phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
13696 commits 1603 branches 645 tags 320 MiB
Commit graph

13696 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
304e84f87c clean up secret detection 2024-06-25 17:25:53 -07:00
Ishaan Jaff
e4653e6032 fix async_pre_call_hook 2024-06-25 16:38:47 -07:00
Ishaan Jaff
e22c9ba0cc init secret detection callback 2024-06-25 16:25:14 -07:00
Ishaan Jaff
4aa686bb05 feat - add secret detection 2024-06-25 16:23:56 -07:00
Krrish Dholakia
6e02ac0056 fix(utils.py): add coverage for anthropic content policy error - vertex ai 2024-06-25 11:47:39 -07:00
Krrish Dholakia
cccc55213b fix(router.py): improve error message returned for fallbacks 2024-06-25 11:27:20 -07:00
Ishaan Jaff
2bd993039b
Merge pull request #4405 from BerriAI/litellm_update_mock_completion 
[Fix] - use `n` in mock completion responses
 2024-06-25 11:20:30 -07:00
Ishaan Jaff
ccf1bbc5d7 fix using mock completion 2024-06-25 11:14:40 -07:00
Krrish Dholakia
71b7c2886b docs(reliability.md): add doc on mock testing fallbacks 2024-06-25 11:07:07 -07:00
Krrish Dholakia
0396d484fb feat(router.py): support mock testing content policy + context window fallbacks 2024-06-25 10:58:19 -07:00
Ishaan Jaff
343e3f3e90 test - test_mock_request_n_greater_than_1 2024-06-25 10:54:18 -07:00
Ishaan Jaff
a230f5f6c5 feat - use n in mock completion 2024-06-25 10:50:47 -07:00
Ishaan Jaff
6f51da4e78
Merge pull request #4403 from BerriAI/litellm_add_nvidia_nim 
[Feat-New Provider] Add Nvidia NIM
 2024-06-25 10:36:28 -07:00
Ishaan Jaff
b9f83f48ba
Merge pull request #4364 from BerriAI/litellm_use_tracemalloc_mem_usage 
[Feat]  add endpoint to debug memory util
 2024-06-25 10:32:52 -07:00
Ishaan Jaff
b4497acfc2 ci/cd run again 2024-06-25 09:48:49 -07:00
Ishaan Jaff
100f245fef docs nvidia_nim 2024-06-25 09:46:42 -07:00
Ishaan Jaff
bac5dfb30b docs - add nvidia nim 2024-06-25 09:38:34 -07:00
Krish Dholakia
e2a50b66f2
Update README.md 2024-06-25 09:24:00 -07:00
Krish Dholakia
e354840f90
Update README.md 2024-06-25 09:23:19 -07:00
Ishaan Jaff
e5f281074f test - nvidia nim 2024-06-25 09:16:31 -07:00
Ishaan Jaff
07829514d1 feat - add param mapping for nvidia nim 2024-06-25 09:13:08 -07:00
Ishaan Jaff
d829d6393d feat - add nvidia nim to main.py 2024-06-25 08:57:11 -07:00
Ishaan Jaff
39a2b41e16
Merge pull request #4401 from kiriloman/main 
Fix Groq Prices
 2024-06-25 08:56:07 -07:00
Ishaan Jaff
abf919eef2 add nvidia nim to __init__ 2024-06-25 08:53:06 -07:00
Kyrylo Yefimenko
8765e120f0 Fix Groq prices 2024-06-25 16:36:40 +01:00
Krish Dholakia
75c8f77d9a
Merge pull request #4373 from CorrM/main 
[Fix-Improve] Improve Ollama prompt input and fix Ollama function calling key error
 2024-06-25 06:27:43 -07:00
corrm
5b720137fd Improve ollama prompt: this formula give good result with AutoGen 2024-06-25 13:53:27 +03:00
corrm
b69a092f56 Rename ollama prompt: 
- 'Function' word to 'FunctionName'
- 'Tool Call' to `FunctionCall`
- 'Tool Call Result' to 'FunctionCall Result'

_I found that changes make some models better_
 2024-06-25 12:40:07 +03:00
Krrish Dholakia
86cb5aa031 docs(routing.md): add quickstart 2024-06-24 22:25:39 -07:00
Krrish Dholakia
f8b390d421 fix(langfuse.py): cleanup 2024-06-24 21:43:40 -07:00
Ishaan Jaff
93dbdf6d92 bump: version 1.40.25 → 1.40.26 2024-06-24 21:15:36 -07:00
Ishaan Jaff
a9d1be71ff
Merge pull request #4395 from BerriAI/litelm_use_spend_calc_aliases 
Fix /spend/calculate use model_group_alias when set
 2024-06-24 21:15:05 -07:00
Ishaan Jaff
9e7d8ba910 /spend/calculate use model aliases on this endpoint 2024-06-24 21:14:00 -07:00
Krish Dholakia
9902947521
Merge pull request #4390 from BerriAI/litellm_langfuse_router_logging 
Log rejected router requests to langfuse
 2024-06-24 21:13:45 -07:00
Ishaan Jaff
a64d1de80f test - aliases on /spend/calculate 2024-06-24 21:13:01 -07:00
Ishaan Jaff
7e5f200c6d
Merge pull request #4394 from BerriAI/docs_enterprise_control_routes 
docs control available public routes
 2024-06-24 20:57:00 -07:00
Ishaan Jaff
7f8c502a44 docs control available public routes 2024-06-24 20:54:43 -07:00
Ishaan Jaff
37f2712bba
Merge pull request #4389 from BerriAI/litellm_allow_user_to_define_public_routes 
[Feat-Enterprise] - Allow setting custom public routes
 2024-06-24 20:23:35 -07:00
Krish Dholakia
5d570e7c6c
Merge pull request #4392 from BerriAI/litellm_gemini_content_policy_errors 
fix(vertex_httpx.py): cover gemini content violation (on prompt)
 2024-06-24 20:00:06 -07:00
Ishaan Jaff
2aa0ce50b5 fix importing litellm 2024-06-24 19:58:53 -07:00
Ishaan Jaff
bd2298eba4 example cofnig with public routes 2024-06-24 19:51:23 -07:00
Ishaan Jaff
5e1403cd0a add helper to check route_in_additonal_public_routes 2024-06-24 19:50:35 -07:00
Krrish Dholakia
d182ea0f77 fix(utils.py): catch 422-status errors 2024-06-24 19:41:48 -07:00
Ishaan Jaff
11117665e1 test - spend/calculate endpoints 2024-06-24 19:32:52 -07:00
Krish Dholakia
95f972ee9f
Merge pull request #4388 from BerriAI/litellm_custom_model_info 
Support custom model info for router logic (e.g. `max_input_tokens`)
 2024-06-24 19:31:37 -07:00
Krrish Dholakia
8e6e5a6d37 fix(vertex_httpx.py): Return empty model response for content filter violations 2024-06-24 19:22:20 -07:00
Krrish Dholakia
1ff0129a94 fix(vertex_httpx.py): cover gemini content violation (on prompt) 2024-06-24 19:13:56 -07:00
Ishaan Jaff
02ffed2545 feat - refactor /spend/calculate 2024-06-24 19:05:34 -07:00
Krrish Dholakia
a4bea47a2d fix(router.py): log rejected router requests to langfuse 
Fixes issue where rejected requests weren't being logged
 2024-06-24 17:52:01 -07:00
Ishaan Jaff
5309be2456 example config with public routes 2024-06-24 17:46:38 -07:00