Commit graph

1750 commits

Author SHA1 Message Date
Krrish Dholakia
a137f000b2 feat(proxy_server.py): save abbreviated key name if allow_user_auth enabled 2024-01-26 15:31:37 -08:00
ishaan-jaff
25757b3353 (fix) proxy - always use hashed_token as /key cache key 2024-01-26 14:30:26 -08:00
Krrish Dholakia
d89afaac7f refactor(proxy_server.py): fix docstring for /key/delete to show hashed tokens as well 2024-01-26 13:33:17 -08:00
Krish Dholakia
2abb430180 Merge pull request #1618 from BerriAI/litellm_sagemaker_cost_tracking_fixes
fix(utils.py): fix sagemaker cost tracking for streaming
2024-01-25 19:01:57 -08:00
ishaan-jaff
90960d2914 (fix) raise correct error when proxy crossed budget 2024-01-25 16:40:23 -08:00
ishaan-jaff
613faff049 (fix) raise exception budget_duration is set and max_budget is Not 2024-01-25 16:40:23 -08:00
ishaan-jaff
1d36b8da31 v0 basic structure 2024-01-25 16:40:23 -08:00
ishaan-jaff
756e0ff55b (feat) view spend/logs by user_id, view spend/user by user 2024-01-25 16:12:28 -08:00
Krrish Dholakia
402235dc5d 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
cd565051f9 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
3e878643c7 (fix) raise correct error when proxy crossed budget 2024-01-25 11:39:57 -08:00
ishaan-jaff
117373ecbe (fix) raise exception budget_duration is set and max_budget is Not 2024-01-25 11:32:05 -08:00
ishaan-jaff
1ff3f64ee6 v0 basic structure 2024-01-25 09:58:43 -08:00
Krrish Dholakia
d3324fa2f2 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
e57f40ea26 fix(dynamo_db.py): fix update bug 2024-01-24 21:29:56 -08:00
Krrish Dholakia
2f25a8db8d test(test_keys.py): reset proxy spend 2024-01-24 21:08:09 -08:00
Krrish Dholakia
5cd9402b76 fix(proxy_server.py): fix handling none value for existing spend object pt.2 2024-01-24 20:39:00 -08:00
Krish Dholakia
f1d309d700 Merge branch 'main' into litellm_global_spend_updates 2024-01-24 20:20:15 -08:00
ishaan-jaff
40a8c1af2d (fix) log cache hits on SpendLogs table 2024-01-24 18:51:39 -08:00
ishaan-jaff
52fb8c5b40 (fix) use litellm.cache for getting key 2024-01-24 18:34:22 -08:00
Krrish Dholakia
7a8f10c1c0 test(test_key_generate_prisma.py): add unit testing for global proxy budget 2024-01-24 17:43:01 -08:00
Krrish Dholakia
8518e2e2d1 fix(proxy_server.py): enforce budget limit if global proxy limit reached 2024-01-24 17:11:40 -08:00
Ishaan Jaff
6dac4ab8aa 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
d536374be0 fix(proxy_server.py): track cost for global proxy 2024-01-24 16:06:10 -08:00
ishaan-jaff
2686d1f087 (fix) only alert users when requests are hanging 2024-01-24 15:58:07 -08:00
Krrish Dholakia
222ddfbd8e fix(proxy_server.py): handle view spend logs for api key none object 2024-01-24 14:57:21 -08:00
Krish Dholakia
65c971e60e 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
Krish Dholakia
e92cf9e6a3 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
f21e003f5b feat(proxy_server.py): support global budget and resets 2024-01-24 14:27:13 -08:00
ishaan-jaff
c493b5f07c (fix) use get_attr for valid_token 2024-01-24 13:01:37 -08:00
ishaan-jaff
b1c91a987a (feat) /spend/users endpoint 2024-01-24 11:34:28 -08:00
Krrish Dholakia
55344e836d 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
b9e3403e8e (v0) 2024-01-24 10:13:57 -08:00
ishaan-jaff
9b3628bc4c (fix) together_ai use sync generator 2024-01-23 20:07:26 -08:00
Ishaan Jaff
85232f9b6e Merge branch 'main' into litellm_map_openai_auth_errors 2024-01-23 18:31:48 -08:00
Krish Dholakia
89e420b243 Merge branch 'main' into litellm_reset_key_budget 2024-01-23 18:10:32 -08:00
ishaan-jaff
29aa7a6c0f (feat) all endpoints raise OpenAI compatible exceptions 2024-01-23 17:32:47 -08:00
Krrish Dholakia
3cf1623727 refactor(proxy/utils.py): fix linting issue 2024-01-23 17:22:22 -08:00
Krish Dholakia
2ba8863f75 Merge pull request #1574 from BerriAI/litellm_fix_streaming_spend_tracking
[WIP] fix(utils.py): fix proxy streaming spend tracking
2024-01-23 17:07:40 -08:00
ishaan-jaff
9ae3d8c243 (feat) /spend/logs 2024-01-23 16:57:51 -08:00
ishaan-jaff
97fd419cb5 (fix) add doc string for /spend/keys 2024-01-23 16:27:25 -08:00
Krrish Dholakia
a5e53271d3 fix(utils.py): fix double hashing issue on spend logs, streaming usage metadata logging iss
ue for spend logs
2024-01-23 16:14:01 -08:00
Krrish Dholakia
344e232549 fix(utils.py): fix proxy streaming spend tracking 2024-01-23 15:59:03 -08:00
ishaan-jaff
9c85d05d24 (feat) add /spend/keys endpoint 2024-01-23 15:10:10 -08:00
Krrish Dholakia
88486a3123 fix(utils.py): fix streaming cost tracking 2024-01-23 14:39:45 -08:00
Krrish Dholakia
e6f05e858b feat(proxy/utils.py): enable background process to reset key budgets 2024-01-23 12:33:13 -08:00
ishaan-jaff
a045400516 (fix) select_data_generator 2024-01-23 12:13:34 -08:00
ishaan-jaff
18fceed1e0 (fix) select_data_generator - sagemaker 2024-01-23 12:08:58 -08:00
ishaan-jaff
1f229a46ad (fix) proxy - streaming sagemaker 2024-01-23 11:12:16 -08:00
Krish Dholakia
3eaae0e73c Merge pull request #1557 from BerriAI/litellm_emit_spend_logs
feat(utils.py): emit response cost as part of logs
2024-01-22 21:02:40 -08:00