Commit graph

912 commits

Author SHA1 Message Date
Krrish Dholakia
0f1ff55a64 fix(proxy_server.py): improve error message on ui login error 2024-03-14 10:02:41 -07:00
ishaan-jaff
c8fbadeec2 (fix) importing PromptInjectionDetection 2024-03-13 21:24:37 -07:00
Krish Dholakia
8436507616 Merge pull request #2506 from BerriAI/litellm_update_db_perf_improvements
fix(proxy_server.py): move to using UPDATE + SET for track_cost_callback
2024-03-13 20:55:40 -07:00
Krrish Dholakia
3232feb123 fix(proxy_server.py): fix key caching logic 2024-03-13 19:10:24 -07:00
Krrish Dholakia
8f6af575e7 fix(proxy_server.py): maintain support for model specific budgets 2024-03-13 17:04:51 -07:00
Krrish Dholakia
1a6154ec74 fix(proxy_server.py): move to using UPDATE + SET for track_cost_callback 2024-03-13 16:13:37 -07:00
Ishaan Jaff
94553ca0b0 Merge pull request #2501 from BerriAI/litellm_fix_using_enterprise_docker
(fix) using enterprise folder on litellm Docker
2024-03-13 14:26:21 -07:00
Ishaan Jaff
a7a74047a9 Merge pull request #2493 from BerriAI/litellm_return_429_no_models_available
[Proxy] return 429 when no models available
2024-03-13 13:33:43 -07:00
Krish Dholakia
42b3577fd0 Merge pull request #2498 from BerriAI/litellm_prompt_injection_detection
feat(prompt_injection_detection.py): support simple heuristic similarity check for prompt injection attacks
2024-03-13 12:28:19 -07:00
ishaan-jaff
ede01e9c8e (fix) using enterprise folder on litellm 2024-03-13 12:16:58 -07:00
Krrish Dholakia
5769bd22c3 feat(prompt_injection_detection.py): support simple heuristic similarity check for prompt injection attacks 2024-03-13 10:32:21 -07:00
ishaan-jaff
2d75daa6ab (fix) issue with using litellm enterprise license 2024-03-13 10:30:31 -07:00
ishaan-jaff
95aa0f0353 (fix) errors fro litellm proxy 2024-03-13 08:05:32 -07:00
ishaan-jaff
9914710d6b (fix) return 429 error 2024-03-13 08:03:28 -07:00
Krish Dholakia
1f4f7d96a1 Merge pull request #2382 from BerriAI/litellm_cost_tracking_fix
fix(proxy_server.py): support cost tracking if general_settings is none
2024-03-12 19:15:23 -07:00
Krrish Dholakia
0510a0f4d4 fix(proxy_server.py): cache master key check 2024-03-12 15:15:33 -07:00
ishaan-jaff
b59e472fcd (fix) patch dynamoDB tea_model_alias bug 2024-03-12 11:17:12 -07:00
Krrish Dholakia
60219254a9 fix(proxy_server.py): fix /user/info for non-existent user id 2024-03-12 11:05:41 -07:00
Krrish Dholakia
5b5d3b10df test(test_key_generate_prisma.py): fix test to only let admin delete a key 2024-03-11 14:18:01 -07:00
Krrish Dholakia
366aaf744e fix(proxy_server.py): bug fix 2024-03-11 13:54:58 -07:00
Krrish Dholakia
1dcaba83d2 fix(proxy_server.py): prevent user from deleting non-user owned keys when they use ui 2024-03-11 12:13:30 -07:00
Krrish Dholakia
4b67e2ce10 fix(proxy_server.py): fix argon import 2024-03-11 11:33:34 -07:00
Krish Dholakia
774ceb741c Merge pull request #2426 from BerriAI/litellm_whisper_cost_tracking
feat: add cost tracking + caching for `/audio/transcription` calls
2024-03-09 19:12:06 -08:00
Krish Dholakia
ba9d96e65e Merge branch 'main' into litellm_faster_api_key_checking 2024-03-09 18:45:03 -08:00
Krrish Dholakia
ca496a8892 fix(proxy_server.py): check if master key is str before hashing 2024-03-09 16:51:11 -08:00
Krrish Dholakia
eda9f2ba81 fix(proxy_server.py): fix argon exceptions 2024-03-09 16:16:40 -08:00
Krrish Dholakia
b2ce963498 feat: add cost tracking + caching for transcription calls 2024-03-09 15:43:38 -08:00
Krish Dholakia
f461352908 Merge branch 'main' into litellm_load_balancing_transcription_endpoints 2024-03-08 23:08:47 -08:00
Krrish Dholakia
f9233fa5b9 fix(proxy_server.py): fix argon cfi checking 2024-03-08 22:01:44 -08:00
Ishaan Jaff
0f19e35f22 Merge pull request #2408 from BerriAI/litellm_no_store_reqs
[FEAT-liteLLM Proxy] Incognito Requests -  Don't log anything
2024-03-08 21:11:43 -08:00
Krrish Dholakia
93615682fe feat(proxy_server.py): working /audio/transcription endpoint 2024-03-08 18:20:27 -08:00
ishaan-jaff
8b5d255bee (fix) proxy setting success callbacks 2024-03-08 16:27:53 -08:00
Krrish Dholakia
8c6a4df3d4 fix(proxy_server.py): fix tagging of endpoints 2024-03-08 14:29:31 -08:00
Krrish Dholakia
29d0fcf34a feat(proxy_server.py): supports /audio/transcription endpoint on proxy 2024-03-08 14:28:07 -08:00
ishaan-jaff
b316b49c32 (feat) read passed api_version 2024-03-08 13:16:12 -08:00
Krrish Dholakia
b81c94e94f fix(proxy_server.py): use argon2 for faster api key checking
0.04s latency boost on load test
2024-03-07 21:48:18 -08:00
Krrish Dholakia
3c414c6357 fix(proxy_server.py): fix model alias map + add back testing 2024-03-07 07:56:51 -08:00
Krrish Dholakia
7d2df12733 fix(proxy_server.py): support cost tracking if general_settings is none
works if database_url is in env
2024-03-06 21:27:41 -08:00
Krish Dholakia
ede9647e49 Merge pull request #2377 from BerriAI/litellm_team_level_model_groups
feat(proxy_server.py): team based model aliases
2024-03-06 21:03:53 -08:00
Krrish Dholakia
df0eb170e6 fix(proxy_server.py): fix sql query 2024-03-06 19:41:12 -08:00
Krish Dholakia
050a056e09 Merge pull request #2347 from BerriAI/litellm_retry_rate_limited_requests
feat(proxy_server.py): retry if virtual key is rate limited
2024-03-06 19:23:11 -08:00
Krrish Dholakia
7bfadc258e feat(proxy_server.py): team based model aliases
allow setting model aliases at a team level (e.g. route all 'gpt-3.5-turbo' requests from team-1 to model-deployment-group-2)
2024-03-06 17:42:08 -08:00
ishaan-jaff
b6f3eb1434 (fix) remove unuse endpoint 2024-03-06 15:40:22 -08:00
ishaan-jaff
b0575bdcf0 (fix) admin UI swagger 2024-03-06 14:01:39 -08:00
ishaan-jaff
086de85625 (fix) update team_id 2024-03-05 19:09:19 -08:00
ishaan-jaff
3ca856fe39 (fix) _update_team_db 2024-03-05 19:03:27 -08:00
Krrish Dholakia
c963e2761b feat(proxy_server.py): retry if virtual key is rate limited
currently for chat completions
2024-03-05 19:00:03 -08:00
ishaan-jaff
a513a05a7f (fix) fix batch update user db 2024-03-05 16:46:58 -08:00
ishaan-jaff
7a72aa8796 (feat) show /model/metrics on Admin UI 2024-03-04 16:25:35 -08:00
ishaan-jaff
d1a3899882 (feat) show model metrics on admin panel 2024-03-04 13:44:13 -08:00