ishaan-jaff
|
b63fe39ed2
|
(fix) semantic cache
|
2024-02-06 13:30:17 -08:00 |
|
ishaan-jaff
|
4450be0a64
|
(test) semantic caching
|
2024-02-06 13:30:17 -08:00 |
|
ishaan-jaff
|
80e1d901d8
|
(test) semantic cache
|
2024-02-06 13:30:17 -08:00 |
|
ishaan-jaff
|
80865f93b8
|
(feat) working - sync semantic caching
|
2024-02-06 13:30:17 -08:00 |
|
ishaan-jaff
|
168a2f7806
|
(feat )add semantic cache
|
2024-02-06 13:30:17 -08:00 |
|
ishaan-jaff
|
a73d57b32b
|
(feat) show langfuse logging tags better through proxy
|
2024-02-06 13:30:17 -08:00 |
|
Krrish Dholakia
|
fa5f4b9774
|
test(test_completion.py): fix test
|
2024-02-06 13:29:47 -08:00 |
|
ishaan-jaff
|
79c225a60f
|
(ci/cd) run again
|
2024-02-06 13:26:48 -08:00 |
|
Ishaan Jaff
|
8a8f538329
|
Merge pull request #1829 from BerriAI/litellm_add_semantic_cache
[Feat] Add Semantic Caching to litellm💰
|
2024-02-06 13:18:59 -08:00 |
|
Krrish Dholakia
|
420d2754d7
|
fix(utils.py): round max tokens to be int always
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
bc6d29f879
|
(ci/cd) run again
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
1bcd2eafd2
|
(ci/cd) run again
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
86c84d72e5
|
(ci/cd) fix test_config_no_auth
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
0f6a9242ec
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
f8491feebd
|
(fix) parallel_request_limiter debug
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
43cb836c4f
|
(ci/cd) run again
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
b1b5daf73d
|
(fix) proxy_startup test
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
ec5b812989
|
(fix) rename proxy startup test
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
249482b3f7
|
(ci/cd) run in verbose mode
|
2024-02-06 13:17:57 -08:00 |
|
Krrish Dholakia
|
4d76af89f3
|
fix(ollama.py): support format for ollama
|
2024-02-06 13:17:57 -08:00 |
|
Krrish Dholakia
|
f9b5e9ea62
|
fix(ollama_chat.py): explicitly state if ollama call is streaming or not
|
2024-02-06 13:17:57 -08:00 |
|
Krrish Dholakia
|
34fcb3c984
|
fix(utils.py): use print_verbose for statements, so debug can be seen when running sdk
|
2024-02-06 13:17:57 -08:00 |
|
Krrish Dholakia
|
3409ac7690
|
fix(ollama_chat.py): fix ollama chat completion token counting
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
f2070d025e
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
6ea17be098
|
(ci/cd) print debug info for test_proxy_gunicorn_startup_config_dict
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
a24041b624
|
(fix) proxy startup test
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
1ef8b459ce
|
(feat) proxy - upperbound params /key/generate
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
2ce4153ace
|
(test) test_upperbound_key_params
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
0871327ff0
|
(feat) upperbound_key_generate_params
|
2024-02-06 13:17:57 -08:00 |
|
ishaan-jaff
|
d09aa560f3
|
(docs) upperbound_key_generate_params
|
2024-02-06 13:17:57 -08:00 |
|
Krrish Dholakia
|
f8380c638f
|
fix(langfuse.py): support logging failed llm api calls to langfuse
|
2024-02-06 13:17:57 -08:00 |
|
Krrish Dholakia
|
67dce555ec
|
fix(utils.py): round max tokens to be int always
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
38445ca508
|
(ci/cd) run again
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
7c9ada1b19
|
(ci/cd) run again
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
47e056d2ea
|
(ci/cd) fix test_config_no_auth
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
adb67da026
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
bdb9fc8f20
|
(fix) parallel_request_limiter debug
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
697109b7ec
|
(ci/cd) run again
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
61e5f2a79b
|
(fix) proxy_startup test
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
d94d925c3b
|
(fix) rename proxy startup test
|
2024-02-06 13:17:26 -08:00 |
|
ishaan-jaff
|
ac31fe0081
|
(ci/cd) run in verbose mode
|
2024-02-06 13:17:26 -08:00 |
|
Krrish Dholakia
|
7055793609
|
fix(ollama.py): support format for ollama
|
2024-02-06 13:17:26 -08:00 |
|
Krrish Dholakia
|
b7f1bd696e
|
fix(utils.py): round max tokens to be int always
|
2024-02-06 13:15:51 -08:00 |
|
ishaan-jaff
|
eb779c61c6
|
(ci/cd) run again
|
2024-02-06 13:15:51 -08:00 |
|
ishaan-jaff
|
2a7b07ffca
|
(ci/cd) run again
|
2024-02-06 13:15:51 -08:00 |
|
ishaan-jaff
|
79f444edda
|
(ci/cd) fix test_config_no_auth
|
2024-02-06 13:15:51 -08:00 |
|
ishaan-jaff
|
9355fc62a7
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 13:15:51 -08:00 |
|
ishaan-jaff
|
b4372457c4
|
(fix) parallel_request_limiter debug
|
2024-02-06 13:15:51 -08:00 |
|
ishaan-jaff
|
84942bb694
|
(ci/cd) run again
|
2024-02-06 13:15:51 -08:00 |
|
ishaan-jaff
|
0719c32f9e
|
(fix) proxy_startup test
|
2024-02-06 13:15:51 -08:00 |
|