436 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Adil Hafeez	3f9eae4aa3	fix llm gateway rust tests	2025-06-09 16:32:42 -07:00
Adil Hafeez	ea2dd85bf1	fix model server testts	2025-06-09 14:48:41 -07:00
Adil Hafeez	641d41de1c	add tests	2025-06-06 00:37:12 -07:00
Adil Hafeez	8a46836ea9	fix tests	2025-06-05 23:42:44 -07:00
Adil Hafeez	04f6c20e38	remove extra log	2025-06-05 23:41:27 -07:00
Adil Hafeez	8bf3f32973	fix tests	2025-06-05 22:24:45 -07:00
Adil Hafeez	b1233da268	add arch	2025-06-05 20:17:07 -07:00
Adil Hafeez	a5bdd9c04f	Merge branch 'main' into adil/hermesllm	2025-06-05 20:14:38 -07:00
Adil Hafeez	96b583c819	make model required in readme and rst files (#503)	2025-06-05 20:14:13 -07:00
Adil Hafeez	950625a65a	fix tests	2025-06-05 20:06:54 -07:00
Adil Hafeez	8e4960df4a	fix more	2025-06-05 20:03:27 -07:00
Adil Hafeez	a3872a57ed	fix docker cli	2025-06-05 17:45:00 -07:00
Adil Hafeez	259683c3c4	dont use host bright staff for github	2025-06-05 17:03:31 -07:00
Adil Hafeez	df340f58c9	Merge branch 'main' into adil/hermesllm	2025-06-05 17:00:40 -07:00
Adil Hafeez	e43d41ba32	add support for bortli compression (#502)	2025-06-05 17:00:14 -07:00
Adil Hafeez	db19395eb7	more changes	2025-06-05 16:58:45 -07:00
Adil Hafeez	25f1b72e7c	more changes	2025-06-05 16:14:40 -07:00
Adil Hafeez	22fde1f333	fmt/clippy	2025-06-05 12:06:50 -07:00
Adil Hafeez	29503ba95e	revert supervisord	2025-06-04 16:49:46 -07:00
Adil Hafeez	6a6afb0888	move models to hermesllm	2025-06-04 16:36:47 -07:00
Adil Hafeez	0c7aa132ee	use hermesllm in arch gateway for both stream and non stream messages	2025-06-04 16:19:45 -07:00
Adil Hafeez	670907145a	more changes	2025-06-04 10:58:09 -07:00
Adil Hafeez	b0c1e97dc5	use req/resp from hermesllm in llm gateway	2025-06-03 15:57:30 -07:00
Adil Hafeez	f10e0fcece	add more changes	2025-06-03 15:00:57 -07:00
Adil Hafeez	2d4d0b01ee	add more changes	2025-06-03 09:58:06 -07:00
Adil Hafeez	9befd6364c	more changes	2025-06-03 00:17:22 -07:00
Adil Hafeez	59dbbd6743	add openai protocol	2025-06-02 23:57:03 -07:00
Adil Hafeez	21ca21dc3c	Merge branch 'main' into adil/hermesllm	2025-06-02 09:29:38 -07:00
Dougal Ballantyne	93224ed551	Update Dockerfile to fix warnings (#500)	2025-05-31 21:27:29 -07:00
Adil Hafeez	2e47d41a8c	Add ARCH_API_KEY in preference based routing demo (#498)	2025-05-31 01:52:25 -07:00
Adil Hafeez	aff389d342	don't run docker compose up for preference based router e2e demo tests (#499)	2025-05-31 01:16:17 -07:00
Adil Hafeez	0f139baf13	use consistent version across all arch_config files (#497)	2025-05-31 01:11:14 -07:00
Adil Hafeez	c7a3a668a9	update readme for preference based routing (#496)	2025-05-30 18:09:10 -07:00
Adil Hafeez	ed28bbaf04	release 0.3.1 (#495)	2025-05-30 17:47:59 -07:00
Adil Hafeez	0d190a6e5c	update code to use new json based system prompt for routing (#493)	2025-05-30 17:40:46 -07:00
Adil Hafeez	8d12a9a6e0	add arch provider (#494)	2025-05-30 17:12:52 -07:00
CTran	6a01eea813	LLM Router api doc (#492) ... * Create router.rst * add doc * update api * update api * Update docs/source/guides/llm_router.rst Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update docs/source/guides/llm_router.rst Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix whitespace * Update llm_router.rst * remove faeture and align examples * remove faeture and align examples --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Shuguang Chen <54548843+nehcgs@users.noreply.github.com>	2025-05-30 16:15:26 -07:00
Adil Hafeez	176f039bbc	fix model warning and use openwebui for preference based router demo	2025-05-30 12:29:56 -07:00
Adil Hafeez	fffa837a06	separate out currency exchange and preference based routing (#491)	2025-05-30 02:14:37 -07:00
Adil Hafeez	cd7b8ef649	add hermes llm	2025-05-29 13:33:41 -07:00
Adil Hafeez	470cdf9843	use provider_name as model_id /v1/models api (#490)	2025-05-29 11:23:18 -07:00
Adil Hafeez	9c4733590f	add support for openwebui (#487)	2025-05-28 19:08:00 -07:00
Adil Hafeez	4899117876	add compress/decompress filter to llm listener (#489)	2025-05-28 15:06:52 -07:00
Adil Hafeez	d29eba4102	trim conversation if it exceed max limit of what router model can handle (#488)	2025-05-27 20:28:22 -07:00
Adil Hafeez	79cbcb5fe1	add claude-4 in llm_routing demo (#486)	2025-05-23 10:21:21 -07:00
Adil Hafeez	dc271f1f76	release 0.3.0 (#483)	2025-05-23 09:52:23 -07:00
Adil Hafeez	99dd900a34	fix panic in brightstaff (#485) ... make router section optional in arch_config	2025-05-23 09:37:25 -07:00
Adil Hafeez	21faae605f	correctly map envoy stats to host (#484) ... host port 19901 -> envoy container port 9901	2025-05-23 09:37:15 -07:00
Adil Hafeez	a0d10153f9	update archgw logs file to stream access logs from container (#482)	2025-05-23 09:15:44 -07:00
Adil Hafeez	d050dfb85a	When router usage is defined ensure that router model is defined too (#481)	2025-05-23 08:46:12 -07:00