phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
19575 commits 2480 branches 894 tags 534 MiB
Commit graph

8 commits

Author SHA1 Message Date
Krish Dholakia
09462ba80c
Add cohere v2/rerank support (#8421) (#8605) 
* Add cohere v2/rerank support (#8421)

* Support v2 endpoint cohere rerank

* Add tests and docs

* Make v1 default if old params used

* Update docs

* Update docs pt 2

* Update tests

* Add e2e test

* Clean up code

* Use inheritence for new config

* Fix linting issues (#8608)

* Fix cohere v2 failing test + linting (#8672)

* Fix test and unused imports

* Fix tests

* fix: fix linting errors

* test: handle tgai instability

* fix: skip service unavailable err

* test: print logs for unstable test

* test: skip unreliable tests

---------

Co-authored-by: vibhavbhat <vibhavb00@gmail.com>
 2025-02-22 22:25:29 -08:00
Krish Dholakia
251467a525
add bedrock llama vision support + cohere / infinity rerank - 'return_documents' support (#8684) 
* build(model_prices_and_context_window.json): mark bedrock llama as supporting vision based on docs

* Add price for Cerebras llama3.3-70b (#8676)

* docs(readme.md): fix contributing docs

point people to new mock directory testing structure s/o @vibhavbhat

* build: update contributing readme

* docs(readme.md): improve docs

* docs(readme.md): cleanup readme on tests/

* docs(README.md): cleanup doc

* feat(infinity/): support returning documents when return_documents=True

* test(test_rerank.py): add e2e testing for cohere rerank

* fix: fix linting errors

* fix(together_ai/): fix together ai transformation

* fix: fix linting error

* fix: fix linting errors

* fix: fix linting errors

* test: mark cohere as flaky

* build: fix model supports check

* test: fix test

* test: mark flaky test

* fix: fix test

* test: fix test

---------

Co-authored-by: Yury Koleda <fut.wrk@gmail.com>
 2025-02-20 21:23:54 -08:00
Krish Dholakia
2340f1b31f
Pass router tags in request headers - x-litellm-tags (#8609) 
* feat(litellm_pre_call_utils.py): support `x-litellm-tags` request header

allow tag based routing + spend tracking via request headers

* docs(request_headers.md): document new `x-litellm-tags` for tag based routing and spend tracking

* docs(tag_routing.md): add to docs

* fix(utils.py): only pass str values for openai metadata param

* fix(utils.py): drop non-str values for metadata param to openai

preview-feature, otel span was being sent in
 2025-02-18 08:26:22 -08:00
Ishaan Jaff
2753de1458
(Bug Fix + Better Observability) - BudgetResetJob: (#8562) 
* use class ResetBudgetJob

* refactor reset budget job

* update reset_budget job

* refactor reset budget job

* fix LiteLLM_UserTable

* refactor reset budget job

* add telemetry for reset budget job

* dd - log service success/failure on DD

* add detailed reset budget reset info on DD

* initialize_scheduled_background_jobs

* refactor reset budget job

* trigger service failure hook when fails to reset a budget for team, key, user

* fix resetBudgetJob

* unit testing for ResetBudgetJob

* test_duration_in_seconds_basic

* testing for triggering service logging

* fix logs on test teams fail

* remove unused imports

* fix import duration in s

* duration_in_seconds
 2025-02-15 16:13:08 -08:00
Krish Dholakia
ce3ead6f91
Log applied guardrails on LLM API call (#8452)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 40s
Details 
* fix(litellm_logging.py): support saving applied guardrails in logging object

allows list of applied guardrails to be logged for proxy admin's knowledge

* feat(spend_tracking_utils.py): log applied guardrails to spend logs

makes it easy for admin to know what guardrails were applied on a request

* ci(config.yml): uninstall posthog from ci/cd

* test: fix tests

* test: update test
 2025-02-10 22:57:30 -08:00
Krish Dholakia
b5850b6b65
Handle azure deepseek reasoning response (#8288) (#8366) 
* Handle azure deepseek reasoning response (#8288)

* Handle deepseek reasoning response

* Add helper method + unit test

* Fix: Follow infinity api url format (#8346)

* Follow infinity api url format

* Update test_infinity.py

* fix(infinity/transformation.py): fix linting error

---------

Co-authored-by: vibhavbhat <vibhavb00@gmail.com>
Co-authored-by: Hao Shan <53949959+haoshan98@users.noreply.github.com>
 2025-02-07 17:45:51 -08:00
Krish Dholakia
f031926b82
fix(utils.py): handle key error in msg validation (#8325) 
* fix(utils.py): handle key error in msg validation

* Support running Aim Guard during LLM call (#7918)

* support running Aim Guard during LLM call

* Rename header

* adjust docs and fix type annotations

* fix(timeout.md): doc fix for openai example on dynamic timeouts

---------

Co-authored-by: Tomer Bin <117278227+hxtomer@users.noreply.github.com>
 2025-02-06 18:13:46 -08:00
Ishaan Jaff
b812286534
(fix) - proxy reliability, ensure duplicate callbacks are not added to proxy (#8067) 
* refactor _add_callbacks_from_db_config

* fix check for _custom_logger_exists_in_litellm_callbacks

* move loc of test utils

* run ci/cd again

* test_add_custom_logger_callback_to_specific_event_with_duplicates_callbacks

* fix _custom_logger_class_exists_in_success_callbacks

* unit testing for test_add_callbacks_from_db_config

* test_custom_logger_exists_in_callbacks_individual_functions

* fix config.yml

* fix test test_stream_chunk_builder_openai_audio_output_usage - use direct dict comparison
 2025-01-28 21:01:56 -08:00
Renamed from tests/local_testing/test_utils.py (Browse further)