4182 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Krrish Dholakia	94f065f83c	feat(sagemaker.py): support huggingface embedding models	2023-12-06 11:41:38 -08:00
ishaan-jaff	aefa4f36f9	(docs) update yaml with chat/embedding/completion mode	2023-12-06 11:36:16 -08:00
ishaan-jaff	fd86876164	(feat) proxy: add mode in model info	2023-12-06 11:29:59 -08:00
ishaan-jaff	7c77cc3cfa	(feat) add mode for config.yaml health checks	2023-12-06 11:16:29 -08:00
ishaan-jaff	4f02b3c161	(fix) print_verbose health check	2023-12-06 11:16:29 -08:00
Krrish Dholakia	f6546076b0	docs(quick_start.md): add docs on calling openai-compatible endpoint on proxy	2023-12-06 11:06:09 -08:00
ishaan-jaff	cc48b35a8d	(test) router - read os.environ/ OpenAI	2023-12-06 10:56:27 -08:00
ishaan-jaff	8f47293ce8	(chore) linting fix	2023-12-06 10:48:01 -08:00
ishaan-jaff	1e2a8869a9	(docs) proxy config with azure, openai embedding models	2023-12-06 10:45:07 -08:00
ishaan-jaff	9f4928fae4	(feat) proxy - add health check for embeddings	2023-12-06 10:45:07 -08:00
Krrish Dholakia	37251d327d	docs(virtual_keys.md): add custom auth to docs	2023-12-06 10:29:52 -08:00
ishaan-jaff	caf2a6b279	(fix) proxy - move new health check import	2023-12-06 10:13:06 -08:00
ishaan-jaff	01aa8941a5	(test) OTEL / traceloop - waiting for async support	2023-12-06 10:08:37 -08:00
ishaan-jaff	11a8713a50	(test) router - set sync stream client	2023-12-06 10:08:37 -08:00
Ishaan Jaff	a4cf4e7ca9	Merge pull request #1023 from PSU3D0/speedup_health_endpoint ... (feat) Speedup health endpoint	2023-12-06 09:52:13 -08:00
ishaan-jaff	bd0579703c	(test) router - reading os.environ/ with client	2023-12-06 09:26:21 -08:00
ishaan-jaff	13f9e78799	(fix) router - errors with reading timeout, stream timeout, max retries	2023-12-06 09:19:51 -08:00
ishaan-jaff	527aadd1ab	(test) router - reading os.environ/ variables	2023-12-06 09:19:51 -08:00
Krish Dholakia	18225c94e4	Merge pull request #993 from geekyayush/main ... feat: add docker compose file and running guide	2023-12-06 09:19:04 -08:00
ishaan-jaff	aab6be654e	(fix) router - set read os.environ/ values	2023-12-06 08:59:33 -08:00
Krrish Dholakia	92b2cbcdc5	feat(proxy_server.py): adding /model/delete endpoint	2023-12-05 22:38:38 -08:00
ishaan-jaff	ff028111cf	(fix) router len(num_retries)	2023-12-05 22:05:47 -08:00
ishaan-jaff	ba99561d08	bump: version 1.10.10 → 1.10.11	2023-12-05 21:57:12 -08:00
ishaan-jaff	5e065ebb8f	(test) router - explcitly call one deployment	2023-12-05 21:57:00 -08:00
ishaan-jaff	8e6c4c5310	(fix) router - allow users to call a specific_model explicit	2023-12-05 21:57:00 -08:00
Krrish Dholakia	acef6bd58d	refactor: linting fixes	2023-12-05 21:43:02 -08:00
Krrish Dholakia	7b83238cb5	fix(router.py): log when a call is retried or fallback happens	2023-12-05 21:29:58 -08:00
Frank Colson	95e5331090	Use litellm logging convention	2023-12-05 22:28:23 -07:00
Frank Colson	fc31221b8a	Speedup health endpoint	2023-12-05 22:09:01 -07:00
Ayush Somani	f0df1fade7	(docs) update docs	2023-12-06 10:38:52 +05:30
Ayush Somani	0bf3de0a01	(docs) update docker compose docs	2023-12-06 10:37:45 +05:30
Ayush Somani	b0fcc5af67	Merge branch 'main' into main	2023-12-06 10:32:59 +05:30
ishaan-jaff	642c62f7b7	(fix) proxy: better debugging when -debug is on	2023-12-05 18:19:15 -08:00
ishaan-jaff	48aa00d6c0	(fix) proxy - clean up print statement	2023-12-05 18:14:01 -08:00
ishaan-jaff	27d7d7ba9c	(feat) proxy cli, better description of config yaml param	2023-12-05 18:11:29 -08:00
ishaan-jaff	56acded998	(router) better debugging using config.yaml	2023-12-05 18:07:27 -08:00
ishaan-jaff	155e99b9a3	(fix) prox cli: remove deprecated param	2023-12-05 18:04:08 -08:00
Krrish Dholakia	39bb972168	bump: version 1.10.9 → 1.10.10	2023-12-05 18:01:58 -08:00
ishaan-jaff	cb52e3347e	(fix) proxy: make yaml load print_verbose	2023-12-05 18:00:00 -08:00
Krrish Dholakia	648d41c96f	fix(sagemaker.py): prompt templating fixes	2023-12-05 17:47:44 -08:00
ishaan-jaff	0eccc1b1f8	(test) router: call 1 deployment	2023-12-05 17:35:35 -08:00
ishaan-jaff	1fa9ddd739	(chore) linting fix	2023-12-05 17:29:09 -08:00
ishaan-jaff	e788a34da4	(chore) linting fix	2023-12-05 17:26:03 -08:00
ishaan-jaff	4d5313343b	(feat) proxy /embedding check 1 deploy call	2023-12-05 17:22:07 -08:00
ishaan-jaff	3af4f7fb0f	(fix) proxy: /chat/cmp - check 1 deployment	2023-12-05 17:19:48 -08:00
ishaan-jaff	a532cf14ae	(feat) router - track original deployment names	2023-12-05 17:19:48 -08:00
Krrish Dholakia	e4fae5a3e8	docs(aws_sagemaker.md): support for all huggingface/jumpstart modelsn	2023-12-05 16:59:37 -08:00
Krrish Dholakia	1addaecf48	docs(aws_sagemaker.md): add hf_model_name to sagemaker docs	2023-12-05 16:58:19 -08:00
ishaan-jaff	703a575a5d	(test) call 1 deployment on router	2023-12-05 16:56:38 -08:00
ishaan-jaff	bb6a1968b3	(fix) router - allow user to call 1 deployment	2023-12-05 16:56:38 -08:00