scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-11 08:38:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 280

fix(huggingface): keep the unreachable async lookup path untouched

Browse source 
The async model lookup helper and the call_type="async" transform branch are never reached, since the async embedding path transforms through the sync lookup. Leave them as they were so the change only touches requests that actually run.
This commit is contained in:
ryan-crabbe-berri 2026-10-27 10:40:15 -07:00
parent e95ae2f065
commit 60bc967239
1 changed files with 4 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
litellm/llms/huggingface/embedding/handler.py
View file

@ -57,9 +57,7 @@ def get_hf_task_embedding_for_model(
return pipeline_tag
async def async_get_hf_task_embedding_for_model(
model: str, task_type: str | None, api_base: str, timeout: float | httpx.Timeout | None = None
) -> object:
async def async_get_hf_task_embedding_for_model(model: str, task_type: str | None, api_base: str) -> object:
if task_type is not None:
if task_type in get_args(hf_tasks_embeddings):
return task_type
@ -69,7 +67,7 @@ async def async_get_hf_task_embedding_for_model(
llm_provider=litellm.LlmProviders.HUGGINGFACE,
)
model_info: Final = await http_client.get(url=f"{api_base}/api/models/{model}", timeout=timeout)
model_info: Final = await http_client.get(url=f"{api_base}/api/models/{model}")
model_info_dict: Final = decoded_json_object(_DECODED_JSON.validate_python(model_info.json()))
@ -111,11 +109,8 @@ class HuggingFaceEmbedding(BaseLLM):
embed_url: str,
input: list,
optional_params: dict,
timeout: float | httpx.Timeout | None = None,
) -> dict:
hf_task = await async_get_hf_task_embedding_for_model(
model=model, task_type=task_type, api_base=HF_HUB_URL, timeout=timeout
)
hf_task = await async_get_hf_task_embedding_for_model(model=model, task_type=task_type, api_base=HF_HUB_URL)
data: Final = self._transform_input_on_pipeline_tag(input=input, pipeline_tag=hf_task)
@ -177,9 +172,7 @@ class HuggingFaceEmbedding(BaseLLM):
model=model, task_type=task_type, api_base=HF_HUB_URL, timeout=timeout
)
elif call_type == "async":
return self._async_transform_input(
model=model, task_type=task_type, embed_url=embed_url, input=input, timeout=timeout
)
return self._async_transform_input(model=model, task_type=task_type, embed_url=embed_url, input=input)
data = self._transform_input_on_pipeline_tag(input=input, pipeline_tag=hf_task)