Krrish Dholakia
|
511510a1cc
|
refactor(proxy_server.py): fix docstring for /key/delete to show hashed tokens as well
|
2024-01-26 13:33:17 -08:00 |
|
Krrish Dholakia
|
e989175c10
|
fix(proxy/utils.py): accept token hashes for deleting tokens
|
2024-01-26 13:29:16 -08:00 |
|
ishaan-jaff
|
273e6d1905
|
Revert "(fix) SpendLogs Table"
This reverts commit 2a1104d1cf .
|
2024-01-26 13:26:49 -08:00 |
|
ishaan-jaff
|
55b95e87dd
|
(fix) SpendLogs Table
|
2024-01-26 13:23:51 -08:00 |
|
ishaan-jaff
|
2a1104d1cf
|
(fix) SpendLogs Table
|
2024-01-26 13:18:27 -08:00 |
|
ishaan-jaff
|
0fc8876ea2
|
(feat) support dimensions param
|
2024-01-26 10:55:38 -08:00 |
|
ishaan-jaff
|
479add6b96
|
(feat) add support for dimensions param
|
2024-01-26 10:54:34 -08:00 |
|
ishaan-jaff
|
17370dc50f
|
(test) dimension param - openai
|
2024-01-26 10:37:01 -08:00 |
|
ishaan-jaff
|
64f1301033
|
(feat) SpendLogs show total_tokens, prompt_tokens, completion_tokens
|
2024-01-26 10:26:15 -08:00 |
|
ishaan-jaff
|
b9fc2c3735
|
(fix) SpendLogs stop logging model params
|
2024-01-26 10:13:34 -08:00 |
|
Sébastien Campion
|
a5d120a68b
|
fix print verbose take only one argument
|
2024-01-26 18:03:55 +01:00 |
|
ishaan-jaff
|
652f4f89d0
|
(test) s3 + r2 logger
|
2024-01-25 21:16:28 -08:00 |
|
ishaan-jaff
|
fa1bbbebf1
|
(fix) r2 s3 logging test
|
2024-01-25 20:49:55 -08:00 |
|
ishaan-jaff
|
4fd2bd230f
|
(fix) test_view_spend_per_user
|
2024-01-25 20:41:31 -08:00 |
|
ishaan-jaff
|
8ed010c428
|
(test) s3 logs - works locally
|
2024-01-25 20:16:33 -08:00 |
|
ishaan-jaff
|
c069acc72e
|
(test) s3 logs
|
2024-01-25 20:13:22 -08:00 |
|
Krish Dholakia
|
612f74a426
|
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
|
933c693e9b
|
s3 logger - add better debug statements
|
2024-01-25 18:47:50 -08:00 |
|
ishaan-jaff
|
863ff8ba26
|
(test) s3 logging on r2 using env vars
|
2024-01-25 18:36:20 -08:00 |
|
ishaan-jaff
|
347bab7786
|
(fix) s3 log .json files
|
2024-01-25 18:36:20 -08:00 |
|
ishaan-jaff
|
7179d0cb48
|
(fix) s3 logger use r2 links
|
2024-01-25 18:36:20 -08:00 |
|
Krrish Dholakia
|
e948b39e3a
|
test(test_streaming.py): fix test to handle none chunk
|
2024-01-25 18:34:13 -08:00 |
|
Krrish Dholakia
|
39aec43b86
|
test(main.py): adding more logging
|
2024-01-25 18:15:24 -08:00 |
|
Krrish Dholakia
|
ac131b3824
|
fix(utils.py): completion_cost support for image gen models
|
2024-01-25 18:08:18 -08:00 |
|
Ishaan Jaff
|
2b1177eaa9
|
Merge pull request #1625 from BerriAI/litellm_improve_admin_ui
[UI] Admin UI improvements
|
2024-01-25 16:48:02 -08:00 |
|
Krrish Dholakia
|
1ae22ea16d
|
refactor: trigger new bump
|
2024-01-25 16:40:23 -08:00 |
|
Krrish Dholakia
|
014f83c847
|
fix(main.py): allow vertex ai project and location to be set in completion() call
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
e00f46a6e9
|
(test) gpt-4-0125-preview
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
c10bda3d30
|
(chore) cleanup testing file
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
7e1b9158fe
|
(test) embedding models
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
5264a3eb53
|
(fix) do nothing if alerting is not switched on
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
1c9b02ad99
|
(fix) alerting debug statements
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
b8f917624f
|
(docs) config.yaml
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
3a1c8f453f
|
(docs) track max_budget on proxy config.yaml
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
229e4920df
|
(fix) better alert message on budgets
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
81c528f6ce
|
(fix) raise correct error when proxy crossed budget
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
56f49a87ba
|
(fix) raise exception budget_duration is set and max_budget is Not
|
2024-01-25 16:40:23 -08:00 |
|
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
|
76468cc351
|
refactor: trigger new bump
|
2024-01-25 16:06:01 -08:00 |
|
Krrish Dholakia
|
72275ad8cb
|
fix(main.py): fix logging event loop for async logging but sync streaming
|
2024-01-25 15:59:53 -08:00 |
|
Krrish Dholakia
|
fbab810189
|
fix(main.py): allow vertex ai project and location to be set in completion() call
|
2024-01-25 15:00:51 -08:00 |
|
Krrish Dholakia
|
bbe6a92eb9
|
fix(main.py): fix order of assembly for streaming chunks
|
2024-01-25 14:51:08 -08:00 |
|
ishaan-jaff
|
e2d9e40886
|
(test) gpt-4-0125-preview
|
2024-01-25 14:42:10 -08:00 |
|
ishaan-jaff
|
72790f44da
|
(chore) cleanup testing file
|
2024-01-25 14:36:11 -08:00 |
|
ishaan-jaff
|
6cbde02cab
|
(test) embedding models
|
2024-01-25 14:30:49 -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 |
|