Yuan2.0

from langchain.chains import LLMChain
from langchain_community.llms.yuan2 import Yuan2

# default infer_api for a local deployed Yuan2.0 inference server
infer_api = "http://127.0.0.1:8000/yuan"

# direct access endpoint in a proxied environment
# import os
# os.environ["no_proxy"]="localhost,127.0.0.1,::1"

yuan_llm = Yuan2(
    infer_api=infer_api,
    max_tokens=2048,
    temp=1.0,
    top_p=0.9,
    use_history=False,
)

# turn on use_history only when you want the Yuan2.0 to keep track of the conversation history
# and send the accumulated context to the backend model api, which make it stateful. By default it is stateless.
# llm.use_history = True

question = "请介绍一下中国。"

print(yuan_llm.invoke(question))