Ishaan Jaff
2b467a847a
fix latency tracking tool tip
2024-05-01 16:47:30 -07:00
Ishaan Jaff
94b98f5c4e
clean up model latency metrics
2024-05-01 08:27:01 -07:00
Ishaan Jaff
b9238a00af
ui - show tokens / sec
2024-04-30 22:44:28 -07:00
Ishaan Jaff
0c464f7f61
fix - viewing model metrics
2024-04-30 18:26:14 -07:00
Ishaan Jaff
f2849d0641
fix - track litellm_model_name in LiteLLM_ErrorLogs
2024-04-30 17:31:40 -07:00
Ishaan Jaff
8a1a043801
backend - show model latency per token
2024-04-30 17:23:36 -07:00
Ishaan Jaff
a2a8fef8f4
fix passing starttime and endtime to model/exceptions
2024-04-30 16:53:53 -07:00
Ishaan Jaff
26a5d85869
fix - backend return exceptions
2024-04-30 15:41:16 -07:00
Marc Abramowitz
dd166680d1
Move chat_completions before completions
...
so that the `chat_completions` route is defined before the `completions` route.
This is necessary because the `chat_completions` route is more
specific than the `completions` route, and the order of route definitions
matters in FastAPI.
Without this, doing a request to
`/openai/deployments/{model_in_url}/chat/completions` might trigger
`completions` being called (with `model` set to `{model_in_url}/chat` instead of
`chat_completions` getting called, which is the correct function.
Fixes: GH-3372
2024-04-30 15:07:10 -07:00
Ishaan Jaff
1f4f1c6f70
stash /model/metrics/exceptions endpoints
2024-04-30 14:19:23 -07:00
Ishaan Jaff
4b8fda4ac4
log startTime and EndTime for exceptions
2024-04-30 13:34:14 -07:00
Ishaan Jaff
3aad034a8b
feat log request kwargs in error logs
2024-04-30 13:28:26 -07:00
Ishaan Jaff
ad5fddef15
fix log model_group
2024-04-30 13:11:09 -07:00
Ishaan Jaff
ee2a2ce559
fix - log api_base in errors
2024-04-30 13:02:42 -07:00
Ishaan Jaff
06804bc70a
fix - working exception writing
2024-04-30 12:48:17 -07:00
Krrish Dholakia
7b617e666d
fix(proxy_server.py): return more detailed auth error message.
2024-04-29 07:24:19 -07:00
Krrish Dholakia
5583197d63
fix(proxy_server.py): fix setting offset-aware datetime
2024-04-25 21:18:32 -07:00
Krrish Dholakia
885de2e3c6
fix(proxy/utils.py): log rejected proxy requests to langfuse
2024-04-25 19:26:27 -07:00
Ishaan Jaff
96921864dc
fixes for testing alerting
2024-04-25 16:33:55 -07:00
Ishaan Jaff
61f48aba6f
backend - update slack alert_to_webhook_url_map
2024-04-25 13:47:52 -07:00
Ishaan Jaff
1d5e70f7a0
pass alert type on alerting handle
2024-04-25 13:05:34 -07:00
Krrish Dholakia
b8f862bb76
fix(proxy_server.py): fix update router
2024-04-24 23:01:21 -07:00
Krrish Dholakia
fe188f3cc1
fix(proxy_server.py): fix updating non-router settings for proxy config
2024-04-24 22:50:04 -07:00
Krrish Dholakia
5650e8ea44
feat(router.py): support mock testing fallbacks flag
...
allow user to test if fallbacks work as expected with a `mock_testing_fallbacks = True` flag set during a call
2024-04-24 20:13:10 -07:00
Krrish Dholakia
f54510b6ee
fix(proxy_server.py): fix /config/update/
...
allows updating router config via UI and having the change be propogated across all proxy instances by persisting config changes to the db
2024-04-24 16:42:42 -07:00
Ishaan Jaff
2ac3885a50
Merge pull request #3277 from BerriAI/litellm_update_deployments
...
[UI] V0 - Edit Model tpm, rpm, api_base
2024-04-24 14:03:00 -07:00
Ishaan Jaff
efbf85a5ad
/model/update endpoint
2024-04-24 10:39:20 -07:00
Krrish Dholakia
26e9ae38ce
fix(proxy_server.py): add new flag for disable sharing master key on ui
2024-04-24 10:06:01 -07:00
Ishaan Jaff
9017d9bb81
backend allow filtering by model_group
2024-04-23 22:03:20 -07:00
Ishaan Jaff
ac6809e9df
ui - filter by time and deployments
2024-04-23 20:42:15 -07:00
Ishaan Jaff
9d18e4770d
fix using slack alerting through admin ui
2024-04-23 19:05:50 -07:00
Krrish Dholakia
9d2726c2ac
fix(proxy_server.py): handle router being initialized without a model list
2024-04-23 10:52:28 -07:00
Ishaan Jaff
fdf432798e
Merge pull request #3228 from BerriAI/litellm_ui_polish
...
[Fix] Non-Admin SSO Login
2024-04-22 18:15:10 -07:00
Ishaan Jaff
9250f61a4c
fix - sso login for non admins
2024-04-22 17:57:47 -07:00
Ishaan Jaff
8874eaa0b3
fix - track litellm_status=fail
2024-04-22 16:11:04 -07:00
Ishaan Jaff
50bbd188fb
ui - show all teams on ui
2024-04-22 14:15:50 -07:00
Ishaan Jaff
877c4e27f4
Merge pull request #3212 from BerriAI/ui_increase_default_session_time
...
UI - increase default session time to 2 hours
2024-04-22 13:46:18 -07:00
Ishaan Jaff
bb065f64c6
increase ui default session time to 2 hours
2024-04-22 10:00:53 -07:00
Ishaan Jaff
f54982a560
fix - round spend to 2 decimals
2024-04-22 09:17:40 -07:00
Ishaan Jaff
f89f8a4157
Merge pull request #3184 from BerriAI/litellm_ui_non_admins_flow
...
[UI] - non admin flow - only Create + Test Key available
2024-04-20 12:40:43 -07:00
Ishaan Jaff
07a10247db
fix - security fix
2024-04-20 12:10:08 -07:00
Ishaan Jaff
5d39865362
fix - audio_transcriptions security fix
2024-04-20 11:58:15 -07:00
Ishaan Jaff
fd282ea932
fix testing fixes
2024-04-20 11:48:41 -07:00
Ishaan Jaff
7ebf2ca4d9
(ci/cd) testing with team_id and /user/new
2024-04-20 11:09:34 -07:00
Ishaan Jaff
00a07a99cd
fix - backend logic for non admin flow
2024-04-19 17:36:29 -07:00
Ishaan Jaff
423121ff7d
feat - track team_alias is metadata for /chat, /embeddings
2024-04-19 10:52:54 -07:00
Ishaan Jaff
554c83fdaf
ui - show all alert types when getting all callbacks
2024-04-18 20:08:13 -07:00
Ishaan Jaff
eb04a929e6
Merge pull request #3112 from BerriAI/litellm_add_alert_types
...
[Feat] Allow user to select slack alert types to Opt In to
2024-04-18 16:21:33 -07:00
Ishaan Jaff
8958bbeac9
Merge pull request #3142 from BerriAI/litellm_slack_alerting_show_model_passed
...
[Fix] Show `model` passed on `"400: {'error': 'Invalid model name passed in mode` errors 👻
2024-04-18 16:18:17 -07:00
Ishaan Jaff
b308f8c079
fix - show model passed in on Invalid model name passed in error
2024-04-18 15:43:30 -07:00
