ishaan-jaff
|
7b26b3b789
|
(ci/cd) run again
|
2024-02-06 18:25:15 -08:00 |
|
Krrish Dholakia
|
b6adeec347
|
fix(proxy_server.py): prisma client fixes for high traffic
|
2024-02-06 17:30:36 -08:00 |
|
Ishaan Jaff
|
73c6ce890b
|
Merge pull request #1859 from BerriAI/litellm_allow_using_budgets_without_keys
[Feat] Budgets for 'user' param passed to /chat/completions, /embeddings etc
|
2024-02-06 16:32:25 -08:00 |
|
ishaan-jaff
|
6369424629
|
(ci/cd) run again
|
2024-02-06 16:08:25 -08:00 |
|
Krish Dholakia
|
9e9fb747ce
|
Merge branch 'main' into litellm_slack_langfuse_alerting
|
2024-02-06 15:48:52 -08:00 |
|
ishaan-jaff
|
196787359f
|
(test) track_cost_ for end users
|
2024-02-06 15:25:51 -08:00 |
|
ishaan-jaff
|
52b864976b
|
(feat) support max_user_budget
|
2024-02-06 15:19:36 -08:00 |
|
Krrish Dholakia
|
be81183782
|
refactor(main.py): trigger deploy
n
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
8ba2c8dbf7
|
(fix) langfuse show semantic-similarity in tags
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
325ca43946
|
(feat) show semantic-cache on health/readiness
|
2024-02-06 15:17:40 -08:00 |
|
Krrish Dholakia
|
0d03b28a3b
|
test(test_completion.py): fix test
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
b5db630dba
|
(ci/cd) run again
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
43061d612d
|
(fix) mark semantic caching as beta test
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
e32c2beddd
|
(fix) semantic caching
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
f3de05cc54
|
(fix) test-semantic caching
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
f8248b2c79
|
(feat) redis-semantic cache on proxy
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
58f47c9e29
|
(fix) use semantic cache on proxy
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
91424b66d7
|
allow setting redis_semantic cache_embedding model
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
e2c88ce154
|
(feat) log semantic_sim to langfuse
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
e0d5c953d6
|
(feat) working semantic cache on proxy
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
c8d5714e59
|
(feat) redis-semantic cache
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
aa7580411d
|
(feat) working semantic-cache on litellm proxy
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
1d151e4777
|
(test) async semantic cache
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
08d72fd2a0
|
(feat) RedisSemanticCache - async
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
553b993473
|
(fix) semantic cache
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
2ad8b70f50
|
(test) semantic caching
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
a5afbf6d56
|
(test) semantic cache
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
a510adb1e6
|
(feat) working - sync semantic caching
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
d67a9ada4f
|
(feat )add semantic cache
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
d85b1f8816
|
(feat) show langfuse logging tags better through proxy
|
2024-02-06 15:17:35 -08:00 |
|
Krrish Dholakia
|
eee5353e77
|
fix(utils.py): round max tokens to be int always
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
647dbb9331
|
(ci/cd) run again
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
01701c95b8
|
(ci/cd) run again
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
5b63827430
|
(ci/cd) fix test_config_no_auth
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
6640690ad6
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
97dbf14b32
|
(fix) parallel_request_limiter debug
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
0d5f6cacc4
|
(ci/cd) run again
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
233590e8c2
|
(fix) proxy_startup test
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
b3a4982eda
|
(fix) rename proxy startup test
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
45ab0f01c0
|
(ci/cd) run in verbose mode
|
2024-02-06 15:17:35 -08:00 |
|
Krrish Dholakia
|
b47f9dcb6d
|
fix(ollama.py): support format for ollama
|
2024-02-06 15:17:35 -08:00 |
|
Krrish Dholakia
|
80eb8d0eae
|
fix(ollama_chat.py): explicitly state if ollama call is streaming or not
|
2024-02-06 15:17:35 -08:00 |
|
Krrish Dholakia
|
3db9830d4b
|
fix(utils.py): use print_verbose for statements, so debug can be seen when running sdk
|
2024-02-06 15:17:35 -08:00 |
|
Krrish Dholakia
|
d189e95045
|
fix(ollama_chat.py): fix ollama chat completion token counting
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
3b977679f8
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
7ccb7c00d8
|
(ci/cd) print debug info for test_proxy_gunicorn_startup_config_dict
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
ca029d13ee
|
(fix) proxy startup test
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
732ac6df49
|
(feat) proxy - upperbound params /key/generate
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
e21f906463
|
(test) test_upperbound_key_params
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
8d0c235004
|
(feat) upperbound_key_generate_params
|
2024-02-06 15:17:35 -08:00 |
|