ishaan-jaff
|
7a2a7e047f
|
(feat) slack alerting budgets
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
55115a75b0
|
(feat) alerts proxy budgets
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
565531fe9e
|
v0 basic structure
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
e56721d6c3
|
(feat) view spend/logs by user_id, view spend/user by user
|
2024-01-25 16:12:28 -08:00 |
|
Krrish Dholakia
|
09ec6d6458
|
fix(utils.py): fix sagemaker async logging for sync streaming
https://github.com/BerriAI/litellm/issues/1592
|
2024-01-25 12:49:45 -08:00 |
|
Ishaan Jaff
|
06a5dbfb5e
|
Merge pull request #1615 from BerriAI/litellm_alerts_budget_tracking
[Feat] Alerts for Proxy Budgets
|
2024-01-25 12:00:18 -08:00 |
|
ishaan-jaff
|
ca12e70369
|
(fix) do nothing if alerting is not switched on
|
2024-01-25 11:58:55 -08:00 |
|
ishaan-jaff
|
e80d32dcdd
|
(fix) alerting debug statements
|
2024-01-25 11:56:52 -08:00 |
|
ishaan-jaff
|
6dc9be4d43
|
(docs) config.yaml
|
2024-01-25 11:41:35 -08:00 |
|
ishaan-jaff
|
6fb3f8f239
|
(docs) track max_budget on proxy config.yaml
|
2024-01-25 11:40:56 -08:00 |
|
ishaan-jaff
|
b3f91844cb
|
(fix) better alert message on budgets
|
2024-01-25 11:40:20 -08:00 |
|
ishaan-jaff
|
450b0a0ad1
|
(fix) raise correct error when proxy crossed budget
|
2024-01-25 11:39:57 -08:00 |
|
ishaan-jaff
|
126b87e3fa
|
(fix) raise exception budget_duration is set and max_budget is Not
|
2024-01-25 11:32:05 -08:00 |
|
ishaan-jaff
|
3ef2afb0e4
|
(feat) slack alerting budgets
|
2024-01-25 11:18:06 -08:00 |
|
ishaan-jaff
|
1ab713c76c
|
(feat) alerts proxy budgets
|
2024-01-25 10:01:32 -08:00 |
|
ishaan-jaff
|
d328a4bad0
|
v0 basic structure
|
2024-01-25 09:58:43 -08:00 |
|
Krrish Dholakia
|
39d5407e67
|
fix(proxy_server.py): don't set tpm/rpm limits unless set
https://github.com/BerriAI/litellm/issues/1594
|
2024-01-25 09:53:10 -08:00 |
|
Krrish Dholakia
|
81846ffdec
|
fix(proxy/utils.py): handle item not existing during batch updates
|
2024-01-24 21:49:47 -08:00 |
|
Krrish Dholakia
|
0752048b81
|
fix(dynamo_db.py): fix update bug
|
2024-01-24 21:29:56 -08:00 |
|
Krrish Dholakia
|
8e1157fc92
|
test(test_keys.py): reset proxy spend
|
2024-01-24 21:08:09 -08:00 |
|
Krrish Dholakia
|
34c4532e7e
|
fix(proxy_server.py): fix handling none value for existing spend object pt.2
|
2024-01-24 20:39:00 -08:00 |
|
Krish Dholakia
|
6501fdb76e
|
Merge branch 'main' into litellm_global_spend_updates
|
2024-01-24 20:20:15 -08:00 |
|
ishaan-jaff
|
2f3765a03f
|
(fix) log cache hits on SpendLogs table
|
2024-01-24 18:51:39 -08:00 |
|
ishaan-jaff
|
bf851ef19a
|
(fix) use litellm.cache for getting key
|
2024-01-24 18:34:22 -08:00 |
|
ishaan-jaff
|
2130a61b6e
|
(feat) add cache_key in spend_log
|
2024-01-24 17:56:00 -08:00 |
|
Krrish Dholakia
|
f148094d18
|
test(test_key_generate_prisma.py): add unit testing for global proxy budget
|
2024-01-24 17:43:01 -08:00 |
|
ishaan-jaff
|
d694993703
|
(fix) bug from bb7705b494
|
2024-01-24 17:34:17 -08:00 |
|
Krrish Dholakia
|
30a8071bf1
|
fix(proxy_server.py): enforce budget limit if global proxy limit reached
|
2024-01-24 17:11:40 -08:00 |
|
Ishaan Jaff
|
45ca7343d0
|
Merge pull request #1601 from BerriAI/litellm_improve_slack_alertign
[Feat] Proxy - Improve Slack Alerting
|
2024-01-24 16:43:23 -08:00 |
|
ishaan-jaff
|
9aae60f162
|
(FIX) improve slack alerting messages
|
2024-01-24 16:07:46 -08:00 |
|
Krrish Dholakia
|
574208f005
|
fix(proxy_server.py): track cost for global proxy
|
2024-01-24 16:06:10 -08:00 |
|
ishaan-jaff
|
b993c62144
|
(fix) only alert users when requests are hanging
|
2024-01-24 15:58:07 -08:00 |
|
Krrish Dholakia
|
bb7705b494
|
test(test_users.py): test budgets with resets
|
2024-01-24 15:30:30 -08:00 |
|
ishaan-jaff
|
6c13776701
|
(fix) alerting - show timestamps in alert
|
2024-01-24 15:25:40 -08:00 |
|
ishaan-jaff
|
8f4e256531
|
(feat) add request_info to slack alerts
|
2024-01-24 15:17:33 -08:00 |
|
Krrish Dholakia
|
f9d159797a
|
fix(proxy_server.py): handle view spend logs for api key none object
|
2024-01-24 14:57:21 -08:00 |
|
Krish Dholakia
|
3e7ed4082a
|
Merge pull request #1600 from BerriAI/litellm_global_budget
feat(proxy_server.py): support global budget and resets
|
2024-01-24 14:55:36 -08:00 |
|
ishaan-jaff
|
087bd5e267
|
(feat) slack alerting - log request/response
|
2024-01-24 14:55:21 -08:00 |
|
Krish Dholakia
|
ed77f2d682
|
Merge pull request #1590 from BerriAI/litellm_spend_logs_by_key
feat(proxy_server.py): enable returning spend logs by api key
|
2024-01-24 14:45:25 -08:00 |
|
Krrish Dholakia
|
159e54d8be
|
feat(proxy_server.py): support global budget and resets
|
2024-01-24 14:27:13 -08:00 |
|
ishaan-jaff
|
fdcb588511
|
(fix) stop logging messages, response in SpendLogs
|
2024-01-24 13:16:34 -08:00 |
|
ishaan-jaff
|
63f18e7163
|
(fix) use get_attr for valid_token
|
2024-01-24 13:01:37 -08:00 |
|
ishaan-jaff
|
25332b4a60
|
(fix) LiteLLM_VerificationToken - use NULL default for max_budget
|
2024-01-24 12:59:50 -08:00 |
|
Ishaan Jaff
|
f76620b1d1
|
Merge branch 'main' into litellm_spend_per_user
|
2024-01-24 12:24:15 -08:00 |
|
ishaan-jaff
|
2692afca75
|
(feat) /spend/users endpoint
|
2024-01-24 11:34:28 -08:00 |
|
ishaan-jaff
|
a842e6520c
|
(test) setting model in SpendTable logs
|
2024-01-24 11:09:20 -08:00 |
|
Krrish Dholakia
|
dd05c6e6e3
|
feat(proxy_server.py): enable returning spend logs by api key
https://github.com/BerriAI/litellm/issues/1582
|
2024-01-24 10:48:23 -08:00 |
|
ishaan-jaff
|
d3848b6e6c
|
(v0)
|
2024-01-24 10:13:57 -08:00 |
|
ishaan-jaff
|
2d26875eb0
|
(fix) together_ai use sync generator
|
2024-01-23 20:07:26 -08:00 |
|
Ishaan Jaff
|
a0cd4e78fc
|
Merge branch 'main' into litellm_map_openai_auth_errors
|
2024-01-23 18:31:48 -08:00 |
|