181 commits

Author	SHA1	Message	Date
ishaan-jaff	c45e2ed48c	hosted vllm usage	2023-09-08 13:58:06 -07:00
ishaan-jaff	c05606b587	custom base with openai completion	2023-09-08 13:21:43 -07:00
ishaan-jaff	a611409e0f	async streaming generator	2023-09-07 13:53:40 -07:00
Krrish Dholakia	6b3cb18983	fix linting issues	2023-09-06 20:43:59 -07:00
Krrish Dholakia	35cf6ef0a1	batch completions for vllm now works too	2023-09-06 19:26:19 -07:00
Krrish Dholakia	4cfcabd919	adding support for vllm	2023-09-06 18:07:44 -07:00
ishaan-jaff	dc0c084813	improve replicate usage	2023-09-06 12:29:34 -07:00
ishaan-jaff	1c61b7b229	add replicate streaming	2023-09-06 10:23:13 -07:00
ishaan-jaff	c45b132675	use replicate http requests instead	2023-09-06 09:43:05 -07:00
ishaan-jaff	0bbcba269d	fix linting	2023-09-05 17:11:31 -07:00
ishaan-jaff	8ecef03f63	custom api base	2023-09-05 16:50:32 -07:00
ishaan-jaff	262bb07ade	clean install and import - vertexai	2023-09-05 16:10:07 -07:00
ishaan-jaff	2250d1375e	clean up azure implementation	2023-09-05 15:31:59 -07:00
ishaan-jaff	2a36f06763	remove install_and_import remove petals	2023-09-05 15:06:24 -07:00
ishaan-jaff	079ec7064b	add completion types	2023-09-05 14:57:03 -07:00
ishaan-jaff	846aeea4f9	types completion()	2023-09-05 14:49:53 -07:00
ishaan-jaff	794964993d	add types to completion()	2023-09-05 14:42:10 -07:00
Krrish Dholakia	faa78ad543	bump version	2023-09-05 14:30:03 -07:00
ishaan-jaff	fe4caf5c3d	baseten client mapping	2023-09-04 15:41:37 -07:00
ishaan-jaff	79acfb4dab	fix aleph alpha client init	2023-09-04 15:14:09 -07:00
Krrish Dholakia	2384806cfd	adding first-party + custom prompt templates for huggingface	2023-09-04 14:54:09 -07:00
ishaan-jaff	a474b89779	clean up hugging face completion()	2023-09-04 14:41:06 -07:00
ishaan-jaff	2bf9ee4ecf	v0 bedrock support	2023-09-04 12:40:40 -07:00
ishaan-jaff	4a4ee51df3	working sagemaker support	2023-09-04 11:30:34 -07:00
ishaan-jaff	138c26d98d	v0 add sagemaker	2023-09-04 11:02:20 -07:00
ishaan-jaff	38564ddc82	clean out AI21 Init Client calls	2023-09-04 10:08:53 -07:00
ishaan-jaff	f2b0fa90ab	remove init for together_ai completion calls	2023-09-04 09:59:24 -07:00
ishaan-jaff	bc065f08df	remove init AnthropicClient for completion calls	2023-09-04 09:34:15 -07:00
ishaan-jaff	9a5636e27b	thread safe azure	2023-09-02 18:05:05 -07:00
ishaan-jaff	1bc2a6d5cc	thread safe version, key and base for openai	2023-09-02 17:49:26 -07:00
ishaan-jaff	ba61600f9c	make api base thread safe	2023-09-02 17:41:59 -07:00
ishaan-jaff	09ae510a58	use api_base instead of custom_api_base	2023-09-02 17:11:30 -07:00
ishaan-jaff	e128b272fa	fix embedding call	2023-09-02 16:48:33 -07:00
Krrish Dholakia	895e3c1a94	update to logging	2023-09-02 15:45:45 -07:00
Krrish Dholakia	83b8af8567	adding support for aleph alpha	2023-09-02 13:15:41 -07:00
Krrish Dholakia	0ff4515f20	fixes to litedebugger	2023-09-01 13:22:16 -07:00
Krrish Dholakia	b44299cce7	update model split tests with ui	2023-08-31 16:42:40 -07:00
Krrish Dholakia	66bfd70253	add completion call id	2023-08-31 12:54:38 -07:00
Krrish Dholakia	14d4c7ead2	update baseten handler to handle TGI calls	2023-08-30 19:14:48 -07:00
Krrish Dholakia	5bcf612724	adding coverage for openrouter in exception mapping	2023-08-29 15:30:24 -07:00
Krrish Dholakia	f11599e50c	add coverage for rate limit errors to togetherai	2023-08-29 12:54:56 -07:00
Krrish Dholakia	88bd1df3e0	adding exception handling for together ai	2023-08-29 12:29:59 -07:00
ishaan-jaff	200e1232e2	vertex ai fix	2023-08-29 09:48:52 -07:00
ishaan-jaff	8af6d967eb	working write to cache with streaming	2023-08-28 18:46:26 -07:00
ishaan-jaff	f84b7d5c0f	add customstreapwrapper for openai streaming	2023-08-28 15:32:53 -07:00
Krrish Dholakia	e8eb92c108	new logger client	2023-08-28 14:59:00 -07:00
Krrish Dholakia	d542066d4b	fixes to streaming for ai21, baseten, and openai text completions	2023-08-28 09:42:51 -07:00
ishaan-jaff	b713acb0a4	formatting improvements	2023-08-28 09:20:50 -07:00
Ishaan Jaff	69beeba025	Merge branch 'main' into dev/openai_api_base	2023-08-28 08:41:46 -07:00
ishaan-jaff	fedd16361f	add text_completion	2023-08-28 08:20:20 -07:00