phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
15012 commits 1603 branches 645 tags 320 MiB
Commit graph

99 commits

Author SHA1 Message Date
Krrish Dholakia
80e7310c5c feat(lakera_ai.py): support running prompt injection detection lakera check pre-api call 2024-07-22 20:16:05 -07:00
Krrish Dholakia
99a5436ed5 feat(lakera_ai.py): control running prompt injection between pre-call and in_parallel 2024-07-22 20:04:42 -07:00
Ishaan Jaff
e66a735304 fix lakera ai tests 2024-07-19 07:49:57 -07:00
Ishaan Jaff
75ca53fab5 fix linting errors on main 2024-07-18 13:32:48 -07:00
Ishaan Jaff
eedacf5193
Merge branch 'main' into litellm_run_moderation_check_on_embedding 2024-07-18 12:44:30 -07:00
Krish Dholakia
57f6923ab6
Merge pull request #4729 from vingiarrusso/vgiarrusso/guardrails 
Add enabled_roles to Guardrails configuration, Update Lakera guardrail moderation hook
 2024-07-17 22:24:35 -07:00
Ishaan Jaff
b2bf5ad3d0 lakera run on /embeddings 2024-07-17 18:27:05 -07:00
Krrish Dholakia
07d90f6739 feat(aporio_ai.py): support aporio ai prompt injection for chat completion requests 
Closes https://github.com/BerriAI/litellm/issues/2950
 2024-07-17 16:38:47 -07:00
Vinnie Giarrusso
a4b41e28a8 remove more unused imports 2024-07-16 12:25:06 -07:00
Vinnie Giarrusso
6ff863ee00 Add enabled_roles to Guardrails configuration, Update Lakera guardrail moderation hook 2024-07-16 01:52:08 -07:00
Krrish Dholakia
6b78e39600 feat(guardrails.py): allow setting logging_only in guardrails_config for presidio pii masking integration 2024-07-13 12:22:17 -07:00
Ishaan Jaff
1028be6308 feat- control lakera ai per llm call 2024-07-03 16:34:23 -07:00
Ishaan Jaff
2dcf06ce7d
Merge pull request #4525 from BerriAI/litellm_control_lakera_per_llm_call 
[Feat] Control Lakera AI per Request
 2024-07-02 18:02:43 -07:00
Ishaan Jaff
23f8d23acb correct guardrail name 2024-07-02 17:50:23 -07:00
Ishaan Jaff
b6af67344c feat - control lakera per call 2024-07-02 17:34:05 -07:00
Ishaan Jaff
9f8572e427 check if key does not want secret detection to run 2024-07-02 17:05:53 -07:00
Ishaan Jaff
e2046bd59c feat - laker return orig response from lakera api 2024-06-28 16:13:44 -07:00
Ishaan Jaff
eaa6441030 test fix secret detection 2024-06-27 17:42:44 -07:00
Ishaan Jaff
baf55a86c9 fix secret scanner 2024-06-27 15:20:30 -07:00
Ishaan Jaff
84ee37086c add stricter secret detection 2024-06-27 15:12:13 -07:00
Ishaan Jaff
552bac586f feat - improve secret detection 2024-06-27 15:07:38 -07:00
Ishaan Jaff
304e84f87c clean up secret detection 2024-06-25 17:25:53 -07:00
Ishaan Jaff
e4653e6032 fix async_pre_call_hook 2024-06-25 16:38:47 -07:00
Ishaan Jaff
4aa686bb05 feat - add secret detection 2024-06-25 16:23:56 -07:00
Ishaan Jaff
2f9aa308f1 fix - remove deprecated clickhouse utils 2024-06-15 15:33:26 -07:00
Krrish Dholakia
3b913443fe feat(vertex_httpx.py): Moving to call vertex ai via httpx (instead of their sdk). Allows us to support all their api updates. 2024-06-12 16:47:00 -07:00
Krrish Dholakia
6cca5612d2 refactor: replace 'traceback.print_exc()' with logging library 
allows error logs to be in json format for otel logging
 2024-06-06 13:47:43 -07:00
Ishaan Jaff
45cb899687 fix - working filter by tag query 2024-06-03 15:12:09 -07:00
Ishaan Jaff
03ec8219a4 fix - lakera ai integration 2024-05-23 15:25:26 -07:00
Ishaan Jaff
ec41226ee8 feat - add lakera ai prompt injection detection 2024-05-23 15:16:46 -07:00
Ishaan Jaff
6aad4e38d3 feat - add debugging for moderation response 2024-05-23 13:24:09 -07:00
Ishaan Jaff
1fe035c6dd feat - add open ai moderations check 2024-05-23 13:08:06 -07:00
Ishaan Jaff
5b51acc773 fix type hints on main 2024-05-13 20:21:23 -07:00
Ishaan Jaff
fa4dcbd37c ui - round up spend per tag 2024-05-13 17:31:29 -07:00
Ishaan Jaff
51961387a2 ui - filter tags by starttime and endtime 2024-05-13 17:15:25 -07:00
Krrish Dholakia
4a3b084961 feat(bedrock_httpx.py): moves to using httpx client for bedrock cohere calls 2024-05-11 13:43:08 -07:00
Krrish Dholakia
6575143460 feat(proxy_server.py): return litellm version in response headers 2024-05-08 16:00:08 -07:00
Krrish Dholakia
b6cd200676 fix(llm_guard.py): enable request-specific llm guard flag 2024-04-08 21:15:33 -07:00
Ishaan Jaff
73fce02392 ui - view spend per tag 2024-04-04 17:18:01 -07:00
Ishaan Jaff
ac5507bd84 ui show spend per tag 2024-04-04 16:57:45 -07:00
Ishaan Jaff
da20aecb16 (fix) check size of data to predict 2024-03-30 11:34:20 -07:00
Krrish Dholakia
1046a63521 test(test_llm_guard.py): unit testing for key-level llm guard enabling 2024-03-26 17:55:53 -07:00
Krrish Dholakia
6d418a2920 fix(llm_guard.py): working llm-guard 'key-specific' mode 2024-03-26 17:47:20 -07:00
Krrish Dholakia
e10eb8f6fe feat(llm_guard.py): enable key-specific llm guard check 2024-03-26 17:21:51 -07:00
Ishaan Jaff
5d121a9f3c (fix) stop using f strings with logger 2024-03-25 10:47:18 -07:00
Krrish Dholakia
b5457beba6 fix(llm_guard.py): await moderation check 2024-03-21 16:55:28 -07:00
Krrish Dholakia
c4dad3f34f fix(llm_guard.py): more logging for llm guard.py 2024-03-21 11:22:52 -07:00
Krrish Dholakia
2ce5de903f fix: fix linting issue 2024-03-21 08:05:47 -07:00
Krrish Dholakia
d91f9a9f50 feat(proxy_server.py): enable llm api based prompt injection checks 
run user calls through an llm api to check for prompt injection attacks. This happens in parallel to th
e actual llm call using `async_moderation_hook`
 2024-03-20 22:43:42 -07:00
Krrish Dholakia
3bb0e24cb7 fix(prompt_injection_detection.py): ensure combinations are actual phrases, not just 1-2 words 
reduces misflagging

https://github.com/BerriAI/litellm/issues/2601
 2024-03-20 19:09:38 -07:00