phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(feat) embedding() support for timeouts

Browse source
This commit is contained in:
ishaan-jaff 2023-11-22 14:25:54 -08:00
parent c38782521c
commit 5abd566b7c
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/llms/openai.py
View file

@ -306,11 +306,13 @@ class OpenAIChatCompletion(BaseLLM):
def embedding(self, def embedding(self,
model: str, model: str,
input: list, input: list,
timeout: float,
api_key: Optional[str] = None, api_key: Optional[str] = None,
api_base: Optional[str] = None, api_base: Optional[str] = None,
logging_obj=None, logging_obj=None,
model_response=None, model_response=None,
optional_params=None,): optional_params=None,
):
super().embedding() super().embedding()
exception_mapping_worked = False exception_mapping_worked = False
try: try:
@ -323,7 +325,7 @@ class OpenAIChatCompletion(BaseLLM):
max_retries = data.pop("max_retries", 2) max_retries = data.pop("max_retries", 2)
if not isinstance(max_retries, int): if not isinstance(max_retries, int):
raise OpenAIError(status_code=422, message="max retries must be an int") raise OpenAIError(status_code=422, message="max retries must be an int")
openai_client = OpenAI(api_key=api_key, base_url=api_base, http_client=litellm.client_session, max_retries=max_retries) openai_client = OpenAI(api_key=api_key, base_url=api_base, http_client=litellm.client_session, max_retries=max_retries, timeout=timeout)
## LOGGING ## LOGGING
logging_obj.pre_call( logging_obj.pre_call(