phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(fix) add linting check to ban creating AsyncHTTPHandler during LLM calling (#6855)

Browse source 
* fix triton

* fix TEXT_COMPLETION_CODESTRAL

* fix REPLICATE

* fix CLARIFAI

* fix HUGGINGFACE

* add test_no_async_http_handler_usage

* fix PREDIBASE

* fix anthropic use get_async_httpx_client

* fix vertex fine tuning

* fix dbricks get_async_httpx_client

* fix get_async_httpx_client vertex

* fix get_async_httpx_client

* fix get_async_httpx_client

* fix make_async_azure_httpx_request

* fix check_for_async_http_handler

* test: cleanup mistral model

* add check for AsyncClient

* fix check_for_async_http_handler

* fix get_async_httpx_client

* fix tests using in_memory_llm_clients_cache

* fix langfuse import

* fix import

---------

Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
This commit is contained in:
Ishaan Jaff 2024-11-21 19:03:02 -08:00 • committed by GitHub
parent 71ebf47cef
commit 920f4c9f82
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 288 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

14
litellm/llms/huggingface_restapi.py
View file

@ -263,7 +263,11 @@ def get_hf_task_for_model(model: str) -> Tuple[hf_tasks, str]:
return "text-generation-inference", model # default to tgi
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
from litellm.llms.custom_httpx.http_handler import (
AsyncHTTPHandler,
HTTPHandler,
get_async_httpx_client,
)
def get_hf_task_embedding_for_model(
@ -301,7 +305,9 @@ async def async_get_hf_task_embedding_for_model(
task_type, hf_tasks_embeddings
)
)
http_client = AsyncHTTPHandler(concurrent_limit=1)
http_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.HUGGINGFACE,
)
model_info = await http_client.get(url=api_base)
@ -1067,7 +1073,9 @@ class Huggingface(BaseLLM):
)
## COMPLETION CALL
if client is None:
client = AsyncHTTPHandler(concurrent_limit=1)
client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.HUGGINGFACE,
)
response = await client.post(api_base, headers=headers, data=json.dumps(data))