phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
11196 commits 1603 branches 645 tags 320 MiB
Commit graph

297 commits

Author SHA1 Message Date
Krish Dholakia
8ad979cdfe
Merge branch 'main' into litellm_region_based_routing 2024-05-08 22:19:51 -07:00
Krrish Dholakia
db666b01e5 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
6575143460 feat(proxy_server.py): return litellm version in response headers 2024-05-08 16:00:08 -07:00
Krrish Dholakia
872470ff1f 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
6b9b4f05ba 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
718f423d7d 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
fdc4fdb91a 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
acda064be6 fix(proxy/utils.py): fix retry logic for generic data request 2024-05-02 14:50:50 -07:00
Krrish Dholakia
2a9651b3ca 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
d0f9f8c0ed 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
885de2e3c6 fix(proxy/utils.py): log rejected proxy requests to langfuse 2024-04-25 19:26:27 -07:00
Ishaan Jaff
1d5e70f7a0 pass alert type on alerting handle 2024-04-25 13:05:34 -07:00
Ishaan Jaff
31979f83d2 fix - refactor slack alerting 2024-04-23 18:34:11 -07:00
Ishaan Jaff
5118c96b4d fix langfuse project id 2024-04-23 11:37:17 -07:00
Ishaan Jaff
517f577292 fix - dont send alert on fail request 2024-04-22 16:07:58 -07:00
Ishaan Jaff
cd3b2a21c1 ui - find all teams 2024-04-22 14:15:09 -07:00
Ishaan Jaff
094583f18e feat - show langfuse trace in alerts 2024-04-22 08:51:46 -07:00
Ishaan Jaff
ddc71d766a fix - slack alerting show input in the api_base 2024-04-20 13:16:47 -07:00
Ishaan Jaff
6d92b13c22 feat - log team_alias to langfuse 2024-04-19 10:29:42 -07:00
Ishaan Jaff
6f948cd559 fix - show api_base in hanging requests 2024-04-18 21:01:26 -07:00
Ishaan Jaff
f04604910b fix - show api base on hanging requests 2024-04-18 20:57:22 -07:00
Ishaan Jaff
554c83fdaf ui - show all alert types when getting all callbacks 2024-04-18 20:08:13 -07:00
Krish Dholakia
77a353d484
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
d9091dcf97 fix order by spend 2024-04-18 17:33:38 -07:00
Ishaan Jaff
b669e2987b fix return key aliases on /user/info 2024-04-18 17:16:52 -07:00
Krrish Dholakia
919a2876f1 fix(proxy/utils.py): add prometheus failed db request tracking 2024-04-18 16:30:29 -07:00
Krrish Dholakia
d61250109e 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
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
Krrish Dholakia
0f95a824c4 feat(prometheus_services.py): emit proxy latency for successful llm api requests 
uses prometheus histogram for this
 2024-04-18 16:04:35 -07:00
Ishaan Jaff
e20b05d6dd fix trim messages to first 100 chars 2024-04-18 15:21:31 -07:00
Ishaan Jaff
1cda0db2ca fix - test alerting 2024-04-18 11:40:40 -07:00
Ishaan Jaff
beeee01199 feat return alert types on /config/get/callback 2024-04-17 21:02:10 -07:00
Ishaan Jaff
9a5fd07f16 fix - user based alerting 2024-04-17 20:35:29 -07:00
Ishaan Jaff
52d7fc22bb v0 add types of alerts to slack alerting 2024-04-17 18:16:19 -07:00
Ishaan Jaff
12a01ba096 litellm_add_proxy_base_url in slack alerts 2024-04-17 17:42:28 -07:00
Krrish Dholakia
f4b595ce71 fix(utils.py): return vertex api base for request hanging alerts 2024-04-16 17:53:28 -07:00
Krrish Dholakia
f4c7f4f901 fix(proxy_server.py): support tracking org spend 
currently works when org set for jwt auth
 2024-04-11 23:01:21 -07:00
Krrish Dholakia
470b7b64c9 fix(proxy/utils.py): fix error message 2024-04-08 20:47:13 -07:00
Krrish Dholakia
6c1444bfaa fix(proxy_server.py): allow mapping a user to an org 2024-04-08 20:45:11 -07:00
Krrish Dholakia
6110d32b1c feat(proxy/utils.py): return api base for request hanging alerts 2024-04-06 15:58:53 -07:00
Krrish Dholakia
e3c2bdef4d feat(ui): add models via ui 
adds ability to add models via ui to the proxy. also fixes additional bugs around new /model/new endpoint
 2024-04-04 18:56:20 -07:00
Krrish Dholakia
f536fb13e6 fix(proxy_server.py): persist models added via /model/new to db 
allows models to be used across instances

https://github.com/BerriAI/litellm/issues/2319 , https://github.com/BerriAI/litellm/issues/2329
 2024-04-03 20:16:41 -07:00
Krrish Dholakia
d7601a4844 perf(proxy_server.py): batch write spend logs 
reduces prisma client errors, by batch writing spend logs - max 1k logs at a time
 2024-04-02 18:46:55 -07:00
Krrish Dholakia
6467dd4e11 fix(tpm_rpm_limiter.py): fix cache init logic 2024-04-01 18:01:38 -07:00
Krrish Dholakia
9c0aecf9b8 fix(proxy/utils.py): support redis caching for alerting 2024-04-01 16:13:59 -07:00
Krrish Dholakia
3b8e7241b4 fix(proxy/utils.py): uncomment max parallel request limit check 2024-03-30 20:51:59 -07:00
Krrish Dholakia
d9ff13b624 fix(utils.py): set redis_usage_cache to none by default 2024-03-30 20:10:56 -07:00
Krrish Dholakia
f58fefd589 fix(tpm_rpm_limiter.py): enable redis caching for tpm/rpm checks on keys/user/teams 
allows tpm/rpm checks to work across instances

https://github.com/BerriAI/litellm/issues/2730
 2024-03-30 20:01:36 -07:00
Krrish Dholakia
5280fc809f fix(proxy_server.py): enforce end user budgets with 'litellm.max_end_user_budget' param 2024-03-29 17:14:40 -07:00
Krrish Dholakia
c15ba368e7 fix(proxy_server.py): enable spend tracking for team-based jwt auth 2024-03-28 20:16:22 -07:00