholakia	9c8af6676c	Merge pull request #3869 from BerriAI/litellm_public_model_hubg ... Admin UI - Public model hub	2024-05-27 19:14:11 -07:00
Ishaan Jaff	f588616498	fix - /customer/update	2024-05-27 19:02:20 -07:00
Ishaan Jaff	24f0b82755	feat - add validation for existing customers	2024-05-27 18:29:09 -07:00
Ishaan Jaff	cdf32ebf0e	docs string - > end user /new	2024-05-27 18:20:44 -07:00
Ishaan Jaff	9b8c143601	feat - rename end_user -> customer	2024-05-27 18:17:46 -07:00
Krrish Dholakia	4516daec90	feat(model_hub.tsx): enable admin to expose a public model hub	2024-05-27 17:45:45 -07:00
Ishaan Jaff	d71bb96047	Merge pull request #3868 from BerriAI/litellm_show_updated_created_models ... [Feat] Show Created at, Created by on `Models` Page	2024-05-27 16:32:29 -07:00
Ishaan Jaff	ef7f3bc4fe	backend - add audit logs for adding models	2024-05-27 16:29:51 -07:00
Ishaan Jaff	eccda76edc	router - include updated at and created at in model info	2024-05-27 15:53:16 -07:00
Ishaan Jaff	ce41778b6f	fix - show activity by model_group	2024-05-27 11:25:16 -07:00
Krrish Dholakia	4408b717f0	fix(parallel_request_limiter.py): fix user+team tpm/rpm limit check ... Closes https://github.com/BerriAI/litellm/issues/3788	2024-05-27 08:48:23 -07:00
Krrish Dholakia	22b6b99b34	feat(proxy_server.py): expose new /model_group/info endpoint ... returns model-group level info on supported params, max tokens, pricing, etc.	2024-05-26 14:07:35 -07:00
Krrish Dholakia	01adeda2e4	build(ui): add enterprise cta	2024-05-25 21:41:53 -07:00
Krish Dholakia	4e230f0a2e	Merge pull request #3844 from BerriAI/litellm_region_based_alerts ... feat(slack_alerting.py): enable provider-region based alerting	2024-05-25 21:03:16 -07:00
Krrish Dholakia	a9a1447513	feat(ui): allow admin to configure slack alerting thresholds on ui	2024-05-25 21:01:19 -07:00
Ishaan Jaff	e4053b6732	Merge pull request #3842 from BerriAI/litellm_set_budget_dur ... [Fix] Set budget_duration on `/team/new` and `/team/update`	2024-05-25 16:31:39 -07:00
Ishaan Jaff	6ec0efab50	fix - test team_alias	2024-05-25 15:42:52 -07:00
Ishaan Jaff	e2d3c0c846	fix - updating team	2024-05-25 15:31:25 -07:00
Ishaan Jaff	22d8eaab93	test - new_team	2024-05-25 15:20:49 -07:00
Ishaan Jaff	6f65df0b1a	feat - update budget duration	2024-05-25 14:57:29 -07:00
Ishaan Jaff	a03d13fedd	fix - allow setting budget duration and reset at	2024-05-25 14:38:05 -07:00
Ishaan Jaff	bf0c0c08c8	feat - set budget duration	2024-05-25 14:32:08 -07:00
Krish Dholakia	322f89782f	Merge pull request #3839 from BerriAI/litellm_fix_models_endpoint ... fix(proxy_server.py): fix model check for `/v1/models` + `/model/info` endpoint when team has restricted access	2024-05-25 14:23:01 -07:00