7255 commits

Author	SHA1	Message	Date
Ishaan Jaff	5177e4408e	Merge pull request #3651 from BerriAI/litellm_improve_load_balancing ... [Feat] Proxy + router - don't cooldown on 4XX error that are not 429, 408, 401	2024-05-15 10:24:34 -07:00
Ishaan Jaff	f17f0a09d8	feat - router use _is_cooldown_required	2024-05-15 10:03:55 -07:00
Krrish Dholakia	f5d73547c7	fix(lowest_latency.py): allow ttl to be a float	2024-05-15 09:59:21 -07:00
Krrish Dholakia	5dcf3d672c	feat(proxy_server.py): new /end_user/info endpoint ... get spend for a specific end-user	2024-05-15 09:50:52 -07:00
Ishaan Jaff	ae80148c12	test - router cooldowns	2024-05-15 09:43:30 -07:00
Ishaan Jaff	52f8c39bbf	feat - don't cooldown deployment on BadRequestError	2024-05-15 09:03:27 -07:00
Krrish Dholakia	f43da3597d	test: fix test	2024-05-15 08:51:40 -07:00
Krrish Dholakia	fffb2427f3	fix(types/init.py): don't import openai assistants types by default	2024-05-15 08:50:31 -07:00
Krrish Dholakia	51a02de4cf	refactor(proxy_server.py): update doc string for /user/update	2024-05-15 08:25:14 -07:00
Krrish Dholakia	1840919ebd	fix(main.py): testing fix	2024-05-15 08:23:00 -07:00
Krrish Dholakia	8117af664c	fix(huggingface_restapi.py): fix task extraction from model name	2024-05-15 07:28:19 -07:00
Krrish Dholakia	900bb9aba8	test(test_token_counter.py): fix load test	2024-05-15 07:12:43 -07:00
Edwin Jose George	81836ebe5d	fix: custom_llm_provider needs to be set before setting timeout	2024-05-15 22:36:15 +09:30
Krrish Dholakia	4ff0703a31	fix(slack_alerting.py): fix timezone utc issue	2024-05-14 22:54:33 -07:00
Krrish Dholakia	b06f989871	refactor(main.py): trigger new build	2024-05-14 22:46:44 -07:00
Krrish Dholakia	3b5c06747d	refactor(main.py): trigger new build	2024-05-14 22:17:40 -07:00
Krrish Dholakia	54587db402	fix(alerting.py): fix datetime comparison logic	2024-05-14 22:10:09 -07:00
Ishaan Jaff	0bac40b0f2	ci/cd run again	2024-05-14 21:53:14 -07:00
Ishaan Jaff	6290de36df	(ci/cd) run again	2024-05-14 21:39:09 -07:00
Krrish Dholakia	73b6b5e804	test(test_token_counter.py): fix token counting test	2024-05-14 21:35:28 -07:00
Ishaan Jaff	faa58c7938	(ci/cd) run again	2024-05-14 20:45:07 -07:00
Ishaan Jaff	e7af8d61cd	fix check_request_disconnected = None case	2024-05-14 20:38:32 -07:00
Ishaan Jaff	6d1ae5b9c4	(ci/cd) run again	2024-05-14 20:18:12 -07:00
Ishaan Jaff	aaea02dee8	Merge pull request #3640 from BerriAI/litellm_fix_client_side_disconnecting_reqs ... [Feat] Proxy - cancel tasks when fast api request is cancelled	2024-05-14 20:14:42 -07:00
Ishaan Jaff	4466982507	feat - cancel tasks when fast api request is cancelled	2024-05-14 19:58:51 -07:00
Krrish Dholakia	0262c480be	refactor(main.py): trigger new build	2024-05-14 19:52:23 -07:00
Krrish Dholakia	9eee2f3889	docs(prod.md): add 'disable load_dotenv' tutorial to docs	2024-05-14 19:13:22 -07:00
Krrish Dholakia	1ab4974773	fix: disable 'load_dotenv' for prod environments	2024-05-14 19:09:36 -07:00
Krrish Dholakia	298fd9b25c	fix(main.py): ignore model_config param	2024-05-14 19:03:17 -07:00
Krrish Dholakia	6de358cf21	build(model_prices_and_context_window.json): support new gemini 1.5 preview models	2024-05-14 18:40:14 -07:00
Krrish Dholakia	a1dd341ca1	fix(utils.py): default claude-3 to tiktoken (0.8s faster than hf tokenizer)	2024-05-14 18:37:14 -07:00
Krish Dholakia	b04a8d878a	Revert "Logfire Integration"	2024-05-14 17:38:47 -07:00
Krrish Dholakia	c0d701a51e	test(test_config.py): fix linting error	2024-05-14 17:32:31 -07:00
Krrish Dholakia	4e30d7cf5e	build(model_prices_and_context_window.json): add gemini 1.5 flash model info	2024-05-14 17:30:31 -07:00
Krrish Dholakia	dd0b4b8644	fix(utils.py): fix pydantic v1 error	2024-05-14 17:17:20 -07:00
Krrish Dholakia	1db1af1154	fix(types): fix typing	2024-05-14 17:09:36 -07:00
Krrish Dholakia	888c53e774	fix(proxy/_types.py): fix linting errors	2024-05-14 17:02:11 -07:00
Krrish Dholakia	ad7e289802	fix(types/router.py): fix python3.8 typing issue	2024-05-14 16:56:07 -07:00
Krrish Dholakia	b984fba73f	fix(types/router.py): fix arbitrary_types_allowed flag	2024-05-14 16:53:02 -07:00
Krrish Dholakia	e5a1050e8d	fix(types/router.py): fix router pydantic v1 errors	2024-05-14 16:49:55 -07:00
Krrish Dholakia	2b41f09268	fix(utils.py): add lru-cache logic to _select_tokenizer ... speed up tokenizer load times	2024-05-14 16:39:50 -07:00
Krrish Dholakia	811406a2c6	fix(types/completion.py): fix completion configdict pydantic v1 error	2024-05-14 16:39:50 -07:00
Krrish Dholakia	c80efb856b	fix(types/completion.py): linting fixes	2024-05-14 13:19:38 -07:00
Ishaan Jaff	aa1615c757	Merge pull request #3626 from BerriAI/litellm_reset_spend_per_team_api_key ... feat - reset spend per team, api_key [Only Master Key]	2024-05-14 11:49:07 -07:00
Krish Dholakia	adaafd72be	Merge pull request #3599 from taralika/patch-1 ... Ignore 0 failures and 0s latency in daily slack reports	2024-05-14 11:47:46 -07:00
Ishaan Jaff	787c02c8db	fix - return success spend reset	2024-05-14 11:38:39 -07:00
Krrish Dholakia	4f3c7752f9	ci: test linting change for pydantic v1	2024-05-14 11:34:16 -07:00
alisalim17	765c382b2a	Merge remote-tracking branch 'upstream/main'	2024-05-14 22:32:57 +04:00
Ishaan Jaff	ca41e6590e	test - auth on /reset/spend	2024-05-14 11:28:35 -07:00
Krrish Dholakia	f41b2a09a4	fix(utils.py): fix python 3.8 linting error	2024-05-14 11:25:36 -07:00