Commit graph

5182 commits

Author SHA1 Message Date
Krrish Dholakia
2fdc20f549 test: handle vertex ai rate limit errors 2024-03-18 21:33:08 -07:00
Krrish Dholakia
2827acc487 refactor(main.py): trigger new build 2024-03-18 21:27:32 -07:00
Krrish Dholakia
7eaddaef10 refactor(proxy_server.py): re-add custom db client logic - prevent regressions 2024-03-18 21:16:28 -07:00
Krrish Dholakia
0b39bc141b test(test_update_spend.py): fix test 2024-03-18 20:38:21 -07:00
Krrish Dholakia
f588bff69b fix(proxy_server.py): fix spend log update 2024-03-18 20:26:28 -07:00
Krrish Dholakia
8fefe625d9 fix(proxy/utils.py): batch writing updates to db 2024-03-18 16:47:02 -07:00
Krrish Dholakia
077b9c6234 fix(proxy/utils.py): move to batch writing db updates 2024-03-16 22:32:00 -07:00
Krrish Dholakia
c69ae8efce refactor(main.py): trigger new build 2024-03-16 18:49:54 -07:00
Krish Dholakia
e55a8c3570
Merge pull request #2556 from BerriAI/litellm_aws_secret_manager_support
fix(utils.py): initial commit for aws secret manager support
2024-03-16 18:41:58 -07:00
Krrish Dholakia
bc66ef9d5c fix(utils.py): fix aws secret manager + support key_management_settings
fixes the aws secret manager implementation and allows the user to set which keys they want to check thr
ough it
2024-03-16 16:47:50 -07:00
Ishaan Jaff
ac6c69ff89
Merge pull request #2559 from BerriAI/litellm_show_spend_correctly
(fix) admin ui - order spend by date
2024-03-16 16:43:13 -07:00
Ishaan Jaff
e3582d86c6
Merge pull request #2557 from BerriAI/litellm_clean_up_health_readiness
(fix) /health/readiness return success callback names as (str)
2024-03-16 16:38:01 -07:00
Ishaan Jaff
34a26f4d05 (feat) new ui build 2024-03-16 16:26:36 -07:00
Ishaan Jaff
2355e9dc51 (fix) admin ui - order spend by date 2024-03-16 16:15:10 -07:00
Ishaan Jaff
cb4c36b7f6 (fix) /health readiness return callback names 2024-03-16 15:56:07 -07:00
Ishaan Jaff
732ab69d32
Merge pull request #2553 from BerriAI/litellm_improve_health_readiness_perf
(feat) Proxy - improve health readiness perf (93% faster)
2024-03-16 15:38:45 -07:00
Krrish Dholakia
d8956e9255 fix(utils.py): initial commit for aws secret manager support 2024-03-16 14:37:46 -07:00
Ishaan Jaff
389e79d3b2 (fix) improve /health/readiness under high load 2024-03-16 14:14:17 -07:00
Krrish Dholakia
3de766c071 fix(proxy_server.py): fix linting errors 2024-03-16 14:02:36 -07:00
Krrish Dholakia
844d6828c8 fix(proxy_server.py): rename beta end user blocking endpoints
separating end user management from user management
2024-03-16 13:53:10 -07:00
Ishaan Jaff
61f129b9ab (feat) improve health readiness perf 2024-03-16 13:10:04 -07:00
Krrish Dholakia
dd151869a3 fix(blocked_user_list.py): check if end user blocked in db 2024-03-16 13:03:52 -07:00
Krrish Dholakia
ef0002f31c fix(proxy_server.py): write blocked user list to a db table
lets this persist across workers
2024-03-16 12:26:29 -07:00
Krrish Dholakia
2c2db9ce89 fix(proxy_server.py): bug fix on getting user obj from cache 2024-03-16 11:07:38 -07:00
Krrish Dholakia
48f96dd563 fix(caching.py): close redis connection pool upon proxy shutdown 2024-03-16 10:39:58 -07:00
Krish Dholakia
0368a335e6
Merge branch 'main' into support_anthropic_function_result 2024-03-16 09:58:08 -07:00
ishaan-jaff
177571bea3 (fix) backoff import 2024-03-16 08:53:06 -07:00
ishaan-jaff
2d7ca36ec4 (fix) errant print saying "Error importing .." msg 2024-03-15 21:47:52 -07:00
Krish Dholakia
4969ae0e9d
Merge pull request #2542 from BerriAI/litellm_redis_perf_improvements
89% Caching improvement - Async Redis completion calls + batch redis GET requests for a given key + call type
2024-03-15 18:58:36 -07:00
Krrish Dholakia
909341c4f2 fix(utils.py): async add to cache - for streaming 2024-03-15 18:25:40 -07:00
Krrish Dholakia
4912ad5cf4 test(test_custom_logger.py): fix async streaming test 2024-03-15 18:18:54 -07:00
Krrish Dholakia
3072137739 test(test_caching.py): fix async tests 2024-03-15 18:09:25 -07:00
Krrish Dholakia
8a20ea795b feat(batch_redis_get.py): batch redis GET requests for a given key + call type
reduces number of redis requests. 85ms latency improvement over 3 minutes of load (19k requests).
2024-03-15 14:54:16 -07:00
ishaan-jaff
fd93a68b0d (fix) fix error message raised on passing invalid tokens 2024-03-15 14:50:34 -07:00
Krrish Dholakia
226953e1d8 feat(batch_redis_get.py): batch redis GET requests for a given key + call type
reduces the number of GET requests we're making in high-throughput scenarios
2024-03-15 14:40:11 -07:00
ishaan-jaff
f3209b63cd (fix) locustfile used in load test 2024-03-15 12:38:37 -07:00
Zihao Li
91f467f55d Add tool result submission to claude 3 function call test and claude 3 multi-turn conversion to ensure alternating message roles 2024-03-16 01:40:36 +08:00
Krish Dholakia
32ca306123
Merge pull request #2535 from BerriAI/litellm_fireworks_ai_support
feat(utils.py): add native fireworks ai support
2024-03-15 10:02:53 -07:00
Krrish Dholakia
4e1dc7d62e fix(cohere.py): return usage as a pydantic object not dict 2024-03-15 10:00:22 -07:00
Krrish Dholakia
860b06d273 refactor(main.py): trigger new build 2024-03-15 09:42:23 -07:00
Krrish Dholakia
f7cf90a636 fix(bedrock.py): add all supported bedrock / anthropic messages api params 2024-03-15 09:41:40 -07:00
Krrish Dholakia
9909f44015 feat(utils.py): add native fireworks ai support
addresses - https://github.com/BerriAI/litellm/issues/777, https://github.com/BerriAI/litellm/issues/2486
2024-03-15 09:09:59 -07:00
Ishaan Jaff
31dcc6acf2
Merge pull request #2524 from BerriAI/litellm_fix_update_user
(fix) - update user error
2024-03-15 08:51:45 -07:00
ishaan-jaff
7f0cebe756 (ci/cd) check triggers 2024-03-15 08:21:16 -07:00
ishaan-jaff
fd33eda29d (ci/cd) check linked triggers 2024-03-15 08:17:55 -07:00
ishaan-jaff
a5450125c5 bump 1.31.13 -> 1.31.14 2024-03-15 08:11:11 -07:00
ishaan-jaff
fa1676b253 (fix) error cli users see when importing enterprise folder 2024-03-15 08:10:45 -07:00
Krrish Dholakia
5a2e024576 fix(factory.py): raise exception on invalid message being received 2024-03-15 07:55:29 -07:00
Zihao Li
807f999a66 Refactor to allow tool invoke conversion and tool results submission; Allow alternating consecutuve message roles and fix a bug 2024-03-15 22:47:11 +08:00
ishaan-jaff
82e44e4962 (ci/cd) check actions run 2024-03-14 20:58:22 -07:00