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

* 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 7c595e770c
commit aa6b133557
26 changed files with 288 additions and 62 deletions

View file

@ -11,7 +11,11 @@ import requests # type: ignore
import litellm
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
from litellm.llms.custom_httpx.http_handler import (
AsyncHTTPHandler,
HTTPHandler,
get_async_httpx_client,
)
from litellm.types.llms.bedrock import CohereEmbeddingRequest
from litellm.utils import Choices, Message, ModelResponse, Usage
@ -71,7 +75,10 @@ async def async_embedding(
)
## COMPLETION CALL
if client is None:
client = AsyncHTTPHandler(concurrent_limit=1, timeout=timeout)
client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.COHERE,
params={"timeout": timeout},
)
try:
response = await client.post(api_base, headers=headers, data=json.dumps(data))