121 commits

Author	SHA1	Message	Date
Krrish Dholakia	6cd950a031	return model name as part of streaming object	2023-09-13 09:48:49 -07:00
Krrish Dholakia	7ebf97637c	add reset budget on duration end to budget manager	2023-09-12 13:01:55 -07:00
Krrish Dholakia	f015cd908a	doc cleanup for custom prompt templates	2023-09-12 12:16:47 -07:00
Krrish Dholakia	abc595998d	fix get llm provider	2023-09-12 11:48:44 -07:00
Krrish Dholakia	3f6b194b71	raise better exception if llm provider isn't passed in or inferred	2023-09-12 11:28:50 -07:00
Krrish Dholakia	0defdc8634	work for hf inference endpoint	2023-09-11 18:37:55 -07:00
Krrish Dholakia	355c2ed00c	improvements to exception mapping	2023-09-11 18:33:57 -07:00
Krrish Dholakia	f944eaee4b	mock responses for streaming	2023-09-11 16:30:29 -07:00
Krrish Dholakia	9f7c1d3885	add mock request to docs	2023-09-11 12:19:13 -07:00
Krrish Dholakia	2564bb8fb3	updating budget manager	2023-09-11 10:58:09 -07:00
Krrish Dholakia	7b6836bb4f	don't fail pytest due to timeout error in batch completions	2023-09-10 08:46:27 -07:00
Krrish Dholakia	88263faf76	update budget manager	2023-09-09 20:06:09 -07:00
Krrish Dholakia	10e4a06799	fix circle ci testing	2023-09-09 16:36:45 -07:00
Krrish Dholakia	1dd77ff176	update testing	2023-09-09 16:35:38 -07:00
Krrish Dholakia	9c715deb57	rename apimanager to budget manager	2023-09-09 16:10:41 -07:00
Krrish Dholakia	4319b1011c	add api manager	2023-09-09 15:55:38 -07:00
Krrish Dholakia	848660be9a	fix exception	2023-09-09 11:24:10 -07:00
Krrish Dholakia	f7dbdb52bd	improve error message returned if model not passed in	2023-09-09 11:18:10 -07:00
Krrish Dholakia	c177267d51	bump version	2023-09-08 19:26:41 -07:00
Krrish Dholakia	c054f22f10	update exception logic	2023-09-08 18:55:11 -07:00
Krrish Dholakia	e69863f91b	fix exception mapping	2023-09-08 18:45:18 -07:00
Krrish Dholakia	a89a491c10	fix exception mapping error	2023-09-08 18:20:07 -07:00
Krrish Dholakia	b60049b030	fix litedebugger double logging error	2023-09-07 18:02:24 -07:00
Krrish Dholakia	b8358da425	bump version	2023-09-07 17:00:20 -07:00
Krrish Dholakia	d20214f99c	fix litellm client	2023-09-07 16:22:00 -07:00
Krrish Dholakia	14fa57c185	batch completions for vllm now works too	2023-09-06 19:26:19 -07:00
Krrish Dholakia	7290a972e5	adding support for vllm	2023-09-06 18:07:44 -07:00
Krrish Dholakia	e24e60cd74	commenting out flaky circle ci test	2023-09-06 12:07:47 -07:00
Krrish Dholakia	311bfb7bb7	logging replicate response logs	2023-09-06 11:28:40 -07:00
Krrish Dholakia	8189a16188	updates	2023-09-06 11:21:48 -07:00
Krrish Dholakia	548b419005	test async streaming	2023-09-04 15:42:24 -07:00
Krrish Dholakia	3147bf1d99	fix linting errors	2023-09-04 15:16:13 -07:00
Krrish Dholakia	5ae420317e	adding first-party + custom prompt templates for huggingface	2023-09-04 14:54:09 -07:00
Krrish Dholakia	57dcd1fee9	update exception mapping and get model cost map	2023-09-04 11:53:20 -07:00
Krrish Dholakia	a07251a514	fix azure streaming	2023-09-02 16:10:19 -07:00
Krrish Dholakia	78cd8d6e27	update to logging	2023-09-02 15:45:45 -07:00
Krrish Dholakia	a972676655	adding support for aleph alpha	2023-09-02 13:15:41 -07:00
Krrish Dholakia	5cd84b709e	fix streaming cache logic	2023-09-01 16:56:07 -07:00
Krrish Dholakia	a2c76eb614	update to litedebugger testing	2023-09-01 16:13:45 -07:00
Krrish Dholakia	455794c628	updates to logging	2023-09-01 14:38:52 -07:00
Krrish Dholakia	db5e7a3515	fixes to litedebugger	2023-09-01 13:22:16 -07:00
Krrish Dholakia	bfa79ea3c0	fixes to core logging	2023-09-01 11:51:49 -07:00
Krrish Dholakia	1f2732a835	update model split tests with ui	2023-08-31 16:42:40 -07:00
Krrish Dholakia	4927e5879f	update baseten handler to handle TGI calls	2023-08-30 19:14:48 -07:00
Krrish Dholakia	fd7b7b998b	add huggingface	2023-08-30 16:05:33 -07:00
Krrish Dholakia	1385c26aff	return logprobs for hf models	2023-08-30 15:16:26 -07:00
Krrish Dholakia	581221339e	updates	2023-08-30 09:55:45 -07:00
Krrish Dholakia	eb33e1fa71	adding testing to make sure litedebugger is opt-in only	2023-08-30 09:55:33 -07:00
Krrish Dholakia	259de2d117	adding context window exceeded error to huggingface	2023-08-29 16:46:04 -07:00
Krrish Dholakia	7c4cc5942d	adding contextwindow exceeded error mapping for replicate	2023-08-29 16:36:31 -07:00