Commit graph

6114 commits

Author SHA1 Message Date
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
01a84837a7 docs(vertex.md): add vertex ai proxy tutorial to docs 2024-01-25 09:11:11 -08:00
Krrish Dholakia
389347250f docs(users.md): add proxy budget to docs 2024-01-25 09:04:23 -08:00
ishaan-jaff
5b151c8566 (ghcr deploy) use platform 2024-01-25 08:43:38 -08:00
Krrish Dholakia
7e06944d80 test(test_dynamodb_logs.py): skip flaky test 2024-01-24 23:18:45 -08:00
Krrish Dholakia
34154dde02 bump: version 1.19.1 → 1.19.2 2024-01-24 22:19:07 -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
Krrish Dholakia
12b2ad9ed1 fix(proxy_server.py): fix handling none value for existing spend object 2024-01-24 20:37:56 -08:00
Krish Dholakia
fe592aa7ec
Merge pull request #1603 from BerriAI/litellm_global_spend_updates
Litellm global spend updates
2024-01-24 20:20:27 -08:00
Krish Dholakia
6501fdb76e
Merge branch 'main' into litellm_global_spend_updates 2024-01-24 20:20:15 -08:00
Krrish Dholakia
30d615f442 build(proxy_server_config.yaml): add proxy budget to default yaml 2024-01-24 20:12:03 -08:00
Krrish Dholakia
b1864c3d11 bump: version 1.19.0 → 1.19.1 2024-01-24 20:10:14 -08:00
Krrish Dholakia
43f139fafd fix(ollama_chat.py): fix default token counting for ollama chat 2024-01-24 20:09:17 -08:00
Krrish Dholakia
05b4d49882 ci(config.yml): add debug logs 2024-01-24 19:54:37 -08:00
ishaan-jaff
3e59a02dfb (test) test /key/gen with max_budget=None 2024-01-24 19:27:53 -08:00
Ishaan Jaff
cf58ecf5c3
Merge pull request #1604 from BerriAI/litellm_view_cache_key_in_spend_logs
[Feat] Add cache_key in SpendLogs Table
2024-01-24 19:13:13 -08:00
ishaan-jaff
6bc715cf85 (test) logging cache_key in spendLogs 2024-01-24 18:54:23 -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
ishaan-jaff
3305dc75ca (docs) add comments on prisma.schema 2024-01-24 17:15:05 -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
Krrish Dholakia
624da17698 test(test_users.py): add testing for global proxy spend tracking 2024-01-24 16:24:50 -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
ba24037baf bump: version 1.18.13 → 1.19.0 2024-01-24 15:30:49 -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
ishaan-jaff
47110180c8 (feat) proxy - add timestamp to debug logs 2024-01-24 15:16:18 -08:00
Krrish Dholakia
e471157d57 test(test_keys.py): add testing to make sure budget resets are working as expected 2024-01-24 15:13:11 -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