phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Litellm dev 12 30 2024 p1 (#7480)

Browse source 
* test(azure_openai_o1.py): initial commit with testing for azure openai o1 preview model

* fix(base_llm_unit_tests.py): handle azure o1 preview response format tests

skip as o1 on azure doesn't support tool calling yet

* fix: initial commit of azure o1 handler using openai caller

simplifies calling + allows fake streaming logic alr. implemented for openai to just work

* feat(azure/o1_handler.py): fake o1 streaming for azure o1 models

azure does not currently support streaming for o1

* feat(o1_transformation.py): support overriding 'should_fake_stream' on azure/o1 via 'supports_native_streaming' param on model info

enables user to toggle on when azure allows o1 streaming without needing to bump versions

* style(router.py): remove 'give feedback/get help' messaging when router is used

Prevents noisy messaging

Closes https://github.com/BerriAI/litellm/issues/5942

* test: fix azure o1 test

* test: fix tests

* fix: fix test
This commit is contained in:
Krish Dholakia 2024-12-30 21:52:52 -08:00 • committed by GitHub
parent f0ed02d3ee
commit 0178e75cd9
17 changed files with 273 additions and 141 deletions
Download patch file Download diff file Expand all files Collapse all files

7
litellm/main.py
View file

@ -1225,10 +1225,7 @@ def completion( # type: ignore # noqa: PLR0915
if extra_headers is not None:
optional_params["extra_headers"] = extra_headers
if (
litellm.enable_preview_features
and litellm.AzureOpenAIO1Config().is_o1_model(model=model)
):
if litellm.AzureOpenAIO1Config().is_o1_model(model=model):
## LOAD CONFIG - if set
config = litellm.AzureOpenAIO1Config.get_config()
for k, v in config.items():
@ -1244,7 +1241,6 @@ def completion( # type: ignore # noqa: PLR0915
api_key=api_key,
api_base=api_base,
api_version=api_version,
api_type=api_type,
dynamic_params=dynamic_params,
azure_ad_token=azure_ad_token,
model_response=model_response,
@ -1256,6 +1252,7 @@ def completion( # type: ignore # noqa: PLR0915
acompletion=acompletion,
timeout=timeout, # type: ignore
client=client, # pass AsyncAzureOpenAI, AzureOpenAI client
custom_llm_provider=custom_llm_provider,
)
else:
## LOAD CONFIG - if set