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

fix get_async_httpx_client

Browse source
This commit is contained in:
Ishaan Jaff 2024-11-21 10:26:18 -08:00
parent 398e6d0ac6
commit 89d76d1eb7
2 changed files with 14 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
litellm/llms/openai_like/embedding/handler.py
View file

@ -45,7 +45,10 @@ class OpenAILikeEmbeddingHandler(OpenAILikeBase):
response = None
try:
if client is None or isinstance(client, AsyncHTTPHandler):
self.async_client = AsyncHTTPHandler(timeout=timeout) # type: ignore
self.async_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.OPENAI,
params={"timeout": timeout},
)
else:
self.async_client = client

12
litellm/llms/vertex_ai_and_google_ai_studio/gemini_embeddings/batch_embed_content_handler.py
View file

@ -7,8 +7,13 @@ from typing import Any, List, Literal, Optional, Union
import httpx
import litellm
from litellm import EmbeddingResponse
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.openai import EmbeddingInput
from litellm.types.llms.vertex_ai import (
VertexAIBatchEmbeddingsRequestBody,
@ -150,7 +155,10 @@ class GoogleBatchEmbeddings(VertexLLM):
else:
_params["timeout"] = httpx.Timeout(timeout=600.0, connect=5.0)
async_handler: AsyncHTTPHandler = AsyncHTTPHandler(**_params) # type: ignore
async_handler: AsyncHTTPHandler = get_async_httpx_client(
llm_provider=litellm.LlmProviders.VERTEX_AI,
params={"timeout": timeout},
)
else:
async_handler = client # type: ignore