litellm/litellm/types
Krish Dholakia 424b8b0231
Litellm dev 11 23 2024 (#6881)
* build(ui/create_key_button.tsx): support adding tags for cost tracking/routing when making key

* LiteLLM Minor Fixes & Improvements (11/23/2024)  (#6870)

* feat(pass_through_endpoints/): support logging anthropic/gemini pass through calls to langfuse/s3/etc.

* fix(utils.py): allow disabling end user cost tracking with new param

Allows proxy admin to disable cost tracking for end user - keeps prometheus metrics small

* docs(configs.md): add disable_end_user_cost_tracking reference to docs

* feat(key_management_endpoints.py): add support for restricting access to `/key/generate` by team/proxy level role

Enables admin to restrict key creation, and assign team admins to handle distributing keys

* test(test_key_management.py): add unit testing for personal / team key restriction checks

* docs: add docs on restricting key creation

* docs(finetuned_models.md): add new guide on calling finetuned models

* docs(input.md): cleanup anthropic supported params

Closes https://github.com/BerriAI/litellm/issues/6856

* test(test_embedding.py): add test for passing extra headers via embedding

* feat(cohere/embed): pass client to async embedding

* feat(rerank.py): add `/v1/rerank` if missing for cohere base url

Closes https://github.com/BerriAI/litellm/issues/6844

* fix(main.py): pass extra_headers param to openai

Fixes https://github.com/BerriAI/litellm/issues/6836

* fix(litellm_logging.py): don't disable global callbacks when dynamic callbacks are set

Fixes issue where global callbacks - e.g. prometheus were overriden when langfuse was set dynamically

* fix(handler.py): fix linting error

* fix: fix typing

* build: add conftest to proxy_admin_ui_tests/

* test: fix test

* fix: fix linting errors

* test: fix test

* fix: fix pass through testing

* feat(key_management_endpoints.py): allow proxy_admin to enforce params on key creation

allows admin to force team keys to have tags

* build(ui/): show teams in leftnav + allow team admin to add new members

* build(ui/): show created tags in dropdown

makes it easier for admin to add tags to keys

* test(test_key_management.py): fix test

* test: fix test

* fix playwright e2e ui test

* fix e2e ui testing deps

* fix: fix linting errors

* fix e2e ui testing

* fix e2e ui testing, only run e2e ui testing in playwright

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
2024-11-23 22:37:16 +05:30
..
integrations (Feat) Add langsmith key based logging (#6682) 2024-11-11 13:58:06 -08:00
llms (Perf / latency improvement) improve pass through endpoint latency to ~50ms (before PR was 400ms) (#6874) 2024-11-22 18:47:26 -08:00
adapter.py feat(anthropic_adapter.py): support for translating anthropic params to openai format 2024-07-10 00:32:28 -07:00
caching.py (refactor caching) use common _retrieve_from_cache helper (#6212) 2024-10-14 19:12:41 +05:30
completion.py LiteLLM Minor Fixes and Improvements (09/12/2024) (#5658) 2024-09-12 23:04:06 -07:00
embedding.py Removed config dict type definition 2024-05-17 10:39:00 +08:00
files.py Fix file type handling of uppercase extensions 2024-06-13 15:00:16 -07:00
guardrails.py LiteLLM Minor Fixes & Improvements (10/15/2024) (#6242) 2024-10-16 07:32:06 -07:00
rerank.py LiteLLM Minor Fixes & Improvement (11/14/2024) (#6730) 2024-11-15 01:02:54 +05:30
router.py (feat) provider budget routing improvements (#6827) 2024-11-19 21:25:08 -08:00
services.py Litellm perf improvements 3 (#6573) 2024-11-05 03:51:26 +05:30
utils.py Litellm dev 11 23 2024 (#6881) 2024-11-23 22:37:16 +05:30