Litellm dev 12 30 2024 p2 (#7495)

* 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

* fix(types/utils.py): handle none logprobs

Fixes https://github.com/BerriAI/litellm/issues/328

* fix(exception_mapping_utils.py): fix error str unbound error

* refactor(azure_ai/): move to openai_like chat completion handler

allows for easy swapping of api base url's (e.g. ai.services.com)

Fixes https://github.com/BerriAI/litellm/issues/7275

* refactor(azure_ai/): move to base llm http handler

* fix(azure_ai/): handle differing api endpoints

* fix(azure_ai/): make sure all unit tests are passing

* fix: fix linting errors

* fix: fix linting errors

* fix: fix linting error

* fix: fix linting errors

* fix(azure_ai/transformation.py): handle extra body param

* fix(azure_ai/transformation.py): fix max retries param handling

* fix: fix test

* test(test_azure_o1.py): fix test

* fix(llm_http_handler.py): support handling azure ai unprocessable entity error

* fix(llm_http_handler.py): handle sync invalid param error for azure ai

* fix(azure_ai/): streaming support with base_llm_http_handler

* fix(llm_http_handler.py): working sync stream calls with unprocessable entity handling for azure ai

* fix: fix linting errors

* fix(llm_http_handler.py): fix linting error

* fix(azure_ai/): handle cohere tool call invalid index param error
This commit is contained in:
Krish Dholakia 2025-01-01 18:57:29 -08:00 committed by GitHub
parent 0f1b298fe0
commit 0120176541
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
42 changed files with 638 additions and 192 deletions

View file

@ -45,7 +45,8 @@ class OpenAIError(BaseLLMException):
####### Error Handling Utils for OpenAI API #######################
###################################################################
def drop_params_from_unprocessable_entity_error(
e: openai.UnprocessableEntityError, data: Dict[str, Any]
e: Union[openai.UnprocessableEntityError, httpx.HTTPStatusError],
data: Dict[str, Any],
) -> Dict[str, Any]:
"""
Helper function to read OpenAI UnprocessableEntityError and drop the params that raised an error from the error message.
@ -58,14 +59,25 @@ def drop_params_from_unprocessable_entity_error(
Dict[str, Any]: A new dictionary with invalid parameters removed
"""
invalid_params: List[str] = []
if e.body is not None and isinstance(e.body, dict) and e.body.get("message"):
message = e.body.get("message", {})
if isinstance(e, httpx.HTTPStatusError):
error_json = e.response.json()
error_message = error_json.get("error", {})
error_body = error_message
else:
error_body = e.body
if (
error_body is not None
and isinstance(error_body, dict)
and error_body.get("message")
):
message = error_body.get("message", {})
if isinstance(message, str):
try:
message = json.loads(message)
except json.JSONDecodeError:
message = {"detail": message}
detail = message.get("detail")
if isinstance(detail, List) and len(detail) > 0 and isinstance(detail[0], dict):
for error_dict in detail:
if (
@ -76,4 +88,5 @@ def drop_params_from_unprocessable_entity_error(
invalid_params.append(error_dict["loc"][1])
new_data = {k: v for k, v in data.items() if k not in invalid_params}
return new_data