3232 commits

Author	SHA1	Message	Date
ishaan-jaff	96cb6f3b10	(fix) azure+stream: count completion tokens	2024-01-03 12:06:39 +05:30
ishaan-jaff	f3b8d9c3ef	(fix) counting response tokens+streaming	2024-01-03 12:06:39 +05:30
Krrish Dholakia	cd98d256b5	fix(proxy_server.py): add alerting for responses taking too long ... https://github.com/BerriAI/litellm/issues/1298	2024-01-03 11:18:21 +05:30
Krrish Dholakia	0d13c51615	fix(proxy/utils.py): fix self.alerting null case ... https://github.com/BerriAI/litellm/issues/1298#issuecomment-1874798056	2024-01-03 10:12:21 +05:30
Krrish Dholakia	a778f8a00e	bump: version 1.16.10 → 1.16.11	2024-01-02 22:26:47 +05:30
Krrish Dholakia	070520d237	fix(proxy_server.py): support smtp email auth ... previously was a hard resend package dependency. removed in favor of allowing any smtp server connection (including resend)	2024-01-02 22:22:19 +05:30
Ased Mammad	c39c8f70eb	fix(proxy_server.py) Check when '_hidden_params' is None	2024-01-02 19:04:51 +03:30
Krrish Dholakia	940569703e	feat(proxy_server.py): add slack alerting to proxy server ... add alerting for calls hanging, failing and db read/writes failing https://github.com/BerriAI/litellm/issues/1298	2024-01-02 17:45:18 +05:30
ishaan-jaff	c27b1fc5f8	(feat) proxy swagger - make admin link clickable	2024-01-02 17:04:32 +05:30
ishaan-jaff	14738ec89d	(test) xinference on litellm router	2024-01-02 16:51:08 +05:30
ishaan-jaff	bfbed2d93d	(test) xinference embeddings	2024-01-02 15:41:51 +05:30
ishaan-jaff	790dcff5e0	(feat) add xinference as an embedding provider	2024-01-02 15:32:26 +05:30
Krrish Dholakia	0fffcc1579	fix(utils.py): support token counting for gpt-4-vision models	2024-01-02 14:41:42 +05:30
ishaan-jaff	bfae0fe935	(test) proxy - pass user_config	2024-01-02 14:15:03 +05:30
ishaan-jaff	075eb1a516	(types) routerConfig	2024-01-02 14:14:29 +05:30
ishaan-jaff	9afdc8b4ee	(feat) add Router init Pydantic Type	2024-01-02 13:30:24 +05:30
ishaan-jaff	1f8fc6d2a7	(feat) litellm add types for completion, embedding request	2024-01-02 12:27:08 +05:30
ishaan-jaff	6d2b9fd470	(feat) use - user router for aembedding	2024-01-02 12:27:08 +05:30
Krrish Dholakia	2ab31bcaf8	fix(lowest_tpm_rpm.py): handle null case for text/message input	2024-01-02 12:24:29 +05:30
ishaan-jaff	0acaaf8f8f	(test) sustained load test proxy	2024-01-02 12:10:34 +05:30
ishaan-jaff	31a896908b	(test) proxy - use, user provided model_list	2024-01-02 12:10:34 +05:30
ishaan-jaff	ddc31c4810	(feat) proxy - use user_config for /chat/compeltions	2024-01-02 12:10:34 +05:30
Krrish Dholakia	a37a18ca80	feat(router.py): add support for retry/fallbacks for async embedding calls	2024-01-02 11:54:28 +05:30
Krrish Dholakia	c12e3bd565	fix(router.py): fix model name passed through	2024-01-02 11:15:30 +05:30
Krrish Dholakia	dff4c172d0	refactor(test_router_caching.py): move tpm/rpm routing tests to separate file	2024-01-02 11:10:11 +05:30
ishaan-jaff	18ef244230	(test) bedrock-test passing boto3 client	2024-01-02 10:23:28 +05:30
ishaan-jaff	d1e8d13c4f	(fix) init_bedrock_client	2024-01-01 22:48:56 +05:30
Ishaan Jaff	9adcfedc04	(test) fix test_get_model_cost_map.py	2024-01-01 21:58:48 +05:30
Krrish Dholakia	a83e2e07cf	fix(router.py): correctly raise no model available error ... https://github.com/BerriAI/litellm/issues/1289	2024-01-01 21:22:42 +05:30
Ishaan Jaff	9cb5a2bec0	Merge pull request #1290 from fcakyon/patch-1 ... fix typos & add missing names for azure models	2024-01-01 17:58:17 +05:30
Krrish Dholakia	e1e3721917	build(user.py): fix page param read issue	2024-01-01 17:25:52 +05:30
Krrish Dholakia	a41e56a730	fix(proxy_server.py): enabling user auth via ui ... https://github.com/BerriAI/litellm/issues/1231	2024-01-01 17:14:24 +05:30
fatih	6566ebd815	update azure turbo namings	2024-01-01 13:03:08 +03:00
Krrish Dholakia	ca40a88987	fix(proxy_server.py): check if user email in user db	2024-01-01 14:19:59 +05:30
ishaan-jaff	7623c1a846	(feat) proxy - only use print_verbose	2024-01-01 13:52:11 +05:30
ishaan-jaff	84cfa1c42a	(test) ci/cd	2024-01-01 13:51:27 +05:30
Krrish Dholakia	24e7dc359d	feat(proxy_server.py): introduces new /user/auth endpoint for handling user email auth ... decouples streamlit ui from proxy server. this then requires the proxy to handle user auth separately.	2024-01-01 13:44:47 +05:30
ishaan-jaff	52db2a6040	(feat) proxy - remove streamlit ui on startup	2024-01-01 12:54:23 +05:30
ishaan-jaff	c8f8bd9e57	(test) proxy - log metadata to langfuse	2024-01-01 11:54:16 +05:30
ishaan-jaff	694956b44e	(test) proxy - pass metadata to openai client	2024-01-01 11:12:57 +05:30
ishaan-jaff	dacd86030b	(fix) proxy - remove extra print statemet	2024-01-01 10:52:09 +05:30
ishaan-jaff	16fb83e007	(fix) proxy - remove errant print statement	2024-01-01 10:48:12 +05:30
ishaan-jaff	84fbc903aa	(test) langfuse - set custom trace_id	2023-12-30 20:19:22 +05:30
ishaan-jaff	8ae4554a8a	(feat) langfuse - set custom trace_id, trace_user_id	2023-12-30 20:19:03 +05:30
ishaan-jaff	cc7b964433	(docs) add litellm.cache docstring	2023-12-30 20:04:08 +05:30
ishaan-jaff	70cdc16d6f	(feat) cache context manager - update cache	2023-12-30 19:50:53 +05:30
ishaan-jaff	e35f17ca3c	(test) caching - context managers	2023-12-30 19:33:47 +05:30
ishaan-jaff	ddddfe6602	(feat) add cache context manager	2023-12-30 19:32:51 +05:30
Krrish Dholakia	8ff3bbcfee	fix(proxy_server.py): router model group alias routing ... check model alias group routing before specific deployment routing, to deal with an alias being the same as a deployment name (e.g. gpt-3.5-turbo) n	2023-12-30 17:55:24 +05:30
Krrish Dholakia	027218c3f0	test(test_lowest_latency_routing.py): add more tests	2023-12-30 17:41:42 +05:30