3189 commits

Author	SHA1	Message	Date
ishaan-jaff	6f9d3fc3bc	(ci/cd) retry hosted ollama + stream test 3 times	2024-01-05 18:02:20 +05:30
ishaan-jaff	0eb899c087	(test) hosted ollama - retry 3 times	2024-01-05 17:58:59 +05:30
ishaan-jaff	90973d92bf	(fix) re-connect prisma if not connected	2024-01-05 17:58:23 +05:30
ishaan-jaff	d2578f0cd2	(ci/cd) proxy print_verbose on failing insert_data	2024-01-05 17:28:27 +05:30
ishaan-jaff	76b2db4492	(ci/cd) run test again	2024-01-05 16:40:56 +05:30
ishaan-jaff	69bac0dbf6	(ci/cd) test proxy - init prisma in test	2024-01-05 16:18:23 +05:30
ishaan-jaff	4679c7b99a	(fix) caching use same "created" in response_object	2024-01-05 16:03:56 +05:30
ishaan-jaff	00b001b96b	(feat) completion_cost: improve model=None error	2024-01-05 15:26:04 +05:30
ishaan-jaff	f211009263	(test) openai embedding cost calculation	2024-01-05 15:22:17 +05:30
ishaan-jaff	20256c45ad	(fix) retry cloudflare ai workers 3 times	2024-01-05 13:55:47 +05:30
ishaan-jaff	6694975ec3	(test) azure completion_cost	2024-01-05 13:53:08 +05:30
ishaan-jaff	13201edc4b	(test) test reading configs on proxy	2024-01-05 13:37:31 +05:30
ishaan-jaff	aeee8fd3da	(fix) reading cache params on proxy	2024-01-05 13:36:48 +05:30
ishaan-jaff	72e7178c9b	(test) azure/embedding + completion_cost	2024-01-05 13:19:17 +05:30
ishaan-jaff	f681f0f2b2	(feat) completion_cost - embeddings + raise Exception	2024-01-05 13:11:23 +05:30
ishaan-jaff	113b5e7284	(ci/cd) retry cloudflare request 3 times	2024-01-05 12:40:53 +05:30
ishaan-jaff	83b31141c6	(ci/cd) raise correct exception proxy	2024-01-05 12:29:03 +05:30
ishaan-jaff	bcf22725a6	(ci/cd) run cloudflare test 3 retries	2024-01-05 11:55:12 +05:30
ishaan-jaff	79ab1aa35b	(fix) undo - model_dump_json() before logging	2024-01-05 11:47:16 +05:30
ishaan-jaff	40b9f1dcb1	(fix) proxy - log response before model_dump_json	2024-01-05 11:00:02 +05:30
ishaan-jaff	d1865591aa	(fix) test caching- use azure, instead of bedrock	2024-01-05 10:51:56 +05:30
Krrish Dholakia	6506fba3bc	test(test_proxy_exception_mapping.py): fix exception checking	2024-01-04 22:45:16 +05:30
Krrish Dholakia	25241de69e	fix(router.py): don't retry malformed / content policy violating errors (400 status code) ... https://github.com/BerriAI/litellm/issues/1317 , https://github.com/BerriAI/litellm/issues/1316	2024-01-04 22:23:51 +05:30
Krrish Dholakia	aa72d65c90	fix(utils.py): fix check for if cached response should be returned	2024-01-04 21:49:19 +05:30
Krrish Dholakia	74f6f6489a	fix(proxy_server.py): fix prisma client connection error	2024-01-04 18:28:18 +05:30
Krrish Dholakia	6b708347f3	fix(proxy_server.py): enable sending test connections when slack alerting added to proxy via ui	2024-01-04 17:00:07 +05:30
Krrish Dholakia	c7644915f9	fix(test_proxy_server.py): fix import	2024-01-04 16:11:23 +05:30
Krrish Dholakia	263d20cdd0	fix(proxy_server.py): update proxy with full model list	2024-01-04 15:56:16 +05:30
Krrish Dholakia	773a0a147a	fix(utils.py): raise a bad request error if litellm client raises a model /provider not found error	2024-01-04 15:50:43 +05:30
Krrish Dholakia	99d9a825de	feat(proxy_server.py): abstract config update/writing and support persisting config in db ... allows user to opt into writing to db (SAVE_CONFIG_TO_DB) and removes any api keys before sending to db https://github.com/BerriAI/litellm/issues/1322	2024-01-04 14:44:59 +05:30
ishaan-jaff	c231a6e4d3	(ci/cd) run proxy test with debug=True	2024-01-04 13:01:00 +05:30
ishaan-jaff	234c057e97	(fix) azure+cf gateway, health check	2024-01-04 12:34:07 +05:30
Krrish Dholakia	b0827a87b2	fix(caching.py): support s-maxage param for cache controls	2024-01-04 11:41:23 +05:30
Krrish Dholakia	0f7d03f761	fix(proxy/rules.md): add docs on setting post-call rules on the proxy	2024-01-04 11:16:50 +05:30
ishaan-jaff	54653f9a4a	(test) proxy + s3 caching	2024-01-04 11:11:08 +05:30
ishaan-jaff	aa757d19f5	(test) router - init clients - azure cloudflare, openai etc	2024-01-04 10:55:18 +05:30
ishaan-jaff	0864713b62	(test) cf azure	2024-01-04 10:26:41 +05:30
ishaan-jaff	8e10a1eb81	(docs) config with cloudflare exampel	2024-01-04 10:25:35 +05:30
ishaan-jaff	6d21ee3a2f	(fix) proxy - cloudflare + Azure bug [non-streaming]	2024-01-04 10:24:51 +05:30
Dustin Miller	b10f64face	Adds "pre-fill" support for Claude	2024-01-03 18:45:36 -06:00
David Manouchehri	c54e0813b4	(caching) improve s3 backend by specifying cache-control and content-type	2024-01-03 13:44:28 -05:00
ishaan-jaff	30c6d164d2	(docs) use s3 Cache on litellm proxy	2024-01-03 17:56:44 +05:30
Krrish Dholakia	469ae0a378	fix(proxy/utils.py): don't keep connecting to db if connection already established	2024-01-03 17:43:44 +05:30
Krrish Dholakia	f2da345173	fix(caching.py): handle cached_response being a dict not json string	2024-01-03 17:29:27 +05:30
Krrish Dholakia	f2210787cd	feat(proxy_server.py): allow admins to update config via /config/update endpoint	2024-01-03 17:18:33 +05:30
ishaan-jaff	4680a26e2e	(test) proxy - load test	2024-01-03 16:16:18 +05:30
Krrish Dholakia	d45101b652	fix(proxy_server.py): fix master key reset, to preserve key from env	2024-01-03 16:10:10 +05:30
Krrish Dholakia	40c974999e	fix(proxy_server.py): reject bad /model/new POST requests	2024-01-03 15:54:58 +05:30
ishaan-jaff	d14a41863f	(test) s3 cache with setting s3_bucket_name	2024-01-03 15:42:23 +05:30
ishaan-jaff	58ce5d44ae	(feat) s3 cache support all boto3 params	2024-01-03 15:42:23 +05:30