1753 commits

Author	SHA1	Message	Date
Krrish Dholakia	8843b0dc77	feat(dynamic_rate_limiter.py): working e2e	2024-06-22 14:41:22 -07:00
Ishaan Jaff	0960f8cfd5	use hash of master key encode the jwt	2024-06-22 08:58:31 -07:00
Ishaan Jaff	7065c9838f	ui - use cookies to return JWTs	2024-06-22 08:50:26 -07:00
Krrish Dholakia	8f95381276	refactor: instrument 'dynamic_rate_limiting' callback on proxy	2024-06-22 00:32:29 -07:00
Ishaan Jaff	aa3f2b3cf9	fix cost tracking by tags	2024-06-21 16:49:57 -07:00
Ishaan Jaff	f4db69a275	fix - /moderation don't require a model	2024-06-21 16:00:43 -07:00
Ishaan Jaff	7cba8f6de5	backend - new endpoint to show cache hit stats	2024-06-21 13:08:54 -07:00
Ishaan Jaff	5dd5cc7d87	fix refactor - add batches endpoints proxy server.py	2024-06-21 07:55:53 -07:00
Ishaan Jaff	a428857d95	Merge pull request #4322 from BerriAI/litellm_bug_fix_spend_tracking ... [Fix] user field and user_api_key_* is sometimes omitted randomly	2024-06-20 21:10:13 -07:00
Ishaan Jaff	beb67dca38	fix update_cache function	2024-06-20 17:27:25 -07:00
Ishaan Jaff	e7180dc624	fix don't store bad api key in user api key cache	2024-06-20 16:55:12 -07:00
Krrish Dholakia	477ed99896	feat(router.py): allow user to call specific deployment via id ... Allows easier health checks for specific deployments by just passing in model id	2024-06-19 13:02:46 -07:00
Krish Dholakia	ea2f27e472	Merge branch 'main' into litellm_aws_kms_fixes	2024-06-19 09:30:54 -07:00
Krrish Dholakia	aeeaadfaa6	fix(router.py): support adding models across multiple orgs, with 1 model definition	2024-06-18 19:57:10 -07:00
Krrish Dholakia	6fcad5f199	fix(proxy_server.py): track team spend for cached team object ... fixes issue where team budgets for jwt tokens weren't asserted	2024-06-18 17:10:12 -07:00
John HU	ec5e26a848	fix: strip llm credential before returning	2024-06-17 12:14:40 -07:00
Ishaan Jaff	b7c5700b54	fix- refactor proxy place internal user endpoints in sep file	2024-06-15 16:39:06 -07:00
Ishaan Jaff	a9649c0860	Merge pull request #4217 from BerriAI/litellm_refactor_proxy_server ... [Refactor-Proxy] Make proxy_server.py < 10K lines (move management, key, endpoints to their own files)	2024-06-15 16:27:31 -07:00
Ishaan Jaff	f3a7c52f60	fix - non sso ui sign up flow	2024-06-15 15:26:44 -07:00
Ishaan Jaff	abb544190a	fix - refactor key endpoints	2024-06-15 14:13:32 -07:00
Ishaan Jaff	9b655c9ef7	use directories for importing new endpoints	2024-06-15 13:35:21 -07:00
Ishaan Jaff	0f8dbe5ed4	refactor health endpoints	2024-06-15 12:39:04 -07:00
Ishaan Jaff	2dcc484e5d	fix swagger	2024-06-15 12:22:16 -07:00
Ishaan Jaff	b1599c3f40	refactor spend endpoints	2024-06-15 12:17:33 -07:00
Ishaan Jaff	749af8278b	fix test	2024-06-15 11:46:15 -07:00
Ishaan Jaff	897f6bc7ea	feat - refactor team endpoints	2024-06-15 11:40:36 -07:00
Ishaan Jaff	4bc2bfb176	fix - proxy refactor user_api_key_auth	2024-06-15 10:33:58 -07:00
Ishaan Jaff	f16a9a6d92	fix send emails to team members	2024-06-14 20:11:16 -07:00
Ishaan Jaff	3c56bfbc5a	send team_alias on team budget alerts	2024-06-14 17:00:43 -07:00
Krish Dholakia	c373f104cc	Merge branch 'main' into litellm_redis_cache_usage	2024-06-13 22:07:21 -07:00
Ishaan Jaff	31e89bf48b	update swagger for /team endpoints	2024-06-13 20:55:50 -07:00
Ishaan Jaff	18c89a0dd7	fix /team/update	2024-06-13 20:55:50 -07:00
Ishaan Jaff	ffe3df74e6	fix bug when updating team	2024-06-13 20:55:49 -07:00
Ishaan Jaff	0d822af00b	fix - clean up swagger spend endpoints	2024-06-13 20:55:49 -07:00
Krrish Dholakia	b580e0992d	fix(utils.py): check if model info is for model with correct provider ... Fixes issue where incorrect pricing was used for custom llm provider	2024-06-13 15:54:24 -07:00
Ishaan Jaff	c55a68a9da	fix "/global/spend/report",	2024-06-13 08:51:49 -07:00
Ishaan Jaff	de0e37ebfb	feat - litellm_model_cost_map	2024-06-12 20:03:46 -07:00
Ishaan Jaff	be7340c5a9	fix - sso pass correct role for user	2024-06-12 19:37:58 -07:00
Ishaan Jaff	67938564b4	fix - comment on /user/new	2024-06-12 13:16:39 -07:00
Krrish Dholakia	77328e4a28	fix(parallel_request_limiter.py): use redis cache, if available for rate limiting across instances ... Fixes https://github.com/BerriAI/litellm/issues/4148	2024-06-12 10:35:48 -07:00
Ishaan Jaff	206791f166	Merge pull request #4138 from BerriAI/litellm_log_management_endpoint_logs_otel ... [FEAT] log management endpoint logs to otel	2024-06-11 19:00:13 -07:00
Krrish Dholakia	499c4fca9f	refactor(proxy_server.py): cleanup sensitive key debug log	2024-06-11 18:45:12 -07:00
Krish Dholakia	30d269f93a	Merge pull request #4139 from BerriAI/litellm_fix_budget_exceeded_error_code ... fix(proxy_server.py): use consistent 400-status code error code for exceeded budget errors	2024-06-11 18:36:58 -07:00
Ishaan Jaff	8c63e6e493	fix linting error	2024-06-11 18:14:06 -07:00
Ishaan Jaff	f9fd962191	fix team endpoints	2024-06-11 18:10:20 -07:00
Ishaan Jaff	5d5d02156a	fix - log mgmt data to OTEL	2024-06-11 18:05:10 -07:00
Ishaan Jaff	5f078edc13	fix http_request	2024-06-11 17:57:50 -07:00
Ishaan Jaff	714b4ee59d	fix test new team	2024-06-11 17:48:11 -07:00
Krrish Dholakia	85c9ff6783	fix: more bug fixes	2024-06-11 17:41:59 -07:00
Ishaan Jaff	4859244e67	feat - otel log /team exceptions	2024-06-11 16:27:07 -07:00