Commit graph

6231 commits

Author SHA1 Message Date
Krrish Dholakia
1e3f14837b fix(router.py): fix dereferencing param order 2024-01-23 07:19:37 -08:00
Krrish Dholakia
ca5fb3f7f1 test(test_router.py): fix test check 2024-01-23 07:07:30 -08:00
Krrish Dholakia
502f8b478c test(test_exceptions.py): fix test name 2024-01-23 06:57:18 -08:00
Krrish Dholakia
23b59ac9b8 fix(utils.py): fix content policy violation check for streaming 2024-01-23 06:55:04 -08:00
Krrish Dholakia
9327d76379 docs(users.md): add key budgets to docs 2024-01-23 06:42:13 -08:00
Krrish Dholakia
53b879bc6c fix(router.py): ensure no unsupported args are passed to completion() 2024-01-22 22:33:06 -08:00
Krrish Dholakia
f19f0dad89 fix(router.py): fix client init 2024-01-22 22:15:39 -08:00
ishaan-jaff
bc3332fc7c (docs) use proxy + Sagemaker stream test 2024-01-22 22:11:06 -08:00
Ishaan Jaff
6d105754d7
Merge pull request #1561 from BerriAI/litellm_sagemaker_streaming
[Feat] Add REAL Sagemaker streaming
2024-01-22 22:10:20 -08:00
ishaan-jaff
bccbb0852d (test) test_completion_sagemaker_stream 2024-01-22 21:57:26 -08:00
ishaan-jaff
c8084bb9d9 v0 sagemaker_stream 2024-01-22 21:53:16 -08:00
ishaan-jaff
9652280c15 (docs) add cookbook on sagemaker streaming 2024-01-22 21:52:31 -08:00
ishaan-jaff
f29de0024a (v0) sagemaker streaming 2024-01-22 21:50:40 -08:00
ishaan-jaff
802fd6cebf v0 add TokenIterator, stream support 2024-01-22 21:49:44 -08:00
Krrish Dholakia
fe489ec22b test(test_key_generate_dynamodb.py): fix test 2024-01-22 21:45:30 -08:00
Krrish Dholakia
4babd67c79 test(test_key_generate_dynamodb.py): fix test 2024-01-22 21:44:13 -08:00
Krrish Dholakia
5e0d99b2ef fix(router.py): fix order of dereferenced dictionaries 2024-01-22 21:42:25 -08:00
Krrish Dholakia
7079b951de test(test_key_generate_prisma.py): fix test 2024-01-22 21:12:03 -08:00
Krish Dholakia
bedb08bdef
Merge pull request #1557 from BerriAI/litellm_emit_spend_logs
feat(utils.py): emit response cost as part of logs
2024-01-22 21:02:40 -08:00
Krrish Dholakia
42a2a2fe94 test(test_custom_callback_input.py): fix assert 2024-01-22 20:39:14 -08:00
Krrish Dholakia
11e3ee4411 test: fix tests 2024-01-22 20:20:17 -08:00
Krrish Dholakia
3e8c8ef507 fix(openai.py): fix linting issue 2024-01-22 18:20:15 -08:00
Krish Dholakia
b1cced16fc
Merge pull request #1556 from BerriAI/litellm_importlib_issue
fix(utils.py): move from pkg_resources to importlib
2024-01-22 15:56:07 -08:00
Ishaan Jaff
5e98c88521
Merge pull request #1552 from BerriAI/litellm_budget_per_key
[Feat] Add Budgets Per API Key - LiteLLM Proxy
2024-01-22 15:54:06 -08:00
ishaan-jaff
c9e5e07a96 (chore) fix merge conflicts 2024-01-22 15:53:12 -08:00
Krrish Dholakia
e917d0eee6 feat(utils.py): emit response cost as part of logs 2024-01-22 15:53:04 -08:00
Ishaan Jaff
db68774d60
Merge branch 'main' into litellm_budget_per_key 2024-01-22 15:49:57 -08:00
Krrish Dholakia
06f6f128b6 refactor(__init__.py): adds init.py file in tokenizers 2024-01-22 15:33:16 -08:00
Krrish Dholakia
36c6d3cd90 fix(utils.py): fix debug log 2024-01-22 15:15:34 -08:00
Krrish Dholakia
a343c4d22f refactor(utils.py): fix linting errors 2024-01-22 15:15:34 -08:00
Krrish Dholakia
25311293e4 fix(utils.py): fix sync/async stream logging 2024-01-22 15:15:34 -08:00
Krrish Dholakia
074ea17325 fix: support streaming custom cost completion tracking 2024-01-22 15:15:34 -08:00
Krrish Dholakia
82bbf336d5 docs(sidebars.js): add custom pricing to docs 2024-01-22 15:15:34 -08:00
Krrish Dholakia
2ce4258cc0 fix(main.py): support custom pricing for embedding calls 2024-01-22 15:15:34 -08:00
Krrish Dholakia
39a1b4c3b5 fix(main.py): support custom pricing for embedding calls 2024-01-22 15:15:34 -08:00
Krrish Dholakia
276a685a59 feat(utils.py): support custom cost tracking per second
https://github.com/BerriAI/litellm/issues/1374
2024-01-22 15:15:34 -08:00
Krrish Dholakia
128cf4a81d fix(utils.py): move from pkg_resources to importlib 2024-01-22 15:05:09 -08:00
ishaan-jaff
44f756efb5 bump: version 1.18.8 → 1.18.9 2024-01-22 14:58:57 -08:00
Ishaan Jaff
6f8a6e1dae
Merge pull request #1555 from BerriAI/litellm_fix_router_tracking_tpm_rpm_with_fallbacks
[Fix] Router - Usage Based Routing with fallbacks (Track the correct tpm/rpm)
2024-01-22 14:45:49 -08:00
ishaan-jaff
14585c9966 (fix) router - update model_group on fallback 2024-01-22 14:41:55 -08:00
ishaan-jaff
982cb04764 (feat) mock_response set custom_llm_provider in hidden param 2024-01-22 14:22:16 -08:00
ishaan-jaff
5807718a69 (test) usage based routing with fallbacks 2024-01-22 14:21:30 -08:00
Ishaan Jaff
5700d60e1a
Merge pull request #1538 from BerriAI/litellm_use_custom_key_gen
[Feat] Proxy Auth - Use custom_key_generate
2024-01-22 14:21:19 -08:00
Krrish Dholakia
6c39b2855f fix(utils.py): fix async/sync streaming logging 2024-01-22 13:54:51 -08:00
ishaan-jaff
9d34281025 (fix) spend tracking per key - when no cache hit 2024-01-22 13:18:33 -08:00
ishaan-jaff
76214baab9 (docs) budget per key 2024-01-22 13:18:07 -08:00
ishaan-jaff
8e41ec96b3 (test) dynamoDB Budgets per key 2024-01-22 12:54:37 -08:00
ishaan-jaff
6120e1c36d (fix) dynamo max_budget per key 2024-01-22 12:50:14 -08:00
ishaan-jaff
de7663ead3 (fix) make max_budget optional for LiteLLM_VerificationToken 2024-01-22 12:20:38 -08:00
ishaan-jaff
152456e10d (test) test_call_with_key_over_budget_stream 2024-01-22 12:16:16 -08:00