3793 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
ishaan-jaff	ba9dbbe6d5	(test) router: acompletion + caching	2023-11-23 21:05:48 -08:00
Krrish Dholakia	02464f6661	fix(router.py): use an older version of async for compatibility	2023-11-23 21:00:53 -08:00
ishaan-jaff	39072bd196	(test) proxy - azure/chat/completion test	2023-11-23 20:56:41 -08:00
ishaan-jaff	ca852e1dcd	(fix) caching use model, messages, temp, max_tokens as cache_key	2023-11-23 20:56:41 -08:00
Krrish Dholakia	187403c5cc	fix(router.py): add modelgroup to call metadata	2023-11-23 20:55:49 -08:00
ishaan-jaff	db8ed601b5	(test) temp comment router to test ci/cd	2023-11-23 20:28:43 -08:00
ishaan-jaff	8a72487dcf	(test) proxy_server /chat/completions	2023-11-23 20:28:06 -08:00
Krrish Dholakia	7d221fe863	fix(utils.py): make failure logging sync	2023-11-23 20:19:27 -08:00
ishaan-jaff	31c5b4572b	(fix) proxy: prisma.schema	2023-11-23 20:11:42 -08:00
ishaan-jaff	4816232674	(test) cost tracker	2023-11-23 18:28:37 -08:00
ishaan-jaff	695eaac542	(fix) cost calculator for FT: gpt-3.5	2023-11-23 18:28:21 -08:00
ishaan-jaff	b6f8dbbc0e	(test) caching	2023-11-23 18:17:12 -08:00
ishaan-jaff	3660fb1f7f	(feat) caching: Use seed, max_tokens etc in cache key	2023-11-23 18:17:12 -08:00
Krrish Dholakia	1cf85b4eb9	fix(utils.py): vertex ai api error exception mapping	2023-11-23 17:50:50 -08:00
Krrish Dholakia	94dc3f66f3	fix(utils.py): remove eos token for zephyr models	2023-11-23 17:47:39 -08:00
Krrish Dholakia	f24786095a	fix(vertex_ai.py): fix exception mapping for vertex ai	2023-11-23 17:35:33 -08:00
ishaan-jaff	704af2ca34	(test) testing fix	2023-11-23 17:20:22 -08:00
ishaan-jaff	69c6bbd50b	(chore) remove bloat: deprecated api.litellm cache	2023-11-23 17:20:22 -08:00
Krrish Dholakia	2cc6acdeec	docs(routing.md): add docs on fallbacks, caching, retries, timeouts for router	2023-11-23 17:17:18 -08:00
ishaan-jaff	3118101e2c	(test) router: raises exception	2023-11-23 17:09:36 -08:00
ishaan-jaff	3ee141e1e2	(test) cleanup	2023-11-23 17:09:36 -08:00
Krrish Dholakia	abe2a009f9	test(test_completion.py): fix azure read from env variable test	2023-11-23 16:58:07 -08:00
ishaan-jaff	60dab0d700	(test) router: azure pass key in model list	2023-11-23 16:51:52 -08:00
ishaan-jaff	f7a5b31b96	(test) azure test passing key as completion param	2023-11-23 16:51:52 -08:00
Krrish Dholakia	dc17f63d0b	fix(router.py): fix linting errors	2023-11-23 16:50:19 -08:00
Krrish Dholakia	bfaed56ffb	fix(main.py): only set api key to dynamic api key if it's not none	2023-11-23 16:45:44 -08:00
Krrish Dholakia	c273d6f0d6	fix(router.py): add support for context window fallbacks on router	2023-11-23 16:43:02 -08:00
ishaan-jaff	a1bb880872	(test) router raise exceptions	2023-11-23 16:28:19 -08:00
ishaan-jaff	f01865e960	(fix) router	2023-11-23 16:28:19 -08:00
ishaan-jaff	43ae3b94fa	(fix) debugging: viewing raw POST request	2023-11-23 16:28:19 -08:00
Krrish Dholakia	afac42e93a	fix(router.py): enable async completions with model fallbacks	2023-11-23 16:15:57 -08:00
ishaan-jaff	9b53ea4b0f	(feat) proxy: cost tracking per completion request	2023-11-23 16:08:59 -08:00
ishaan-jaff	1365092c89	(test) router: ensure errors are raised	2023-11-23 16:08:59 -08:00
ishaan-jaff	37dedeee04	(fix) debugging: POST request	2023-11-23 16:08:59 -08:00
ishaan-jaff	e8b844abae	(fix) azure: better debugging	2023-11-23 16:08:59 -08:00
ishaan-jaff	525e01824a	(test) ensure exception raised when incorrect key passed	2023-11-23 16:08:59 -08:00
Krrish Dholakia	8ac03e492f	fix(router.py): enable fallbacks for sync completions	2023-11-23 16:06:46 -08:00
ishaan-jaff	bb00595429	(feat) cost: azure gpt + testing	2023-11-23 14:20:48 -08:00
ishaan-jaff	90a9116a17	(test) strict test ft:gpt-3.5 cost calc	2023-11-23 14:11:01 -08:00
ishaan-jaff	46fc8be4c8	(feat) cost tracking ft:gpt-3.5-turbo	2023-11-23 13:58:59 -08:00
ishaan-jaff	da7c07574f	(test) cost calc on azure	2023-11-23 13:50:09 -08:00
ishaan-jaff	5408a40cc8	(feat) cost calc: add azure cost tracking	2023-11-23 13:50:09 -08:00
Krrish Dholakia	c074023e14	fix: fix linting issues	2023-11-23 13:47:43 -08:00
Krrish Dholakia	4f183dc6a0	fix(utils.py): support reading api keys dynamically from the os environment	2023-11-23 13:41:56 -08:00
Krrish Dholakia	87aa36a2ec	fix(caching.py): fix linting issues	2023-11-23 13:21:45 -08:00
Krrish Dholakia	b10102c285	bump: version 1.5.0 → 1.6.0	2023-11-23 13:21:45 -08:00
Krrish Dholakia	8c4e8d6c62	feat(proxy_server.py): add in-memory caching for user api keys	2023-11-23 13:21:45 -08:00
ishaan-jaff	8291f239a4	(feat) proxy server: add spend column	2023-11-23 11:46:59 -08:00
ishaan-jaff	65d978622d	(docs) proxy	2023-11-23 11:46:59 -08:00
Ishaan Jaff	ed17e04bc2	Update README.md	2023-11-23 11:39:39 -08:00