用conda在本地创建虚拟环境安装和配置LangChain：
conda create --name langchain创建虚拟环境。
conda中安装langchain：conda install langchain -c conda-forge
但这只是安装上了langchain的主包，如果想要连上openai还需要安装集成包。
pip install langchain-openai
pip install langchain-community
更新下langchain到最新。
尝试下调用下Text模型：
from openai import OpenAI
client = OpenAI(
base_url='https://xiaoai.plus/v1',
# sk-xxx替换为自己的key
api_key='sk-xxx'
)
response = client.completions.create(
model="gpt-3.5-turbo-instruct",
temperature=0.5,
max_tokens=100,
prompt="请给我的花店起个名")
print(response)
尝试下调用Chat模型：
from openai import OpenAI
client = OpenAI(
base_url='https://xiaoai.plus/v1',
# sk-xxx替换为自己的key
api_key='sk-xxx'
)
response = client.chat.completions.create(
model="gpt-4",
messages=[
{"role": "system", "content": "You are a creative AI."},
{"role": "user", "content": "请给我的花店起个名"},
],
temperature=0.8,
max_tokens=60
)
print(response)
