Commit graph

435 commits

Author SHA1 Message Date
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
2dfdc8dd69 Revert "Merge pull request #2593 from BerriAI/litellm_reset_budget_fix"
This reverts commit afd363129f, reversing
changes made to c94bc94ad5.
2024-03-19 20:25:41 -07:00
Krrish Dholakia
3a866dd349 bump: version 1.32.5 → 1.32.6 2024-03-19 20:17:50 -07:00
Krrish Dholakia
f6de3a0359 fix: better debug logs 2024-03-19 19:28:26 -07:00
Krrish Dholakia
e0d3b18835 fix(proxy/utils.py): fix reset budget logic
uses fewer clients - prevents read timeouts
2024-03-19 18:02:09 -07:00
Krrish Dholakia
8c91156842 build: build fixes 2024-03-19 16:59:59 -07:00
Krrish Dholakia
c03694ae1e fix(proxy/utils.py): cleanup logging 2024-03-19 09:29:29 -07:00
Krrish Dholakia
8fefe625d9 fix(proxy/utils.py): batch writing updates to db 2024-03-18 16:47:02 -07:00
Krrish Dholakia
077b9c6234 fix(proxy/utils.py): move to batch writing db updates 2024-03-16 22:32:00 -07:00
Krrish Dholakia
1b807fa3f5 fix(proxy_server.py): fix key caching logic 2024-03-13 19:10:24 -07:00
Krrish Dholakia
fd4086d5da fix(proxy_server.py): fix /user/info for non-existent user id 2024-03-12 11:05:41 -07:00
Krrish Dholakia
2addd66393 fix(proxy_server.py): bug fix 2024-03-11 13:54:58 -07:00
Krrish Dholakia
4eb244c3ca 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
fa45c569fd feat: add cost tracking + caching for transcription calls 2024-03-09 15:43:38 -08:00
Krrish Dholakia
4b60bea975 fix(proxy/utils.py): add more logging for prisma client get_data error 2024-03-09 13:06:30 -08:00
ishaan-jaff
8c3ec15856 (fix) improve improve prisma alerting/debug 2024-03-07 15:44:03 -08:00
ishaan-jaff
5217e800c4 (fix) better prisma debug logs 2024-03-07 14:04:02 -08:00
ishaan-jaff
b64e4c3e6f (feat) better debugging when reading prisma 2024-03-07 13:42:54 -08:00
Krrish Dholakia
d1d8adfb11 fix(proxy_server.py): fix sql query 2024-03-06 19:41:12 -08:00
Krrish Dholakia
ca97ea8acd 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
ee468a4e05 (feat) circular ref error on prisa 2024-03-06 12:08:22 -08:00
ishaan-jaff
c17789f170 (fix) circular ref error h 2024-03-06 12:02:44 -08:00
ishaan-jaff
2313f5f90a (feat) handle litellm circular ref error 2024-03-06 10:21:25 -08:00
ishaan-jaff
52e59e050c (fix) use str(e) 2024-03-05 18:57:26 -08:00
ishaan-jaff
00666566c2 (fix) chore 2024-03-05 18:54:04 -08:00
Ishaan Jaff
03fa322b38
Merge branch 'main' into litellm_fixes_proxy_db 2024-03-05 18:51:55 -08:00
ishaan-jaff
735728c4dd (feat) add better debugging when DB read/write fails 2024-03-05 18:16:59 -08:00
Krrish Dholakia
387864662e fix(main.py): trigger new build 2024-03-05 15:50:40 -08:00
ishaan-jaff
b706598415 (v0) fixes 2024-03-05 15:27:06 -08:00
Krrish Dholakia
db0489d603 fix(proxy/utils.py): add linting fix 2024-03-02 21:11:25 -08:00
Krrish Dholakia
ff2e002a92 fix(proxy/utils.py): fix pydantic model dump logic 2024-03-02 21:10:37 -08:00
Krrish Dholakia
a4b4489832 fix(proxy/utils.py): fix model dump pydantic versioning issue 2024-03-02 21:01:36 -08:00
Krrish Dholakia
37ad5efc61 fix(proxy/utils.py): fix resetting budget logic 2024-03-02 20:52:54 -08:00
Krrish Dholakia
ac085a4643 fix(proxy_server.py): actual implementation of slack soft budget alerting 2024-03-02 18:34:18 -08:00
ishaan-jaff
0418ba5fc3 (feat) log api_base in spend logs 2024-03-02 12:02:06 -08:00
ishaan-jaff
0bb45b33fd (feat) send api_base 2024-03-02 11:06:03 -08:00
ishaan-jaff
be2243a4d3 (feat) neatly format slack alerts 2024-03-01 20:45:22 -08:00
Krish Dholakia
5f9cd5a4f6
Merge branch 'main' into litellm_end_user_spend_tracking 2024-02-29 19:31:19 -08:00
ishaan-jaff
56fe8726ab (feat) use view to see monthly spend per key 2024-02-29 19:22:22 -08:00
Krrish Dholakia
7cfcaa9556 fix: return end user top spend 2024-02-29 19:11:50 -08:00
ishaan-jaff
60238f866b Revert "(feat) use view to see monthly spend per key"
This reverts commit 3bae0d5526.
2024-02-29 19:10:36 -08:00
ishaan-jaff
3bae0d5526 (feat) use view to see monthly spend per key 2024-02-29 17:46:39 -08:00
Krrish Dholakia
1788c894f2 fix: enable end user tracking on ui 2024-02-29 16:30:12 -08:00
Krrish Dholakia
c60fa9c84d feat(proxy/utils.py): enable end_user + team id tracking in spend logs
allows separating proxy owner vs. end user in the spen
d logs
2024-02-29 16:04:52 -08:00
Krish Dholakia
d9e272942b
Merge pull request #2257 from BerriAI/litellm_ui_top_models
[UI] View top models by spend
2024-02-29 13:59:40 -08:00
Ishaan Jaff
e044d6332f
Merge pull request #2255 from BerriAI/litellm_admin_ui_user_panel_load_time_high
[FEAT] proxy add pagination on /user/info endpoint (Admin UI does not load all users)
2024-02-29 13:22:00 -08:00
Krrish Dholakia
52ee407f50 fix(usage.tsx): show top models by spend 2024-02-29 13:10:20 -08:00
ishaan-jaff
432ce90a9a (feat) proxy add pagination on /user/info endpoint 2024-02-29 12:30:47 -08:00
Krrish Dholakia
034ca95a94 build(ui): fix admin viewer issue 2024-02-29 09:56:26 -08:00
Krrish Dholakia
1f28867d20 fix(proxy/utils.py): add script for adding MonthlyGlobalSpend view to the db 2024-02-28 13:08:38 -08:00