525 commits

Author	SHA1	Message	Date
Krrish Dholakia	0ab6b2451d	fix(acompletion): support client side timeouts + raise exceptions correctly for async calls	2023-11-17 15:39:47 -08:00
ishaan-jaff	7abb65d53f	(feat) completion: add response_format, seed, tools, tool_choice	2023-11-17 13:59:57 -08:00
Ishaan Jaff	61705f3467	(ci/cd) run again	2023-11-16 21:29:18 -08:00
Krrish Dholakia	a94c09c13c	fix(openai.py): handling extra headers	2023-11-16 12:48:21 -08:00
ishaan-jaff	23d560071b	(linting) fix	2023-11-16 12:33:03 -08:00
ishaan-jaff	f8af5e0155	(fix) linting	2023-11-16 12:25:46 -08:00
Krrish Dholakia	f99a161d98	fix(azure.py): fix linting errors	2023-11-16 12:15:50 -08:00
ishaan-jaff	a1cecbafe6	(fix) linting	2023-11-16 11:44:26 -08:00
ishaan-jaff	77468e0a70	(feat) text_completion add rules on when to use engine & model together	2023-11-16 11:37:31 -08:00
Rodney Rodriguez	5d39279ac0	bugfixes for ollama	2023-11-15 19:27:06 -06:00
Krrish Dholakia	a59494571f	fix(huggingface_restapi.py): fix linting errors	2023-11-15 15:34:21 -08:00
Krrish Dholakia	1a705bfbcb	refactor(huggingface_restapi.py): moving async completion + streaming to real async calls	2023-11-15 15:14:21 -08:00
Krrish Dholakia	59eaeba92a	fix(router.py): enabling retrying with expo backoff (without tenacity) for router	2023-11-14 20:57:51 -08:00
Krrish Dholakia	1738341dcb	fix(main.py): misrouting ollama models to nlp cloud	2023-11-14 18:55:08 -08:00
ishaan-jaff	e82b8ed7e2	(feat) debug ollama POST request	2023-11-14 17:53:48 -08:00
Krrish Dholakia	a7222f257c	fix(main.py): keep client consistent across calls + exponential backoff retry on ratelimit errors	2023-11-14 16:26:05 -08:00
ishaan-jaff	72755125fc	(fix) linting fix	2023-11-14 14:40:59 -08:00
ishaan-jaff	53ed8f3b7e	(feat) pass azure_ad_token to embedding	2023-11-14 12:48:31 -08:00
ishaan-jaff	78f42921b9	(feat) pass azure_ad_token to completion	2023-11-14 12:48:31 -08:00
ishaan-jaff	ceaf944cd4	(feat) completion:azure - add azure_ad_token	2023-11-14 12:12:14 -08:00
Krrish Dholakia	548933d0bb	fix(main.py): fix linting errors	2023-11-13 15:31:46 -08:00
Krrish Dholakia	f20820fd00	fix(main.py): fix linting errors	2023-11-13 14:52:37 -08:00
Krrish Dholakia	8a3b771e50	fix(tests): fixing response objects for testing	2023-11-13 14:39:30 -08:00
Krrish Dholakia	d4de55b053	fix(together_ai.py): exception mapping for tgai	2023-11-13 13:17:15 -08:00
ishaan-jaff	27cbd7d895	(fix) deepinfra with openai v1.0.0	2023-11-13 09:51:22 -08:00
Krrish Dholakia	c5c3096a47	build(main.py): trigger testing	2023-11-11 19:20:48 -08:00
Krrish Dholakia	45b6f8b853	refactor: fixing linting issues	2023-11-11 18:52:28 -08:00
Krrish Dholakia	c6ce3fedcd	fix(main.py): fix caching for router	2023-11-11 17:45:23 -08:00
Krrish Dholakia	39c2597c33	refactor(azure.py): working azure completion calls with openai v1 sdk	2023-11-11 16:44:39 -08:00
Krrish Dholakia	d0bd932b3c	refactor(openai.py): working openai chat + text completion for openai v1 sdk	2023-11-11 16:25:10 -08:00
Krrish Dholakia	d3323ba637	refactor(openai.py): making it compatible for openai v1 ... BREAKING CHANGE:	2023-11-11 15:33:02 -08:00
Krrish Dholakia	41c94d50e2	fix(text_completion.py): fix routing logic	2023-11-10 15:46:37 -08:00
Krrish Dholakia	18a8bd5543	fix(utils.py): return function call as part of response object	2023-11-10 11:02:10 -08:00
Krrish Dholakia	a4c9e6bd46	fix(utils.py): fix cached responses - translate dict to objects	2023-11-10 10:38:20 -08:00
Pratham Soni	2f37baa690	add custom open ai models to asyncio call	2023-11-09 20:47:46 -08:00
Krrish Dholakia	249cde3d40	fix(main.py): accepting azure deployment_id	2023-11-09 18:16:02 -08:00
Krrish Dholakia	b9e6989e41	test: fix linting issues	2023-11-09 16:50:43 -08:00
Krrish Dholakia	e12bff6d7f	refactor(azure.py): enabling async streaming with aiohttp	2023-11-09 16:41:06 -08:00
Krrish Dholakia	c053782d96	refactor(openai.py): support aiohttp streaming	2023-11-09 16:15:30 -08:00
Krrish Dholakia	86ef2a02f7	fix(azure.py): adding support for aiohttp calls on azure + openai	2023-11-09 10:40:33 -08:00
Krrish Dholakia	9bfbdc18fb	feat(utils.py): enable returning complete response when stream=true	2023-11-09 09:17:51 -08:00
Krrish Dholakia	6f4707bbb3	refactor(azure.py): moving embeddings to http call	2023-11-08 19:07:21 -08:00
Krrish Dholakia	70311502c8	refactor(openai.py): moving embedding calls to http	2023-11-08 19:01:17 -08:00
Krrish Dholakia	c2cbdb23fd	refactor(openai.py): moving openai text completion calls to http	2023-11-08 18:40:03 -08:00
Krrish Dholakia	c57ed0a9d7	refactor(openai.py): moving openai chat completion calls to http	2023-11-08 17:40:41 -08:00
Krrish Dholakia	53abc31c27	refactor(azure.py): moving azure openai calls to http calls	2023-11-08 16:52:18 -08:00
ishaan-jaff	2a751c277f	(feat) add streaming for text_completion	2023-11-08 11:58:07 -08:00
ishaan-jaff	2498d95dc5	(feat) parallel HF text completion + completion_with_retries show exception	2023-11-06 17:58:06 -08:00
ishaan-jaff	b4797bec3b	(fix) bug fix: completion, text_completion, check if optional params are not None and pass to LLM	2023-11-06 13:17:19 -08:00
ishaan-jaff	f591d79376	(fix) linting fixes	2023-11-06 13:02:11 -08:00