Commit graph

7072 commits

Author SHA1 Message Date
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
6de6da71b7 bump: version 1.22.8 → 1.22.9 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
334acfb5f8 (ci/cd) run pytest without -s 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
fbf95ca9c7 bump: version 1.22.7 → 1.22.8 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
944833b04a build(requirements.txt): update the proxy requirements.txt 2024-02-06 15:17:35 -08:00
Krrish Dholakia
7b286f38ce bump: version 1.22.6 → 1.22.7 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
ishaan-jaff
0996ea3f36 (docs) upperbound_key_generate_params 2024-02-06 15:17:35 -08:00
Krrish Dholakia
f363f0f5ba fix(langfuse.py): support logging failed llm api calls to langfuse 2024-02-06 15:17:35 -08:00
John HU
f48c92e817 Fix admin UI title and description 2024-02-06 15:17:35 -08:00
Krish Dholakia
2dab09cde1 Update model_prices_and_context_window.json 2024-02-06 15:17:35 -08:00
ishaan-jaff
4e3f048967 (feat) max_user_budget 2024-02-06 15:16:20 -08:00
ishaan-jaff
047b2f9b1a (Feat) support max_user_budget 2024-02-06 15:13:59 -08:00
Krrish Dholakia
0609968853 test(test_key_generate_dynamodb.py): fix test 2024-02-06 14:36:24 -08:00
Krish Dholakia
e36566a212
Merge branch 'main' into litellm_admin_ui_view_all_keys 2024-02-06 14:34:57 -08:00
Krish Dholakia
db68b837e2
Merge pull request #1847 from BerriAI/litellm_vertex_ai_streaming_fix
fix(utils.py): return finish reason for last vertex ai chunk
2024-02-06 14:34:09 -08:00
Krish Dholakia
f70bbc7b2e
Merge branch 'main' into litellm_vertex_ai_streaming_fix 2024-02-06 14:33:54 -08:00
Krish Dholakia
284a256ccf
Merge pull request #1856 from BerriAI/litellm_fix_proxy_health_readiness
fix(proxy_server.py): do a health check on db before returning if proxy ready (if db connected)
2024-02-06 14:32:15 -08:00
Krish Dholakia
4fe4d0c1f3
Merge branch 'main' into litellm_fix_proxy_health_readiness 2024-02-06 14:31:57 -08:00
Krrish Dholakia
191eef06de build(requirements.txt): fix dependency 2024-02-06 14:10:56 -08:00
ishaan-jaff
223cc88f0c (ci/cd) run again 2024-02-06 14:00:27 -08:00
ishaan-jaff
7f870ebced (feat) redis-semantic cache on proxy 2024-02-06 13:58:20 -08:00
ishaan-jaff
3fa5bba4ea (fix) add redisvl==0.0.7 2024-02-06 13:58:20 -08:00
Krrish Dholakia
c46aca7951 refactor(main.py): trigger deploy
n
2024-02-06 13:58:20 -08:00
ishaan-jaff
2b9a48eb6c (fix) redisvl requirements.txt issue 2024-02-06 13:58:20 -08:00