Langchain中如何调用GPT API代理？

[WangDuanqi]

代码如下：
“
from openai import OpenAI

client = OpenAI(
api_key="sk-xxx",
base_url="https://api.chatanywhere.tech/v1"
)

index = VectorstoreIndexCreator(
vectorstore_cls=DocArrayInMemorySearch
).from_loaders([loader])
”

bug如下：
“
Did not find openai_api_key, please add an environment variable OPENAI_API_KEY which contains it, or pass openai_api_key as a named parameter. (type=value_error)
”

[ChatAnywhere]

建议设置环境变量，参考python-openai官方库使用方法二

[WangDuanqi]

已更改调用API方式为环境变量，代码如下：
`import os
from openai import OpenAI
from langchain.indexes import VectorstoreIndexCreator
from dotenv import load_dotenv, find_dotenv

_ = load_dotenv(find_dotenv())

client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"),
base_url="https://api.chatanywhere.tech/v1"
)

index = VectorstoreIndexCreator(
vectorstore_cls=DocArrayInMemorySearch,
).from_loaders([loader])`

其中client可以正常使用，使用langchain的VectorstoreIndexCreator库时报连接异常错误，但是不能像client那样加入 base_url。这种情况有解决方案吗？

[ChatAnywhere]

你似乎搞错了
重点是要设置baseURL的环境变量的

[WangDuanqi]

已解决，感觉解答！