Ishaan Jaff
|
6091c7798e
|
use cache tools as dep
|
2024-06-24 17:31:59 -07:00 |
|
Ishaan Jaff
|
d0b1d3e9cc
|
fix python3.8 with cachetools
|
2024-06-24 17:30:48 -07:00 |
|
Ishaan Jaff
|
effc7579ac
|
fix install on python 3.8
|
2024-06-24 17:27:14 -07:00 |
|
Ishaan Jaff
|
b13a93d9bc
|
cleanup InMemoryCache
|
2024-06-24 17:24:59 -07:00 |
|
Ishaan Jaff
|
4053c7aeb3
|
use lru cache
|
2024-06-24 17:15:53 -07:00 |
|
Ishaan Jaff
|
2e3119e75f
|
fix testing env
|
2024-06-24 17:12:11 -07:00 |
|
Ishaan Jaff
|
5bbbb5a7ee
|
fix router.py
|
2024-06-24 17:10:34 -07:00 |
|
Ishaan Jaff
|
e5ab0d4ecd
|
fix InMemoryCache
|
2024-06-24 17:08:30 -07:00 |
|
Ishaan Jaff
|
974d92ff45
|
fix use caching lib
|
2024-06-24 17:03:23 -07:00 |
|
Ishaan Jaff
|
8a66e074ce
|
fix in mem cache tests
|
2024-06-22 19:52:18 -07:00 |
|
Ishaan Jaff
|
fbef5013a1
|
Merge branch 'main' into litellm_fix_in_mem_usage
|
2024-06-22 19:23:37 -07:00 |
|
Ishaan Jaff
|
0418db3044
|
fix caching clear in memory cache mem util
|
2024-06-22 19:21:37 -07:00 |
|
Krish Dholakia
|
eaad36a2cb
|
Merge pull request #4349 from BerriAI/litellm_dynamic_tpm_limits
feat(dynamic_rate_limiter.py): Dynamic tpm quota (multiple projects)
|
2024-06-22 19:15:05 -07:00 |
|
Krish Dholakia
|
961e7ac95d
|
Merge branch 'main' into litellm_dynamic_tpm_limits
|
2024-06-22 19:14:59 -07:00 |
|
Ishaan Jaff
|
fa554ae218
|
fix - clean up in memory cache
|
2024-06-22 18:46:30 -07:00 |
|
Ishaan Jaff
|
4fc8efd640
|
bump: version 1.40.23 → 1.40.24
|
2024-06-22 18:00:40 -07:00 |
|
Krrish Dholakia
|
c4b1540ce0
|
fix(utils.py): support streamingchoices in 'get_response_string
|
2024-06-22 15:45:52 -07:00 |
|
Krrish Dholakia
|
bae7377128
|
docs(team_budgets.md): fix script
/
|
2024-06-22 15:42:05 -07:00 |
|
Krrish Dholakia
|
fc4e900a23
|
docs(team_budgets.md): update docs with script for testing dynamic rate limiting
|
2024-06-22 15:26:58 -07:00 |
|
Krrish Dholakia
|
a31a05d45d
|
feat(dynamic_rate_limiter.py): working e2e
|
2024-06-22 14:41:22 -07:00 |
|
Ishaan Jaff
|
cb828a464a
|
fix langfuse tests in_memory_langfuse_clients
|
2024-06-22 13:59:36 -07:00 |
|
Ishaan Jaff
|
ebbe97910c
|
Merge pull request #4360 from BerriAI/litellm_fix_access_audio_endpoint
fix[ - Can't access /v1/audio/speech with some user key
|
2024-06-22 13:46:50 -07:00 |
|
Ishaan Jaff
|
ab38a90be0
|
fix /audio/speech
|
2024-06-22 13:45:34 -07:00 |
|
Ishaan Jaff
|
c44e5a3d93
|
testing - use in memory langfuse client cache
|
2024-06-22 13:40:34 -07:00 |
|
Ishaan Jaff
|
b201402b0b
|
fix testing - we had two files running the exact same langfuse test
|
2024-06-22 13:32:28 -07:00 |
|
Ishaan Jaff
|
c4f6b903b3
|
ui - new build
|
2024-06-22 09:13:34 -07:00 |
|
Ishaan Jaff
|
1a4ddf9a8e
|
Merge pull request #4356 from BerriAI/litellm_test_routes_on_proxy
[Test] Test routes on LiteLLM Proxy always includes OpenAI Routes
|
2024-06-22 09:12:30 -07:00 |
|
Ishaan Jaff
|
d32b8d589b
|
Merge pull request #4357 from BerriAI/litellm_use_jwt_in_cookies
[Security Fix - Proxy Server ADMIN UI] - Store credentials in cookies + use strong JWT signing secret
|
2024-06-22 09:12:17 -07:00 |
|
Krrish Dholakia
|
f814f24d9d
|
fix(litellm_logging.py): Fix gemini google ai studio system prompt logging
Fixes https://github.com/BerriAI/litellm/issues/2963
|
2024-06-22 09:11:23 -07:00 |
|
Ishaan Jaff
|
066ed01d0f
|
read token from cookie
|
2024-06-22 09:05:06 -07:00 |
|
Ishaan Jaff
|
c86efa55a5
|
use hash of master key encode the jwt
|
2024-06-22 08:58:31 -07:00 |
|
Ishaan Jaff
|
03d1d9229d
|
ui - use cookies to return JWTs
|
2024-06-22 08:50:26 -07:00 |
|
Ishaan Jaff
|
204f7725ee
|
ui - read jwts from cookie
|
2024-06-22 08:47:43 -07:00 |
|
Ishaan Jaff
|
b2a1cadf8c
|
test test_routes_on_litellm_proxy
|
2024-06-22 08:19:17 -07:00 |
|
Krrish Dholakia
|
709bd9678c
|
bump: version 1.40.22 → 1.40.23
|
2024-06-22 00:40:11 -07:00 |
|
Krrish Dholakia
|
532f24bfb7
|
refactor: instrument 'dynamic_rate_limiting' callback on proxy
|
2024-06-22 00:32:29 -07:00 |
|
Krish Dholakia
|
f192b76ed4
|
Merge pull request #4344 from BerriAI/litellm_refactor_langfuse_slack_trace_url
refactor(litellm_logging.py): refactors how slack_alerting generates langfuse trace url
|
2024-06-21 23:37:38 -07:00 |
|
Krrish Dholakia
|
068e8dff5b
|
feat(dynamic_rate_limiter.py): passing base case
|
2024-06-21 22:46:46 -07:00 |
|
Krrish Dholakia
|
5e893ed13e
|
fix(utils.py): Fix anthropic tool calling exception mapping
Fixes https://github.com/BerriAI/litellm/issues/4348
|
2024-06-21 21:20:49 -07:00 |
|
Krrish Dholakia
|
44bd9548d9
|
docs(anthropic.md): update with correct model string
|
2024-06-21 21:16:07 -07:00 |
|
Krrish Dholakia
|
000d678445
|
fix(utils.py): improve coverage for anthropic exception mapping
|
2024-06-21 21:15:10 -07:00 |
|
Ishaan Jaff
|
24addd8a4f
|
fix test test_router_completion_streaming
|
2024-06-21 21:02:34 -07:00 |
|
Ishaan Jaff
|
b4d95e740e
|
fix get_logging_payload
|
2024-06-21 20:42:28 -07:00 |
|
Krrish Dholakia
|
a028600932
|
feat(dynamic_rate_limiter.py): update cache with active project
|
2024-06-21 20:25:40 -07:00 |
|
Ishaan Jaff
|
4cd1171abb
|
Merge pull request #4350 from CaseMark/print-content-fallback
Print content window fallbacks on startup to help verify configuration
|
2024-06-21 20:01:22 -07:00 |
|
Steven Osborn
|
0ab6a18516
|
Print content window fallbacks on startup to help verify configuration
|
2024-06-21 19:43:26 -07:00 |
|
Krrish Dholakia
|
2545da777b
|
feat(dynamic_rate_limiter.py): initial commit for dynamic rate limiting
Closes https://github.com/BerriAI/litellm/issues/4124
|
2024-06-21 18:41:31 -07:00 |
|
Ishaan Jaff
|
98c131e1e9
|
bump: version 1.40.21 → 1.40.22
|
2024-06-21 18:12:12 -07:00 |
|
Ishaan Jaff
|
662cb5a5ec
|
ui - new build
|
2024-06-21 18:12:12 -07:00 |
|
Ishaan Jaff
|
6b63b663b9
|
Merge pull request #4345 from BerriAI/litellm_fix_cost_tracking_tags
[Fix + Test] - Spend tags not getting stored on 1.40.9
|
2024-06-21 17:34:27 -07:00 |
|