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
|
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
|
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
|
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 |
|
ishaan-jaff
|
9988a39169
|
(ci/cd) deploy again
|
2024-01-22 08:25:17 -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
|
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
|
480f237fb5
|
(test) add custom_key_generate test
|
2024-01-20 09:59:04 -08:00 |
|
ishaan-jaff
|
13eb40e7bd
|
v0 using custom_key_generate
|
2024-01-20 08:39:52 -08:00 |
|
Ishaan Jaff
|
435d4b9279
|
Merge pull request #1534 from BerriAI/litellm_custom_cooldown_times
[Feat] Litellm.Router set custom cooldown times
|
2024-01-19 20:49:17 -08:00 |
|
ishaan-jaff
|
ccbc47122c
|
(fix) test caching
|
2024-01-19 20:45:10 -08:00 |
|
ishaan-jaff
|
84684c50fa
|
(fix) router - timeout exception mapping
|
2024-01-19 20:30:41 -08:00 |
|
Krrish Dholakia
|
7cf0bb475f
|
fix(proxy_server.py): run all endpoints through custom auth
|
2024-01-19 20:24:33 -08:00 |
|
Krrish Dholakia
|
b07677c6be
|
fix(gemini.py): support streaming
|
2024-01-19 20:21:34 -08:00 |
|
Ishaan Jaff
|
b59e67f099
|
Merge pull request #1529 from BerriAI/litellm_router_add_type_hints
[Feat] Add typehints for litellm.Router
|
2024-01-19 19:45:54 -08:00 |
|
ishaan-jaff
|
16b688d1ff
|
(feat) router - set custom cooldown times
|
2024-01-19 19:43:41 -08:00 |
|
ishaan-jaff
|
0fa9d8af82
|
(test) custom cooldown times - router
|
2024-01-19 19:41:52 -08:00 |
|
Krrish Dholakia
|
2c2163e4e5
|
fix(proxy_server.py): fix key info to handle pydantic v1
|
2024-01-19 18:52:09 -08:00 |
|
Krrish Dholakia
|
f2a8ceddc2
|
fix(utils.py): revert exception mapping change
|
2024-01-19 17:39:35 -08:00 |
|
Krrish Dholakia
|
f05aba1f85
|
fix(utils.py): add metadata to logging obj on setup, if exists
|
2024-01-19 17:29:47 -08:00 |
|
Krrish Dholakia
|
1ec5083542
|
fix(anthropic.py): fix pr for anthropic headers
|
2024-01-19 17:06:24 -08:00 |
|
Krrish Dholakia
|
1be4f7d2d1
|
fix(test_key_generate_prisma.py): fix testing
n
|
2024-01-19 16:53:46 -08:00 |
|
ishaan-jaff
|
91e57bd039
|
(fix) add router typehints
|
2024-01-19 16:32:43 -08:00 |
|
ishaan-jaff
|
a9cf6cec80
|
(feat) add typehints for litellm.acompletion
|
2024-01-19 16:05:26 -08:00 |
|
ishaan-jaff
|
b730482aaf
|
v0
|
2024-01-19 15:49:37 -08:00 |
|
Ishaan Jaff
|
6134b655e8
|
Merge pull request #1513 from costly-ai/main
Allow overriding headers for anthropic
|
2024-01-19 15:21:45 -08:00 |
|
ishaan-jaff
|
6bc7cc46b4
|
(docs) router debugging
|
2024-01-19 15:18:00 -08:00 |
|