5b51acc773
fix type hints on main
2024-05-13 20:21:23 -07:00
fa4dcbd37c
ui - round up spend per tag
2024-05-13 17:31:29 -07:00
51961387a2
ui - filter tags by starttime and endtime
2024-05-13 17:15:25 -07:00
4a3b084961
feat(bedrock_httpx.py): moves to using httpx client for bedrock cohere calls
2024-05-11 13:43:08 -07:00
6575143460
feat(proxy_server.py): return litellm version in response headers
2024-05-08 16:00:08 -07:00
b6cd200676
fix(llm_guard.py): enable request-specific llm guard flag
2024-04-08 21:15:33 -07:00
73fce02392
ui - view spend per tag
2024-04-04 17:18:01 -07:00
ac5507bd84
ui show spend per tag
2024-04-04 16:57:45 -07:00
da20aecb16
(fix) check size of data to predict
2024-03-30 11:34:20 -07:00
1046a63521
test(test_llm_guard.py): unit testing for key-level llm guard enabling
2024-03-26 17:55:53 -07:00
6d418a2920
fix(llm_guard.py): working llm-guard 'key-specific' mode
2024-03-26 17:47:20 -07:00
e10eb8f6fe
feat(llm_guard.py): enable key-specific llm guard check
2024-03-26 17:21:51 -07:00
5d121a9f3c
(fix) stop using f strings with logger
2024-03-25 10:47:18 -07:00
b5457beba6
fix(llm_guard.py): await moderation check
2024-03-21 16:55:28 -07:00
c4dad3f34f
fix(llm_guard.py): more logging for llm guard.py
2024-03-21 11:22:52 -07:00
2ce5de903f
fix: fix linting issue
2024-03-21 08:05:47 -07:00
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
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
dd151869a3
fix(blocked_user_list.py): check if end user blocked in db
2024-03-16 13:03:52 -07:00
fa1676b253
(fix) error cli users see when importing enterprise folder
2024-03-15 08:10:45 -07:00
3e66b50602
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
b3493269b3
fix(proxy_server.py): support checking openai user param
2024-03-13 12:00:27 -07:00
234cdbbfef
feat(prompt_injection_detection.py): support simple heuristic similarity check for prompt injection attacks
2024-03-13 10:32:21 -07:00
323f15aa2f
(fix) litellm cloud formation stack
2024-03-07 18:06:59 -08:00
a491704201
(feat) show monthly predicted spend
2024-03-01 09:54:12 -08:00
03a0b274f7
(feat) predict spend
2024-03-01 09:28:22 -08:00
47c5b94c50
(feat) /predict/spend endpoint
2024-03-01 08:20:35 -08:00
3bb861ae02
(feat) predict spend
2024-03-01 07:54:09 -08:00
9ad8b7c8fb
(chore) move clickhouse to correct directory
2024-02-27 19:41:01 -08:00
30f4033bbc
(feat) enable viewing /spend/logs for clickhouse
2024-02-26 18:05:21 -08:00
dc5942f6aa
(feat) use clickhouse for viewing data on Admin UI
2024-02-26 17:53:21 -08:00
acae98fd50
feat(proxy_server.py): enable admin to set banned keywords on proxy
2024-02-22 18:30:42 -08:00
028f455ad0
feat(proxy_server.py): add support for blocked user lists (enterprise-only)
2024-02-22 17:51:31 -08:00
0e62c8bd27
Update README.md
2024-02-21 22:11:39 -08:00
d07846646c
(ui) fix build command
2024-02-21 21:02:46 -08:00
49847347d0
fix(llm_guard.py): add streaming hook for moderation calls
2024-02-20 20:31:32 -08:00
fde478f70b
docs(enterprise.md): add llm guard to docs
2024-02-19 21:05:01 -08:00
14513af2e2
feat(llm_guard.py): support llm guard for content moderation
...
https://github.com/BerriAI/litellm/issues/2056
2024-02-19 20:51:25 -08:00
7348956bf2
docs(enterprise.md): add google text moderations to the docs
2024-02-19 14:17:52 -08:00
52e425c7ac
fix(llama_guard.py): fix merge
2024-02-17 23:38:53 -08:00
b41cdf598b
Merge branch 'main' into litellm_google_text_moderation
2024-02-17 22:10:26 -08:00
038ba426ab
Merge branch 'main' into litellm_llamaguard_custom_categories
2024-02-17 21:36:40 -08:00
ddf0911c46
feat(google_text_moderation.py): allow user to use google text moderation for content mod on proxy
2024-02-17 18:36:29 -08:00
73acdf3736
refactor: rename enterprise specific hooks and callbacks to be more precise
2024-02-17 17:52:45 -08:00
074d93cc97
feat(llama_guard.py): allow user to define custom unsafe content categories
2024-02-17 17:42:47 -08:00
a3d197fa1f
Update README.md
2024-02-17 16:46:11 -08:00
2de5a60993
Update README.md
2024-02-17 16:45:46 -08:00
2a4a6995ac
feat(llama_guard.py): add llama guard support for content moderation + new async_moderation_hook endpoint
2024-02-16 18:45:25 -08:00
566c505f5f
Update README.md
2024-02-16 16:26:39 -08:00
a137680895
Update README.md
2024-02-16 14:17:24 -08:00
Ishaan Jaff