tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-24 00:28:32 +00:00
Code Issues Packages Projects Releases Wiki Activity
12,839 Commits 2,072 Branches 1,425 Tags
af39e2d2ddf5f4c1c80098682ffe8520c2e6a8b9
Commit Graph
12839 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Ishaan Jaff 51961387a2 ui - filter tags by starttime and endtime 2024-05-13 17:15:25 -07:00
Ishaan Jaff 5845d6f958 feat - filter tags by startTime and endTime 2024-05-13 17:15:04 -07:00
Ishaan Jaff 6ea5a276f8 backend - show spend per tag by time 2024-05-13 17:13:48 -07:00
Krrish Dholakia d7c28509d7 fix(utils.py): watsonx ai exception mapping fix 2024-05-13 17:11:33 -07:00
Marc Abramowitz 94f7353596 Document SLACK_DAILY_REPORT_FREQUENCY 
in `docs/my-website/docs/proxy/alerting.md`
 2024-05-13 17:10:41 -07:00
Marc Abramowitz bfec894f6b Cast SLACK_DAILY_REPORT_FREQUENCY to int 2024-05-13 17:08:53 -07:00
Krrish Dholakia af9489bbfd fix(router.py): overloads fix 2024-05-13 17:04:04 -07:00
Marc Abramowitz bdb995f436 Revert = None changes 
because @krrishdholakia said [here](https://github.com/BerriAI/litellm/pull/3600#discussion_r1599108453)
that they were problematic in the past.
 2024-05-13 16:49:36 -07:00
Krrish Dholakia 240c9550f0 fix(utils.py): handle api assistant returning 'null' role 
Fixes https://github.com/BerriAI/litellm/issues/3621
 2024-05-13 16:46:07 -07:00
Marc Abramowitz 01da3b0a7a Add ability to customize slack report frequency 
via `SLACK_DAILY_REPORT_FREQUENCY` env var

Addresses one thing that @taralika mentioned in
https://github.com/BerriAI/litellm/issues/3597
 2024-05-13 16:39:44 -07:00
Ishaan Jaff d3f76e33e4 ui - clean up edit team input box 2024-05-13 16:36:21 -07:00
Ishaan Jaff 8c37c47c8d bump: version 1.37.8 → 1.37.9 2024-05-13 16:30:05 -07:00
Krish DholakiaandGitHub e92f433566 Merge pull request #3554 from paneru-rajan/Issue-3544-fix-message 
Fixes #3544 based on the data-type of message
 2024-05-13 16:23:58 -07:00
Krrish Dholakia c7b3193944 fix(proxy/_types.py): allow jwt admin to access /team/list route 2024-05-13 16:07:31 -07:00
Ishaan JaffandGitHub ea9b4dc439 Merge pull request #3619 from BerriAI/litellm_show_spend_reports 
[Feat] -  `/global/spend/report`
 2024-05-13 16:06:02 -07:00
Ishaan Jaff eb2d6ba20a ui - new build 2024-05-13 15:56:59 -07:00
Ishaan Jaff 53ab935151 cleanup PR template 2024-05-13 15:54:58 -07:00
Ishaan Jaff d0a5c9b363 docs - spend per team 2024-05-13 15:48:26 -07:00
Krrish Dholakia aa2f6aa5bd bump: version 1.37.7 → 1.37.8 2024-05-13 15:31:59 -07:00
Ishaan Jaff 11d3c86cf1 test /spend/report 2024-05-13 15:26:39 -07:00
Krrish Dholakia b4a8665d11 fix(utils.py): fix custom pricing when litellm model != response obj model name 2024-05-13 15:25:35 -07:00
Ishaan JaffandGitHub 1be6ea0c0d Merge pull request #3603 from alexanderepstein/langfuse_turn_off_messaging 
feat(langfuse.py): Allow for individual call message/response redaction
 2024-05-13 15:21:41 -07:00
Ishaan Jaff 12cf9d71c7 feat - /spend/report endpoint 2024-05-13 15:01:02 -07:00
Krrish Dholakia 1312eece6d fix(router.py): overloads for better router.acompletion typing 2024-05-13 14:27:16 -07:00
Krrish Dholakia bd2f46fd75 fix(slack_alerting.py): if 'turn_off_message_logging' enabled, do not log the message to logging integration 2024-05-13 14:02:43 -07:00
Ishaan Jaff 9d4b727913 fix - show team based spend reports 2024-05-13 13:56:48 -07:00
Krrish Dholakia 7fa203c810 docs(input.md): add mistral to input param docs 2024-05-13 13:50:49 -07:00
Krrish Dholakia 20456968e9 fix(openai.py): creat MistralConfig with response_format mapping for mistral api v1.37.7 2024-05-13 13:29:58 -07:00
Ishaan Jaff 20fe4ffd6b bump: version 1.37.6 → 1.37.7 2024-05-13 13:03:14 -07:00
Ishaan JaffandGitHub 112c06ae54 Merge pull request #3550 from BerriAI/dependabot/npm_and_yarn/ui/litellm-dashboard/next-14.1.1 
build(deps): bump next from 14.1.0 to 14.1.1 in /ui/litellm-dashboard
 2024-05-13 13:01:02 -07:00
Ishaan Jaff 3a838934c9 docs - cooldown deployment 2024-05-13 12:50:59 -07:00
Ishaan Jaff dac8c644fd docs - router show cooldown_time 2024-05-13 12:49:51 -07:00
Ishaan JaffandGitHub 21845bc061 Merge pull request #3609 from BerriAI/litellm_send_daily_spend_report 
[Feat] send weekly spend reports by Team/Tag
 2024-05-13 12:45:37 -07:00
Krrish Dholakia 39e4927752 fix(utils.py): fix vertex ai function calling + streaming 
Completes https://github.com/BerriAI/litellm/issues/3147
v1.37.6 		2024-05-13 12:32:39 -07:00
Ishaan Jaff 40b2f33a80 fix - only schedule spend alerting when db is not none 2024-05-13 12:30:54 -07:00
Ishaan JaffandGitHub efaf4c87f2 Merge pull request #3601 from msabramo/msabramo/update-fastapi-to-update-starlette-to-fix-httpx-warnings 
Update FastAPI to update starlette to fix warnings
 2024-05-13 12:20:17 -07:00
Krrish Dholakia 5dc3f157a6 build(model_prices_and_context_window.json): fix gpt-4o max tokens 2024-05-13 12:11:15 -07:00
Krish DholakiaandGitHub 6c2168b6f7 Merge pull request #3613 from ConnorDoyle/patch-1 
Add gpt-4o metadata
 2024-05-13 12:09:27 -07:00
Connor DoyleandGitHub 5da5021918 Update model_prices_and_context_window.json 2024-05-13 11:51:54 -07:00
Marc Abramowitz 1efa2e65ac Merge branch 'main' into msabramo/fix-pydantic-warnings 2024-05-13 11:34:06 -07:00
Marc Abramowitz 73541b1f17 Merge branch 'msabramo/pydantic_replace_root_validator_with_model_validator' into msabramo/fix-pydantic-warnings 2024-05-13 11:25:55 -07:00
Marc Abramowitz e261a9b2c2 Use Config class w/ arbitrary_types_allowed for pydantic v1 
pydantic v2 warns about using a Config class.
But without this, pydantic v1 will raise an error:
    RuntimeError: no validator found for <class 'openai.Timeout'>,
    see `arbitrary_types_allowed` in Config
Putting arbitrary_types_allowed = True in the ConfigDict doesn't work in pydantic v1.
So we mostly use model_config = ConfigDict(...) and then only use the Config
class with arbitrary_types_allowed = True for pydantic v1.
 2024-05-13 11:22:50 -07:00
Connor DoyleandGitHub a4380f67a9 Add gpt-4o metadata 
#3612
 2024-05-13 11:12:17 -07:00
Marc Abramowitz f233cde36c Replace some Config classes with model_config 
in `litellm/types/router.py`

I didn't replace the ones that have `allow_arbitrary_types` because changing
those seems to break pydantic v1 compatibility.
 2024-05-13 11:04:13 -07:00
Ishaan Jaff 7f6f196e66 ui - show daily reports on UI 2024-05-13 10:55:54 -07:00
Ishaan Jaff 3fbebe16aa fix - spend reports on alerts 2024-05-13 10:51:59 -07:00
Ishaan Jaff aac81c59b5 test - weekly / monthly spend report alerts on /health/services 2024-05-13 10:50:26 -07:00
Ishaan Jaff 197eb44832 fix scheduling spend reports 2024-05-13 10:45:22 -07:00
Ishaan Jaff 4a679bb640 schedule weekly/monthly spend reports 2024-05-13 10:44:19 -07:00
Krrish Dholakia 04ae285001 fix(vertex_ai.py): support tool call list response async completion 2024-05-13 10:42:31 -07:00