phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
13685 commits 1603 branches 645 tags 320 MiB
Commit graph

13685 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
22b7c0333d docs - add nvidia nim 2024-06-27 20:20:30 -07:00
Ishaan Jaff
ee0d8341b0 test - nvidia nim 2024-06-27 20:20:30 -07:00
Ishaan Jaff
a9f17d141c feat - add param mapping for nvidia nim 2024-06-27 20:20:30 -07:00
Ishaan Jaff
11ea1474b1 feat - add nvidia nim to main.py 2024-06-27 20:20:30 -07:00
Ishaan Jaff
b55c31ec3f add nvidia nim to __init__ 2024-06-27 20:20:30 -07:00
Ishaan Jaff
e471aca81f feat - add debug_utils 2024-06-27 20:20:30 -07:00
Krish Dholakia
c18b8bb011 Update README.md 2024-06-27 20:20:30 -07:00
Krish Dholakia
43e42389d7 Update README.md 2024-06-27 20:20:30 -07:00
Kyrylo Yefimenko
1946610efd Fix Groq prices 2024-06-27 20:20:30 -07:00
corrm
2e7b0096d0 Improve ollama prompt: this formula give good result with AutoGen 2024-06-27 20:20:30 -07:00
corrm
ec36dd40d7 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_
 2024-06-27 20:20:30 -07:00
Islam Nofl
cc261580ac Rename ollama prompt 'Function' word to 'Name' 2024-06-27 20:20:30 -07:00
corrm
a7efb9c332 Added improved function name handling in ollama_async_streaming 2024-06-27 20:20:30 -07:00
corrm
5d5227294d chore: Improved OllamaConfig get_required_params and ollama_acompletion and ollama_async_streaming functions 2024-06-27 20:20:30 -07:00
corrm
e1e8f5a00e chore: Improved prompt generation in ollama_pt function 2024-06-27 20:20:30 -07:00
Krrish Dholakia
bb64c68daf docs(routing.md): add quickstart 2024-06-27 20:20:30 -07:00
Krrish Dholakia
673696222d fix(langfuse.py): cleanup 2024-06-27 20:20:30 -07:00
Ishaan Jaff
4d7b2e578c bump: version 1.40.25 → 1.40.26 2024-06-27 20:20:30 -07:00
Ishaan Jaff
c5020878e4 /spend/calculate use model aliases on this endpoint 2024-06-27 20:20:30 -07:00
Ishaan Jaff
08f83e6392 test - aliases on /spend/calculate 2024-06-27 20:20:30 -07:00
Krrish Dholakia
690c7f6e47 fix(router.py): log rejected router requests to langfuse 
Fixes issue where rejected requests weren't being logged
 2024-06-27 20:20:30 -07:00
Ishaan Jaff
7a961e8a0b docs control available public routes 2024-06-27 20:20:30 -07:00
Ishaan Jaff
412c1fc541 fix importing litellm 2024-06-27 20:20:29 -07:00
Ishaan Jaff
e7ff5014b1 example cofnig with public routes 2024-06-27 20:20:29 -07:00
Ishaan Jaff
fa5eb5c96f add helper to check route_in_additonal_public_routes 2024-06-27 20:20:29 -07:00
Ishaan Jaff
556ef8dd18 test - spend/calculate endpoints 2024-06-27 20:20:29 -07:00
Ishaan Jaff
2cb4d845ae feat - refactor /spend/calculate 2024-06-27 20:20:29 -07:00
Ishaan Jaff
bfae8c3da6 example config with public routes 2024-06-27 20:20:29 -07:00
Ishaan Jaff
e30410f700 feat - allow user to define public routes 2024-06-27 20:20:29 -07:00
Krrish Dholakia
a087596be0 fix(vertex_httpx.py): Return empty model response for content filter violations 2024-06-27 20:20:29 -07:00
Krrish Dholakia
6f2f89d7b2 fix(vertex_httpx.py): cover gemini content violation (on prompt) 2024-06-27 20:20:29 -07:00
Krrish Dholakia
438f65666b fix(utils.py): catch 422-status errors 2024-06-27 20:20:29 -07:00
Krrish Dholakia
82c6f31095 test(test_router.py): add testing 2024-06-27 20:20:29 -07:00
Krrish Dholakia
2e588c0685 fix(router.py): use user-defined model_input_tokens for pre-call filter checks 2024-06-27 20:20:29 -07:00
Krrish Dholakia
247d71db7a fix(utils.py): fix exception_mapping check for errors 
If exception already mapped - don't attach traceback to it
 2024-06-27 20:20:29 -07:00
Ishaan Jaff
6ac0f20099 docs - update telemetry 2024-06-27 20:20:29 -07:00
Ishaan Jaff
b2302bf224 fix ui login bug 2024-06-27 20:20:29 -07:00
7HR4IZ3
4e84147593 fix: Lunary integration 
Fixes the bug of litellm not logging system messages to lunary
 2024-06-27 20:20:29 -07:00
Krrish Dholakia
af21695f2b test: skip unstable tests 2024-06-27 20:20:29 -07:00
Krrish Dholakia
d2fe2b30a9 test(test_completion.py): handle replicate api error 2024-06-27 20:20:29 -07:00
Krrish Dholakia
b577f65798 test(test_proxy_server_langfuse.py): cleanup tests causing OOM issues. 2024-06-27 20:20:29 -07:00
Krrish Dholakia
c450dee681 fix(redact_messages.py): fix pr 2024-06-27 20:20:29 -07:00
Krrish Dholakia
3c92467ae8 fix(test_dynamic_rate_limit_handler.py): cleanup 2024-06-27 20:20:29 -07:00
Krrish Dholakia
2834a6395a fix(redact_messages.py): fix get 2024-06-27 20:20:29 -07:00
Krrish Dholakia
0971219470 docs(team_budgets.md): cleanup docs 2024-06-27 20:20:29 -07:00
Krrish Dholakia
544338bdf4 bump: version 1.40.24 → 1.40.25 2024-06-27 20:20:29 -07:00
Marc Abramowitz
379b834480 Document feature 2024-06-27 20:20:29 -07:00
Marc Abramowitz
d14138dbd9 Rename request header 2024-06-27 20:20:29 -07:00
Marc Abramowitz
efae9fa991 Turn on message logging via request header 2024-06-27 20:20:29 -07:00
Krrish Dholakia
7f54c90459 fix(add-exception-mapping-+-langfuse-exception-logging-for-streaming-exceptions): add exception mapping + langfuse exception logging for streaming exceptions 
Fixes https://github.com/BerriAI/litellm/issues/4338
 2024-06-27 20:20:29 -07:00