3482 commits

Author	SHA1	Message	Date
Ishaan Jaff	1b1e0f2d77	init custom guardrail class	2024-08-23 10:54:42 -07:00
Ishaan Jaff	7d30188f84	custom_callbacks	2024-08-23 09:52:52 -07:00
Ishaan Jaff	a99258440c	fix use guardrail for pre call hook	2024-08-23 09:34:08 -07:00
Krrish Dholakia	93ed8c7216	fix(utils.py): handle additionalProperties is False for vertex ai / gemini calls ... Fixes https://github.com/BerriAI/litellm/issues/5338 Also adds together ai json mode support	2024-08-23 09:21:32 -07:00
Ishaan Jaff	af92cff44d	add custom guardrail reference	2024-08-23 08:32:07 -07:00
Ishaan Jaff	e62d0c7922	add the ability to init a custom guardrail	2024-08-23 08:21:07 -07:00
Krrish Dholakia	afb00a27cb	fix(litellm_pre_call_utils.py): don't override k-v pair sent in spend_logs_metadata by user	2024-08-23 07:10:18 -07:00
Krish Dholakia	76b3db334b	Merge branch 'main' into litellm_azure_batch_apis	2024-08-22 19:07:54 -07:00
Ishaan Jaff	228252b92d	Merge branch 'main' into litellm_allow_using_azure_ad_token_auth	2024-08-22 18:21:24 -07:00
Ishaan Jaff	70f9e41ed9	Merge branch 'main' into litellm_add_bedrock_guardrails	2024-08-22 17:28:49 -07:00
Ishaan Jaff	1f0cc72531	test bedrock guardrails	2024-08-22 17:24:42 -07:00
Krrish Dholakia	735fc804ed	fix(proxy_server.py): expose flag to disable retries when max parallel request limit is hit	2024-08-22 16:49:52 -07:00
Krrish Dholakia	7398e94472	fix(files_endpoints.py): fix multiple args error	2024-08-22 16:42:44 -07:00
Krrish Dholakia	d7b525f391	feat(auth_checks.py): allow team to call all models, when explicitly set via /*	2024-08-22 16:38:56 -07:00
Ishaan Jaff	9e3d573bcb	add async_post_call_success_hook	2024-08-22 16:34:43 -07:00
Krish Dholakia	3cf009efbf	Merge pull request #5325 from BerriAI/litellm_redis_cluster ... feat(caching.py): redis cluster support	2024-08-22 16:13:45 -07:00
Krrish Dholakia	d7d3eee349	feat(azure.py): support health checking azure deployments ... Fixes https://github.com/BerriAI/litellm/issues/5279	2024-08-22 16:11:14 -07:00
Ishaan Jaff	7d55047ab9	add bedrock guardrails support	2024-08-22 16:09:55 -07:00
Krrish Dholakia	63cd94c32a	fix: fix linting errors	2024-08-22 15:51:59 -07:00
Krrish Dholakia	8625663458	feat(proxy_server.py): support azure batch api endpoints	2024-08-22 15:21:43 -07:00
Ishaan Jaff	06a362d35f	track litellm_request_latency_metric	2024-08-22 13:58:10 -07:00
Ishaan Jaff	08fa3f346a	add new litellm params for client_id, tenant_id etc	2024-08-22 11:37:30 -07:00
Krish Dholakia	68cb5cae58	Merge branch 'main' into litellm_redis_cluster	2024-08-22 11:06:14 -07:00
Ishaan Jaff	8f657b40f5	use azure_ad_token_provider to init clients	2024-08-22 11:03:49 -07:00
Ishaan Jaff	a120135dd1	fix allow setting LiteLLM license as .env	2024-08-22 10:05:00 -07:00
Ishaan Jaff	cc8e6f1d44	fix allow setting license in config.yaml	2024-08-22 09:45:15 -07:00
Ishaan Jaff	2be984ebee	add docstring for /embeddings and /completions	2024-08-22 09:30:47 -07:00
Ishaan Jaff	f6e80b0031	add doc string for /chat/completions swagger	2024-08-22 09:27:40 -07:00
Ishaan Jaff	374bef4326	fix /user/delete doc string	2024-08-22 09:09:51 -07:00
Ishaan Jaff	03c65c889a	fix team_member_add	2024-08-21 19:10:37 -07:00
Ishaan Jaff	f0f1d50734	fix test_master_key_hashing	2024-08-21 17:56:09 -07:00
Ishaan Jaff	0ea1f367d7	use litellm proxy with vertex ai sdk	2024-08-21 17:47:01 -07:00
Ishaan Jaff	a174cbdd72	Merge branch 'main' into litellm_pass_through_vtx_multi_modal	2024-08-21 17:23:22 -07:00
Ishaan Jaff	bcc0f99476	fix pass through endpoints	2024-08-21 17:21:22 -07:00
Ishaan Jaff	0e1d3804ff	refactor vertex endpoints to pass through all routes	2024-08-21 17:08:42 -07:00
Ishaan Jaff	f947cec7fc	add test vtx embedding	2024-08-21 17:05:47 -07:00
Ishaan Jaff	e9537c6560	proxy - print embedding request when recieved	2024-08-21 17:00:18 -07:00
Krrish Dholakia	8a05ce77e9	feat(litellm_logging.py): add 'saved_cache_cost' to standard logging payload (s3)	2024-08-21 16:58:07 -07:00
Krrish Dholakia	0a42347a8d	docs(users.md): add doc on setting max budget for internal users	2024-08-21 16:21:40 -07:00
Krish Dholakia	72169fd5c4	Merge branch 'main' into litellm_disable_storing_master_key_hash_in_db	2024-08-21 15:37:25 -07:00
Krrish Dholakia	e2d7539690	feat(caching.py): redis cluster support ... Closes https://github.com/BerriAI/litellm/issues/4358	2024-08-21 15:01:52 -07:00
Krish Dholakia	509ae0ca71	Merge pull request #5308 from BerriAI/litellm_team_admin_permissions ... feat(user_api_key_auth.py): allow team admin to add new members to team	2024-08-21 14:21:22 -07:00
Krrish Dholakia	7aec6f0f2a	fix(litellm_pre_call_utils.py): handle dynamic keys via api correctly	2024-08-21 13:37:21 -07:00
Ishaan Jaff	d6493b0e7f	docs semantic caching qdrant	2024-08-21 13:03:41 -07:00
Krrish Dholakia	83bed56b66	fix(internal_user_endpoints.py): pass in user api key dict value	2024-08-21 12:46:43 -07:00
Ishaan Jaff	c6dfd2d276	fixes for using qdrant with litellm proxy	2024-08-21 12:36:41 -07:00
Krrish Dholakia	89014dfc07	feat(proxy_server.py): support disabling storing master key hash in db, for spend tracking	2024-08-21 12:35:37 -07:00
Krrish Dholakia	5ba517819c	test(test_proxy_server.py): fix test to specify user role	2024-08-21 08:37:04 -07:00
Krrish Dholakia	04fc0bd7b3	feat(litellm_pre_call_utils.py): support passing tags/spend logs metadata from keys/team metadata to request	2024-08-21 08:13:36 -07:00
Ishaan Jaff	cea7b73015	enforece guardrails per API Key as enterprise	2024-08-20 17:34:28 -07:00