149 commits

Author	SHA1	Message	Date
ishaan-jaff	a688df79b1	(feat) proxy: make chat/completions async	2023-11-25 12:54:03 -08:00
Krrish Dholakia	d62da29cbe	fix: fix linting issues	2023-11-24 15:46:25 -08:00
Krrish Dholakia	bc84b38154	feat(proxy_server.py): new /key/info endpoint to access key information (master key only)	2023-11-24 15:24:50 -08:00
Krrish Dholakia	4f22e7de18	feat(proxy_server.py): tracking spend per api key	2023-11-24 15:14:06 -08:00
Krrish Dholakia	2e8d582a34	fix(proxy_server.py): fix linting issues	2023-11-24 11:39:01 -08:00
ishaan-jaff	8edfcd8e5d	(fix) prisma using: secrets.compare_digest	2023-11-24 10:02:08 -08:00
David Manouchehri	ac08e3616c	Fix timing attack on master_key.	2023-11-24 12:12:29 -05:00
David Manouchehri	5b6f227170	Fix master key check.	2023-11-24 12:03:30 -05:00
David Manouchehri	3fa3a767b3	Fix OpenAPI auth spec.	2023-11-24 11:59:33 -05:00
ishaan-jaff	0a23af7990	(feat) proxy: cost tracking add track_cost_callback	2023-11-24 05:53:23 -08:00
Kumaran Rajendhiran	01fad94485	Fail gracefully if ollama is already being served	2023-11-24 16:52:55 +05:30
Krrish Dholakia	c9e37b8fb8	fix(proxy_server.py): fix linting errors	2023-11-23 21:42:39 -08:00
Krrish Dholakia	9a44433844	feat(proxy_server.py): /key/delete endpoint	2023-11-23 21:37:53 -08:00
ishaan-jaff	486037ff8b	(fix) proxy: /embeddings	2023-11-23 21:16:51 -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	1dcab433b4	(feat) proxy: caching - show redis settings when initializing	2023-11-23 10:52:50 -08:00
ishaan-jaff	ae3eeb16ab	(feat) proxy: add curl command test + read cache config	2023-11-23 10:31:04 -08:00
Krrish Dholakia	448ec0a571	feat(proxy_server): add /v1/embeddings endpoint ... n	2023-11-22 14:03:27 -08:00
Krrish Dholakia	b0801f61e6	test(test_caching.py): cleaning up tests	2023-11-22 13:43:48 -08:00
Krrish Dholakia	78582e158a	fix(main.py): fix acompletion for anyscale, openrouter, deepinfra, perplexity endpoints	2023-11-22 13:22:58 -08:00
ishaan-jaff	ba73224a3a	(feat) proxy server add /routes to see available routes	2023-11-22 13:20:21 -08:00
Krrish Dholakia	604ad41eac	fix(proxy_server.py): If master key is set, only master key can be used to generate new keys	2023-11-22 10:18:28 -08:00
Krrish Dholakia	e7bb4a0cbd	fix(proxy_server): fix linting issues	2023-11-22 08:47:59 -08:00
ishaan-jaff	6aa8b41fb3	(fix) caching config	2023-11-21 20:48:56 -08:00
ishaan-jaff	3c30705b76	(fix) cache configs	2023-11-21 20:48:56 -08:00
Krrish Dholakia	904def6119	fix(proxy_server.py): fix /models endpoint	2023-11-21 20:15:43 -08:00
ishaan-jaff	363d74cf7d	(fix) proxy server set model list through headers	2023-11-21 19:33:48 -08:00
Krrish Dholakia	826f56a6a0	docs(routing.md): update routing docs	2023-11-21 19:32:50 -08:00
Krrish Dholakia	9d97082eed	docs(routing.md): add queueing to docs	2023-11-21 18:01:02 -08:00
ishaan-jaff	a2681e353f	(fix) explicitly run prisma generate	2023-11-21 17:42:42 -08:00
ishaan-jaff	99b2a1bc8a	(fix) prisma	2023-11-21 17:38:34 -08:00
ishaan-jaff	410c059d52	(fix) prisma always installed on deploys	2023-11-21 17:27:07 -08:00
Krrish Dholakia	b16646e584	refactor(proxy_server.py): using celery workers instead of rq for concurrency	2023-11-21 16:31:56 -08:00
ishaan-jaff	8c98a2c899	(feat)proxy: readon config per request	2023-11-21 16:26:05 -08:00
Krrish Dholakia	a1f6b9b531	refactor(proxy_server.py): refactoring background rq worker	2023-11-21 13:47:09 -08:00
Krrish Dholakia	015c7de549	fix(proxy_server.py): defaulting status to queued	2023-11-21 12:40:30 -08:00
Krrish Dholakia	331fe86c8f	refactor(proxy_server.py): experimental endpoint - defined job status	2023-11-21 12:37:00 -08:00
Krrish Dholakia	d0f228e53f	refactor(proxy_server.py): refactoring experimental endpoint names	2023-11-21 12:12:15 -08:00
Krrish Dholakia	c6a4744947	feat(proxy_server.py): EXPERIMENTAL: adding queuing endpoints to openai proxy server	2023-11-21 12:06:23 -08:00
ishaan-jaff	6898840218	(fix) proxy server - raise 500 on exceptions	2023-11-21 08:36:34 -08:00
Krrish Dholakia	846a824c47	fix(proxy_server.py): run ollama serve when ollama in config.yaml	2023-11-21 08:35:04 -08:00
Krrish Dholakia	33e47dae8e	feat(proxy_server.py): enable model aliases	2023-11-20 16:51:04 -08:00
Krrish Dholakia	1976d0f7d6	fix(routing.py): update token usage on streaming	2023-11-20 14:19:25 -08:00
Krrish Dholakia	d8079907b9	fix(proxy_server.py): fix linting errors	2023-11-18 17:35:16 -08:00
Krrish Dholakia	eefa66e8f0	docs(simple_proxy.md): adding token based auth to docs	2023-11-18 17:34:11 -08:00
ishaan-jaff	73ce9aceb2	(fix) linting	2023-11-18 17:05:46 -08:00
Krrish Dholakia	7a669a36d2	fix(proxy_server.py): handle initializing prisma / db connection just once	2023-11-18 16:45:19 -08:00
Krrish Dholakia	c02794d3ff	feat(proxy_server.py): enable token based authentication for server endpoints	2023-11-18 16:13:53 -08:00
Krrish Dholakia	8ae855e008	fix(proxy_server.py): allow user to connect their proxy to a postgres db	2023-11-18 15:57:38 -08:00