mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
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
This commit is contained in:
parent
d81ae45827
commit
7e9d8b58f6
35 changed files with 871 additions and 248 deletions
|
@ -91,6 +91,7 @@ def rerank(
|
|||
model_info = kwargs.get("model_info", None)
|
||||
metadata = kwargs.get("metadata", {})
|
||||
user = kwargs.get("user", None)
|
||||
client = kwargs.get("client", None)
|
||||
try:
|
||||
_is_async = kwargs.pop("arerank", False) is True
|
||||
optional_params = GenericLiteLLMParams(**kwargs)
|
||||
|
@ -150,7 +151,7 @@ def rerank(
|
|||
or optional_params.api_base
|
||||
or litellm.api_base
|
||||
or get_secret("COHERE_API_BASE") # type: ignore
|
||||
or "https://api.cohere.com/v1/rerank"
|
||||
or "https://api.cohere.com"
|
||||
)
|
||||
|
||||
if api_base is None:
|
||||
|
@ -173,6 +174,7 @@ def rerank(
|
|||
_is_async=_is_async,
|
||||
headers=headers,
|
||||
litellm_logging_obj=litellm_logging_obj,
|
||||
client=client,
|
||||
)
|
||||
elif _custom_llm_provider == "azure_ai":
|
||||
api_base = (
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue