(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 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

View file

@ -12,6 +12,7 @@ sys.path.insert(0, os.path.abspath("../.."))
import litellm
from litellm import completion
from litellm.caching import InMemoryCache
litellm.num_retries = 3
litellm.success_callback = ["langfuse"]
@ -29,15 +30,20 @@ def langfuse_client():
f"{os.environ['LANGFUSE_PUBLIC_KEY']}-{os.environ['LANGFUSE_SECRET_KEY']}"
)
# use a in memory langfuse client for testing, RAM util on ci/cd gets too high when we init many langfuse clients
if _langfuse_cache_key in litellm.in_memory_llm_clients_cache:
langfuse_client = litellm.in_memory_llm_clients_cache[_langfuse_cache_key]
_cached_client = litellm.in_memory_llm_clients_cache.get_cache(_langfuse_cache_key)
if _cached_client:
langfuse_client = _cached_client
else:
langfuse_client = langfuse.Langfuse(
public_key=os.environ["LANGFUSE_PUBLIC_KEY"],
secret_key=os.environ["LANGFUSE_SECRET_KEY"],
host=None,
)
litellm.in_memory_llm_clients_cache[_langfuse_cache_key] = langfuse_client
litellm.in_memory_llm_clients_cache.set_cache(
key=_langfuse_cache_key,
value=langfuse_client,
)
print("NEW LANGFUSE CLIENT")