Add asynchronous generate interface

[TheSongg]

• PR title: [langchain_community.llms.xinference]: Add asynchronous generate interface

• PR message: The asynchronous generate interface support stream data and non-stream data.

    chain = prompt | llm
    async for chunk in chain.astream(input=user_input):
        yield chunk
  

• Add tests and docs:

   from langchain_community.llms import Xinference
   from langchain.prompts import PromptTemplate
  
   llm = Xinference(
   server_url="http://0.0.0.0:9997",  # replace your xinference server url
   model_uid={model_uid}  # replace model_uid with the model UID return from launching the model
       stream = True
        )
   prompt = PromptTemplate(input=['country'], template="Q: where can we visit in the capital of {country}? A:")
   chain = prompt | llm
   async for chunk in chain.astream(input=user_input):
       yield chunk
  

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
langchain	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Feb 27, 2025 2:46am

[ccurme]

How is authentication handled here?

[ccurme]

Does their client not support async calls?

[TheSongg]

Does their client not support async calls?

no，xinference client only support sync call. In addition, langchain_community.chat_models doesn't support xinference chat client.
https://github.com/xorbitsai/inference/blob/main/xinference/client/restful/restful_client.py

[TheSongg]

How is authentication handled here?

In fact, there was no authentication during initialization.
https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/llms/xinference.py