Commit graph

6804 commits

Author SHA1 Message Date
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
Krrish Dholakia
0609968853 test(test_key_generate_dynamodb.py): fix test 2024-02-06 14:36:24 -08:00
Krrish Dholakia
e35a7c32cb fix(proxy/utils.py): if langfuse trace id passed in, just send that as part of alert 2024-02-05 16:34:33 -08:00
Krrish Dholakia
cdbbedec36 bump: version 1.22.5 → 1.22.6 2024-02-05 16:26:30 -08:00
Krrish Dholakia
3b9ada07e0 fix(main.py): raise better error message for health check models without mode 2024-02-05 16:26:25 -08:00
ishaan-jaff
1f7c8e86a7 (fix) make sure route is str 2024-02-05 16:22:36 -08:00
Ishaan Jaff
5ebb1b4447
Merge pull request #1836 from BerriAI/litellm_fix_litellm_dashboard_keys
[Fix] UI - Security - Litellm UI Keys meant for litellm-dashboard shouldn't be allowed to make non-management related requests
2024-02-05 16:20:33 -08:00
ishaan-jaff
2b588a8786 (test) litellm-dashboard never allowed to /chat/completions 2024-02-05 16:11:33 -08:00
ishaan-jaff
8d7698f24d (fix) litellm-ui keys can never access /chat/completions 2024-02-05 16:10:49 -08:00
Krrish Dholakia
77fe71ee08 fix(utils.py): support together ai function calling 2024-02-05 15:30:44 -08:00
ishaan-jaff
006b5efef0 bump: version 1.22.4 → 1.22.5 2024-02-05 15:10:59 -08:00
Ishaan Jaff
5fc7041cf3
Merge pull request #1834 from BerriAI/litellm_sync_backup_model_info_with_root
[Feat] Sync model_prices_and_context_window.json and litellm/model_prices_and_context_window_backup.json
2024-02-05 15:08:49 -08:00
ishaan-jaff
7557a2535a (fix) model_prices 2024-02-05 15:04:39 -08:00
ishaan-jaff
70f36073dc (fix) pre commit hook to sync backup context_window mapping 2024-02-05 15:03:04 -08:00
ishaan-jaff
8b571159fc (feat) add pre-commit hook to check model_prices_and_context_window.json litellm/model_prices_and_context_window_backup.json 2024-02-05 15:00:13 -08:00
ishaan-jaff
a6836a0996 (feat) pre-commit hook to validate 2024-02-05 14:42:10 -08:00