Skip to main content

Xorbits Inference (Xinference)

Xinference is a powerful and versatile library designed to serve LLMs, speech recognition models, and multimodal models, even on your laptop. It supports a variety of models compatible with GGML, such as chatglm, baichuan, whisper, vicuna, orca, and many others. This notebook demonstrates how to use Xinference with LangChain.


Install Xinference through PyPI:

%pip install --upgrade --quiet  "xinference[all]"

Deploy Xinference Locally or in a Distributed Cluster.​

For local deployment, run xinference.

To deploy Xinference in a cluster, first start an Xinference supervisor using the xinference-supervisor. You can also use the option -p to specify the port and -H to specify the host. The default port is 9997.

Then, start the Xinference workers using xinference-worker on each server you want to run them on.

You can consult the README file from Xinference for more information.


To use Xinference with LangChain, you need to first launch a model. You can use command line interface (CLI) to do so:

!xinference launch -n vicuna-v1.3 -f ggmlv3 -q q4_0
Model uid: 7167b2b0-2a04-11ee-83f0-d29396a3f064

A model UID is returned for you to use. Now you can use Xinference with LangChain:

from langchain_community.llms import Xinference

llm = Xinference(
server_url="", model_uid="7167b2b0-2a04-11ee-83f0-d29396a3f064"

prompt="Q: where can we visit in the capital of France? A:",
generate_config={"max_tokens": 1024, "stream": True},

API Reference:

' You can visit the Eiffel Tower, Notre-Dame Cathedral, the Louvre Museum, and many other historical sites in Paris, the capital of France.'

Integrate with a LLMChain​

from langchain.chains import LLMChain
from langchain_core.prompts import PromptTemplate

template = "Where can we visit in the capital of {country}?"

prompt = PromptTemplate.from_template(template)

llm_chain = LLMChain(prompt=prompt, llm=llm)

generated ="France")

A: You can visit many places in Paris, such as the Eiffel Tower, the Louvre Museum, Notre-Dame Cathedral, the Champs-ElysΓ©es, Montmartre, SacrΓ©-CΕ“ur, and the Palace of Versailles.

Lastly, terminate the model when you do not need to use it:

!xinference terminate --model-uid "7167b2b0-2a04-11ee-83f0-d29396a3f064"

Help us out by providing feedback on this documentation page: