682 commits

Author	SHA1	Message	Date
Krrish Dholakia	8c6402b02d	docs(routing.md): add pre-call checks to docs	2024-03-23 19:10:34 -07:00
Krrish Dholakia	292cdd81e4	fix(router.py): fix pre call check logic	2024-03-23 18:56:08 -07:00
Krrish Dholakia	4e70a3e09a	feat(router.py): enable pre-call checks ... filter models outside of context window limits of a given message for a model group https://github.com/BerriAI/litellm/issues/872	2024-03-23 18:03:30 -07:00
Krrish Dholakia	0bbc8ac4ad	fix(router.py): add no-proxy support for router	2024-03-14 14:25:30 -07:00
ishaan-jaff	ef7fbcf617	(fix) raising No healthy deployment	2024-03-13 08:00:56 -07:00
Ishaan Jaff	89ef2023e9	Merge branch 'main' into litellm_imp_mem_use	2024-03-11 19:00:56 -07:00
Ishaan Jaff	fa655d62fb	Merge pull request #2461 from BerriAI/litellm_improve_mem_use ... LiteLLM - improve memory utilization - don't use inMemCache on Router	2024-03-11 18:59:57 -07:00
ishaan-jaff	39299d3aa7	(fix) mem usage router.py	2024-03-11 16:52:06 -07:00
ishaan-jaff	b617263860	(fix) improve mem util	2024-03-11 16:22:04 -07:00
Krrish Dholakia	03e8ce938b	fix(router.py): support fallbacks / retries with sync embedding calls	2024-03-11 14:51:22 -07:00
Krrish Dholakia	a97e8a9029	fix(router.py): add more debug logs	2024-03-11 12:34:35 -07:00
Ishaan Jaff	3f520d8c93	Merge pull request #2416 from BerriAI/litellm_use_consistent_port ... (docs) LiteLLM Proxy - use port 4000 in examples	2024-03-09 16:32:08 -08:00
ishaan-jaff	9e1d089770	(docs) use port 4000	2024-03-08 21:59:00 -08:00
Krrish Dholakia	aca37d3bc5	test(test_whisper.py): add testing for load balancing whisper endpoints on router	2024-03-08 14:19:37 -08:00
Krrish Dholakia	93e9781d37	feat(router.py): add load balancing for async transcription calls	2024-03-08 13:58:15 -08:00
ishaan-jaff	f1cc47e6dc	(fix) show latency per deployment on router debug logs	2024-03-07 18:50:45 -08:00
ishaan-jaff	db002315e3	(feat) print debug info per deployment	2024-03-07 18:33:09 -08:00
Krrish Dholakia	bcfb113b22	fix(router.py): fix text completion error logging	2024-02-24 10:46:59 -08:00
Krrish Dholakia	21f2d9ce59	fix(router.py): mask the api key in debug statements on router	2024-02-21 18:13:03 -08:00
Krrish Dholakia	2796f1c61c	fix(router.py): fix debug log	2024-02-21 08:45:42 -08:00
ishaan-jaff	6c1c2e8c7d	(feat) add moderation on router	2024-02-14 11:00:09 -08:00
ishaan-jaff	cd9005d6e6	(feat) support timeout on bedrock	2024-02-09 17:42:17 -08:00
ishaan-jaff	d5af088f12	(feat) log model_info in router metadata	2024-02-07 15:44:28 -08:00
Krish Dholakia	058813da76	Merge branch 'main' into litellm_http_proxy_support	2024-02-01 09:18:50 -08:00
Krrish Dholakia	96c630a740	fix(router.py): remove wrapping of router.completion() let clients handle this	2024-01-30 21:12:41 -08:00
ishaan-jaff	2806a2e99f	(fix) use OpenAI organization in ahealth_check	2024-01-30 11:45:22 -08:00
ishaan-jaff	463ad30d84	(router) set organization OpenAI	2024-01-30 10:54:05 -08:00
Ishaan Jaff	5f96228ced	Merge pull request #1534 from BerriAI/litellm_custom_cooldown_times ... [Feat] Litellm.Router set custom cooldown times	2024-01-23 08:05:59 -08:00
ishaan-jaff	98e7aac672	(fix) router - update model_group on fallback	2024-01-23 08:04:29 -08:00
ishaan-jaff	8305516d66	(fix) revert router.py to stable version	2024-01-23 08:03:29 -08:00
ishaan-jaff	bc93a554db	Revert "(feat) add typehints for litellm.acompletion" ... This reverts commit a9cf6cec80.	2024-01-23 07:57:09 -08:00
ishaan-jaff	1bb73b0926	Revert "v0" ... This reverts commit b730482aaf.	2024-01-23 07:54:02 -08:00
Krrish Dholakia	e996e17e18	fix(router.py): fix dereferencing param order	2024-01-23 07:19:37 -08:00
Krrish Dholakia	2912c3dcbb	fix(router.py): ensure no unsupported args are passed to completion()	2024-01-22 22:33:06 -08:00
Krrish Dholakia	9aaec44dff	fix(router.py): fix client init	2024-01-22 22:15:39 -08:00
Krrish Dholakia	29fe97b6a9	fix(router.py): fix order of dereferenced dictionaries	2024-01-22 21:42:25 -08:00
ishaan-jaff	038495d452	(fix) router - update model_group on fallback	2024-01-22 14:41:55 -08:00
Ishaan Jaff	8fcf9d0a69	Merge pull request #1534 from BerriAI/litellm_custom_cooldown_times ... [Feat] Litellm.Router set custom cooldown times	2024-01-19 20:49:17 -08:00
ishaan-jaff	e55afeeafe	(fix) router - timeout exception mapping	2024-01-19 20:30:41 -08:00
ishaan-jaff	8aa682bbfb	(feat) router - set custom cooldown times	2024-01-19 19:43:41 -08:00
ishaan-jaff	91b3035165	(fix) add router typehints	2024-01-19 16:32:43 -08:00
ishaan-jaff	739895cc9d	(feat) add typehints for litellm.acompletion	2024-01-19 16:05:26 -08:00
ishaan-jaff	c1d5a65a12	v0	2024-01-19 15:49:37 -08:00
ishaan-jaff	00adee75c5	(feat) - improve router logging/debugging messages	2024-01-19 13:57:33 -08:00
ishaan-jaff	ea3fe0124c	(feat) improve litellm.Router logging	2024-01-19 12:28:51 -08:00
Krrish Dholakia	b0a8976684	fix(router.py): support http and https proxys	2024-01-18 09:58:41 -08:00
ishaan-jaff	d80ae8b9bb	(feat) set Azure vision enhancement params using os.environ	2024-01-17 21:23:40 -08:00
ishaan-jaff	fcc387358a	(feat) litellm router - Azure, use base_url when set	2024-01-17 10:24:30 -08:00
Krrish Dholakia	da2af9f45e	fix(router.py): bump httpx pool limits	2024-01-11 12:51:29 +05:30
Krrish Dholakia	f288b12411	fix(lowest_latency.py): add back tpm/rpm checks, configurable time window	2024-01-10 20:52:01 +05:30