Commit graph

470 commits

Author SHA1 Message Date
Krrish Dholakia
c441232c62 feat(proxy_server.py): add setup instructions for UI 2024-05-24 08:15:44 -07:00
Ishaan Jaff
56c2d63d1f feat - async_post_call_streaming_hook 2024-05-23 09:30:53 -07:00
Ishaan Jaff
e2fa0cf79f Merge pull request #3790 from BerriAI/litellm_set_team_member_budgets
[Feat] Set Budgets for Users within a Team
2024-05-22 19:44:04 -07:00
Ishaan Jaff
181675c6b7 feat - check team member spend, budget 2024-05-22 18:36:39 -07:00
Ishaan Jaff
5a013fb7be feat - update team+user_id spend 2024-05-22 17:49:54 -07:00
Krrish Dholakia
2bdff9b19e feat(schema.prisma): store model id + model group as part of spend logs
allows precise model metrics
2024-05-22 17:29:44 -07:00
Krrish Dholakia
fda9e7107a build(schema.prisma): add completion_start_time to spend logs
enables time to first token tracking for models
2024-05-22 16:43:08 -07:00
Krish Dholakia
f3a47e4b1a Merge branch 'main' into litellm_webhook_support 2024-05-20 18:41:58 -07:00
Krish Dholakia
db77e41833 Merge pull request #3740 from BerriAI/litellm_return_rejected_response
feat(proxy_server.py): allow admin to return rejected response as string to user
2024-05-20 17:48:21 -07:00
Krrish Dholakia
fd13a830ab fix(slack_alerting.py): cleanup webhook event 2024-05-20 16:55:01 -07:00
Ishaan Jaff
7e6c9274fc Merge branch 'main' into litellm_standardize_slack_exception_msg_format 2024-05-20 16:39:41 -07:00
Ishaan Jaff
6194860da4 fix standardize llm exception alert to msg: value 2024-05-20 16:23:48 -07:00
Krrish Dholakia
c0d5e83570 feat(slack_alerting.py): support webhook for budget alerts
Closes https://github.com/BerriAI/litellm/issues/3743
2024-05-20 15:30:56 -07:00
Ishaan Jaff
175ef7f4f2 fix - only adding alerting callbacks when alerting is on 2024-05-20 14:59:06 -07:00
Krrish Dholakia
8fb8d068fb feat(proxy_server.py): refactor returning rejected message, to work with error logging
log the rejected request as a failed call to langfuse/slack alerting
2024-05-20 11:14:36 -07:00
Krrish Dholakia
45fedb83c6 feat(proxy_server.py): allow admin to return rejected response as string to user
Closes https://github.com/BerriAI/litellm/issues/3671
2024-05-20 10:30:23 -07:00
Ishaan Jaff
70194f7ba2 fix - allow users to opt into specific alert types 2024-05-16 16:52:44 -07:00
Krish Dholakia
4c8b620352 Merge pull request #3685 from BerriAI/litellm_lago_integration
feat(lago.py): Enable Usage-based billing with lago
2024-05-16 13:09:48 -07:00
Krrish Dholakia
d167a9ea99 feat(lago.py): adding support for usage-based billing with lago
Closes https://github.com/BerriAI/litellm/issues/3639
2024-05-16 10:54:18 -07:00
Krish Dholakia
07a1cf39e8 Merge branch 'main' into litellm_end_user_cost_tracking 2024-05-15 22:27:04 -07:00
Ishaan Jaff
d257518e47 fix deep copy logic in during_call_hook 2024-05-15 17:34:54 -07:00
Ishaan Jaff
38a539baf4 show debug info on slack alerts 2024-05-15 13:23:44 -07:00
Krrish Dholakia
9945387d7a feat(proxy_server.py): new /end_user/info endpoint
get spend for a specific end-user
2024-05-15 09:50:52 -07:00
Krish Dholakia
64ca2fde53 Merge branch 'main' into litellm_region_based_routing 2024-05-08 22:19:51 -07:00
Krrish Dholakia
7c99808529 feat(proxy_server.py): add CRUD endpoints for 'end_user' management
allow admin to specify region + default models for end users
2024-05-08 18:50:36 -07:00
Krrish Dholakia
5f93cae3ff feat(proxy_server.py): return litellm version in response headers 2024-05-08 16:00:08 -07:00
Krrish Dholakia
e5c57cdddb feat(slack_alerting.py): reintegrate langfuse trace url for slack alerts
this ensures langfuse trace url returned in llm api exception err
2024-05-07 12:58:49 -07:00
Krrish Dholakia
2170e1723d feat(proxy_server.py): schedule slack daily report if enabled
if user enabled daily_reports, send them a slack report every 12 hours
2024-05-06 18:25:48 -07:00
Krrish Dholakia
0c1fc34e9f feat(slack_alerting.py): support sending daily reports on deployments
allow admin to easily know slow + failing deployments

Closes  https://github.com/BerriAI/litellm/issues/3483
2024-05-06 17:18:42 -07:00
Krrish Dholakia
4a22948ce4 fix(proxy/utils.py): fix slack alerting to only raise alerts for llm api exceptions
don't spam for bad user requests. Closes https://github.com/BerriAI/litellm/issues/3395
2024-05-02 17:18:21 -07:00
Krrish Dholakia
c1ffa7d409 fix(proxy/utils.py): fix retry logic for generic data request 2024-05-02 14:50:50 -07:00
Krrish Dholakia
e7b3ac8e06 feat(openmeter.py): add support for user billing
open-meter supports user based billing. Closes https://github.com/BerriAI/litellm/issues/1268
2024-05-01 17:23:48 -07:00
Krrish Dholakia
0b2c3f78d4 fix(proxy/utils.py): emit number of spend transactions for keys being written to db in a batch 2024-05-01 08:25:04 -07:00
Krrish Dholakia
462724feef fix(proxy/utils.py): log rejected proxy requests to langfuse 2024-04-25 19:26:27 -07:00
Ishaan Jaff
2190b039fd pass alert type on alerting handle 2024-04-25 13:05:34 -07:00
Ishaan Jaff
c5a0b3a8d4 fix - refactor slack alerting 2024-04-23 18:34:11 -07:00
Ishaan Jaff
a3109db4e1 fix langfuse project id 2024-04-23 11:37:17 -07:00
Ishaan Jaff
d076aed9d0 fix - dont send alert on fail request 2024-04-22 16:07:58 -07:00
Ishaan Jaff
8fb9c8d833 ui - find all teams 2024-04-22 14:15:09 -07:00
Ishaan Jaff
aa365c5c4a feat - show langfuse trace in alerts 2024-04-22 08:51:46 -07:00
Ishaan Jaff
d4c9439cc0 fix - slack alerting show input in the api_base 2024-04-20 13:16:47 -07:00
Ishaan Jaff
828645137c feat - log team_alias to langfuse 2024-04-19 10:29:42 -07:00
Ishaan Jaff
532e252559 fix - show api_base in hanging requests 2024-04-18 21:01:26 -07:00
Ishaan Jaff
ecc770be00 fix - show api base on hanging requests 2024-04-18 20:57:22 -07:00
Ishaan Jaff
977b030dd9 ui - show all alert types when getting all callbacks 2024-04-18 20:08:13 -07:00
Krish Dholakia
741a18a040 Merge pull request #3144 from BerriAI/litellm_prometheus_latency_tracking
feat(prometheus_services.py): emit proxy latency for successful llm api requests
2024-04-18 19:10:58 -07:00
Ishaan Jaff
27333d17e2 fix order by spend 2024-04-18 17:33:38 -07:00
Ishaan Jaff
03b4652af1 fix return key aliases on /user/info 2024-04-18 17:16:52 -07:00
Krrish Dholakia
51cc8dd95b fix(proxy/utils.py): add prometheus failed db request tracking 2024-04-18 16:30:29 -07:00
Krrish Dholakia
cdfd873713 fix(proxy/utils.py): add call type and duration to proxy_logging failure calls
this is for tracking failed db requests on prometheus
2024-04-18 16:24:36 -07:00