Commit graph

5961 commits

Author SHA1 Message Date
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
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
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
ishaan-jaff
e846b8fca8 (test) ExceededTokenBudget 2024-01-22 12:13:41 -08:00
ishaan-jaff
8979b74d49 (feat) working budgets per key 2024-01-22 12:13:19 -08:00
Krrish Dholakia
29800d1e01 fix(azure_dall_e_2.py): handle azure not returning a 'retry-after' param 2024-01-22 12:02:02 -08:00
ishaan-jaff
de1502658d (test) budgets per key 2024-01-22 11:58:55 -08:00
ishaan-jaff
7ed3141c7d (feat) working create budgets per key 2024-01-22 11:58:20 -08:00
ishaan-jaff
8b599d4398 v0 max_budget per key 2024-01-22 11:33:34 -08:00
Krrish Dholakia
265f5ef6da docs(routing.md): add timeouts per model 2024-01-22 08:55:17 -08:00
ishaan-jaff
9988a39169 (ci/cd) deploy again 2024-01-22 08:25:17 -08:00
Ishaan Jaff
597effd5eb
Update ghcr_deploy.yml 2024-01-22 08:14:48 -08:00
Ishaan Jaff
0d747d52b8
Merge pull request #1505 from ShaunMaher/litellm_github_action_build_admin_ui
Litellm GitHub action build admin UI
2024-01-22 08:09:34 -08:00
Krrish Dholakia
2165dcf6fb fix(utils.py): fix callback logging 2024-01-21 00:56:30 -08:00
Krrish Dholakia
e2831e9c80 fix: fix proxy logging 2024-01-20 18:22:45 -08:00
Krrish Dholakia
6b8e6497f6 build(Dockerfile): set dockerfile to always use config 2024-01-20 17:46:52 -08:00
Krrish Dholakia
09b7235b31 fix: support info level logging on pkg + proxy 2024-01-20 17:45:47 -08:00
Krrish Dholakia
3e5b743b89 fix(caching.py): add logging module support for caching 2024-01-20 17:34:29 -08:00
ishaan-jaff
ccfcc39681 (test) custom key/generate 2024-01-20 10:13:32 -08:00
ishaan-jaff
6b7fd172a3 (docs) Custom /key/generate 2024-01-20 10:12:47 -08:00
ishaan-jaff
480f237fb5 (test) add custom_key_generate test 2024-01-20 09:59:04 -08:00
Ishaan Jaff
d60af6fff5
Merge pull request #1535 from kihaya/docs/fix_sample_code_import_for_providers
docs: Fix import statement for provider's sample code
2024-01-20 08:42:42 -08:00
ishaan-jaff
13eb40e7bd v0 using custom_key_generate 2024-01-20 08:39:52 -08:00