3863 commits

Author	SHA1	Message	Date
Krrish Dholakia	0ffdf57dec	fix(vertex_ai.py): add async embedding support for vertex ai	2024-02-03 10:35:17 -08:00
Krish Dholakia	5bf51a6058	Merge pull request #1794 from BerriAI/litellm_vertex_ai_gecko_support ... Litellm vertex ai gecko support	2024-02-03 10:17:37 -08:00
Krrish Dholakia	1ba6882f76	fix(test_embedding.py): fix test	2024-02-03 09:49:23 -08:00
Krrish Dholakia	d9ba8668f4	feat(vertex_ai.py): vertex ai gecko text embedding support	2024-02-03 09:48:29 -08:00
Ishaan Jaff	6950f99804	Merge pull request #1788 from BerriAI/litellm_fix_delete_key ... [Fix] /key/delete + add delete cache keys	2024-02-02 20:22:26 -08:00
ishaan-jaff	ebb221f743	(fix) ui - don't fail when no DB connected	2024-02-02 20:17:26 -08:00
ishaan-jaff	ed048fb822	(ui) update ui build	2024-02-02 20:08:49 -08:00
ishaan-jaff	cfec3c611e	(fix) improve proxy api_key caching	2024-02-02 19:59:13 -08:00
ishaan-jaff	ae95e4c3f9	(test) user_api_key_auth_cache	2024-02-02 19:57:55 -08:00
Krish Dholakia	38a299a1bc	Merge pull request #1786 from BerriAI/litellm_cost_tracking_caching_fixes ... Litellm cost tracking caching fixes (should be 0.0)	2024-02-02 19:23:07 -08:00
ishaan-jaff	42fcce4645	(fix) /key/info test	2024-02-02 19:22:55 -08:00
Krrish Dholakia	bfe2faa454	test(test_keys.py): separate streaming key info test from normal completion key info test	2024-02-02 19:03:47 -08:00
Krrish Dholakia	3aab719521	test(test_completion.py): skip flaky test	2024-02-02 19:03:47 -08:00
Krrish Dholakia	1f0598a277	fix(proxy_server.py): load default team config straight from config file	2024-02-02 19:03:47 -08:00
Krrish Dholakia	142e7cf1ce	test(test_image_generation.py): ignore content violation errors for image gen test	2024-02-02 19:03:47 -08:00
Krrish Dholakia	c0699b08e5	test(test_caching.py): fix test to check id	2024-02-02 19:03:47 -08:00
Krrish Dholakia	c997d4b0ce	fix(test_key_generate_prisma.py): add longer delay to allow logs to update	2024-02-02 19:03:47 -08:00
Krrish Dholakia	ddf3e51545	fix(main.py): for health checks, don't use cached responses	2024-02-02 19:03:47 -08:00
Krrish Dholakia	688193bea3	fix(proxy_server.py): don't silently fail load_team_config	2024-02-02 19:03:47 -08:00
Krrish Dholakia	8988353176	test(test_keys.py): separate streaming key info test from normal completion key info test	2024-02-02 18:57:19 -08:00
ishaan-jaff	3899361aa4	(test) state of litellm cache after create, delete	2024-02-02 18:49:20 -08:00
Krrish Dholakia	2d59331148	test(test_completion.py): skip flaky test	2024-02-02 18:44:17 -08:00
ishaan-jaff	9852462d1f	(fix) proxy - clear cache after /key/delete	2024-02-02 18:40:18 -08:00
ishaan-jaff	4d6ffe4400	(feat) - cache - add delete cache	2024-02-02 18:36:51 -08:00
Krrish Dholakia	5631b3357b	fix(proxy_server.py): load default team config straight from config file	2024-02-02 18:35:30 -08:00
Krrish Dholakia	f3dd0c0563	test(test_image_generation.py): ignore content violation errors for image gen test	2024-02-02 18:05:39 -08:00
Krrish Dholakia	92b0a4cf50	test(test_key_generate_prisma.py): add longer sleep time	2024-02-02 18:03:07 -08:00
Krrish Dholakia	93e8a9ff91	test(test_caching.py): fix test to check id	2024-02-02 18:01:43 -08:00
Krrish Dholakia	a79f92533f	fix(test_key_generate_prisma.py): add longer delay to allow logs to update	2024-02-02 17:51:15 -08:00
Krish Dholakia	a1c567a47d	Merge pull request #1785 from BerriAI/litellm_fix_health_check ... fix(main.py): for health checks, don't use cached responses	2024-02-02 17:47:15 -08:00
Krrish Dholakia	6767e808a6	fix(proxy_server.py): don't silently fail load_team_config	2024-02-02 17:39:55 -08:00
Krrish Dholakia	1ed6842009	fix(utils.py): fix cost tracking for cache hits (should be 0)	2024-02-02 17:33:39 -08:00
Krrish Dholakia	62ad6f19b7	fix(main.py): for health checks, don't use cached responses	2024-02-02 16:51:42 -08:00
ishaan-jaff	d69edac11b	(feat) use same id to log on s3, langfuse	2024-02-02 16:26:59 -08:00
Krrish Dholakia	24b8abe10d	fix(view_key_table_tsx): show abbreviated key name instead of hashed token	2024-02-02 14:56:19 -08:00
Krish Dholakia	6bc27b1f64	Merge pull request #1781 from BerriAI/litellm_security_fix_allow_user_auth ... Litellm security fix allow user auth	2024-02-02 14:34:51 -08:00
Krrish Dholakia	643ff0438e	test(test_amazing_s3_logs.py): fix test ... n	2024-02-02 14:33:51 -08:00
Krrish Dholakia	31b19a420f	fix(helicone.py): fix logging	2024-02-02 14:30:01 -08:00
ishaan-jaff	9947b0db96	(fix) langfuse - use exact same response_id as s3 logging	2024-02-02 14:29:23 -08:00
ishaan-jaff	553349cb18	(fix) langfuse logging, append time to logs	2024-02-02 14:20:02 -08:00
ishaan-jaff	46a76852c7	(fix) s3 logging test	2024-02-02 14:10:24 -08:00
Krrish Dholakia	a11b505721	fix(utils.py): dynamic switch langfuse client based on keys	2024-02-02 14:03:46 -08:00
Krrish Dholakia	bc688d4662	fix(utils.py): dynamic switch langfuse client based on keys	2024-02-02 14:03:18 -08:00
Krrish Dholakia	e8785d5dff	fix(proxy_server.py): have spend logs be admin controlled only	2024-02-02 13:43:48 -08:00
Krrish Dholakia	0111c17981	refactor(main.py): trigger rebuild	2024-02-02 13:18:51 -08:00
Krrish Dholakia	937731fe48	refactor(main.py): trigger rebuild	2024-02-02 13:17:25 -08:00
Krrish Dholakia	ada62192ad	fix(proxy_server.py): stronger type checking for team based settings	2024-02-02 13:15:44 -08:00
Ishaan Jaff	730c5ef9f6	Merge pull request #1780 from BerriAI/litellm_langfuse_logging ... (feat) langfuse set generation_id to chatcmpl-response ID	2024-02-02 13:08:09 -08:00
Krish Dholakia	93fb0134e5	Merge pull request #1761 from BerriAI/litellm_fix_dynamic_callbacks ... fix(utils.py): override default success callbacks with dynamic callbacks if set	2024-02-02 13:06:55 -08:00
ishaan-jaff	9657fb0f0c	(feat) langfuse set generation_id to response ID	2024-02-02 13:06:47 -08:00