langchain/docs/extras/integrations/providers/xinference.mdx
Jiayi Ni 1efb9bae5f
FEAT: Integrate Xinference LLMs and Embeddings (#8171)
- [Xorbits
Inference(Xinference)](https://github.com/xorbitsai/inference) is a
powerful and versatile library designed to serve language, speech
recognition, and multimodal models. Xinference supports a variety of
GGML-compatible models including chatglm, whisper, and vicuna, and
utilizes heterogeneous hardware and a distributed architecture for
seamless cross-device and cross-server model deployment.
- This PR integrates Xinference models and Xinference embeddings into
LangChain.
- Dependencies: To install the depenedencies for this integration, run
    
    `pip install "xinference[all]"`
    
- Example Usage:

To start a local instance of Xinference, run `xinference`.

To deploy Xinference in a distributed cluster, first start an Xinference
supervisor using `xinference-supervisor`:

`xinference-supervisor -H "${supervisor_host}"`

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

`xinference-worker -e "http://${supervisor_host}:9997"`

To use Xinference with LangChain, you also need to launch a model. You
can use command line interface (CLI) to do so. Fo example: `xinference
launch -n vicuna-v1.3 -f ggmlv3 -q q4_0`. This launches a model named
vicuna-v1.3 with `model_format="ggmlv3"` and `quantization="q4_0"`. A
model UID is returned for you to use.

Now you can use Xinference with LangChain:

```python
from langchain.llms import Xinference

llm = Xinference(
    server_url="http://0.0.0.0:9997", # suppose the supervisor_host is "0.0.0.0"
    model_uid = {model_uid} # model UID returned from launching a model
)

llm(
    prompt="Q: where can we visit in the capital of France? A:",
    generate_config={"max_tokens": 1024},
)
```

You can also use RESTful client to launch a model:
```python
from xinference.client import RESTfulClient

client = RESTfulClient("http://0.0.0.0:9997")

model_uid = client.launch_model(model_name="vicuna-v1.3", model_size_in_billions=7, quantization="q4_0")
```

The following code block demonstrates how to use Xinference embeddings
with LangChain:
```python
from langchain.embeddings import XinferenceEmbeddings

xinference = XinferenceEmbeddings(
    server_url="http://0.0.0.0:9997",
    model_uid = model_uid
)
```

```python
query_result = xinference.embed_query("This is a test query")
```

```python
doc_result = xinference.embed_documents(["text A", "text B"])
```

Xinference is still under rapid development. Feel free to [join our
Slack
community](https://xorbitsio.slack.com/join/shared_invite/zt-1z3zsm9ep-87yI9YZ_B79HLB2ccTq4WA)
to get the latest updates!

- Request for review: @hwchase17, @baskaryan
- Twitter handle: https://twitter.com/Xorbitsio

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-27 21:23:19 -07:00

102 lines
2.5 KiB
Plaintext

# Xorbits Inference (Xinference)
This page demonstrates how to use [Xinference](https://github.com/xorbitsai/inference)
with LangChain.
`Xinference` is a powerful and versatile library designed to serve LLMs,
speech recognition models, and multimodal models, even on your laptop.
With Xorbits Inference, you can effortlessly deploy and serve your or
state-of-the-art built-in models using just a single command.
## Installation and Setup
Xinference can be installed via pip from PyPI:
```bash
pip install "xinference[all]"
```
## LLM
Xinference supports various models compatible with GGML, including chatglm, baichuan, whisper,
vicuna, and orca. To view the builtin models, run the command:
```bash
xinference list --all
```
### Wrapper for Xinference
You can start a local instance of Xinference by running:
```bash
xinference
```
You can also deploy Xinference in a distributed cluster. To do so, first start an Xinference supervisor
on the server you want to run it:
```bash
xinference-supervisor -H "${supervisor_host}"
```
Then, start the Xinference workers on each of the other servers where you want to run them on:
```bash
xinference-worker -e "http://${supervisor_host}:9997"
```
You can also start a local instance of Xinference by running:
```bash
xinference
```
Once Xinference is running, an endpoint will be accessible for model management via CLI or
Xinference client.
For local deployment, the endpoint will be http://localhost:9997.
For cluster deployment, the endpoint will be http://${supervisor_host}:9997.
Then, you need to launch a model. You can specify the model names and other attributes
including model_size_in_billions and quantization. You can use command line interface (CLI) to
do it. For example,
```bash
xinference launch -n orca -s 3 -q q4_0
```
A model uid will be returned.
Example usage:
```python
from langchain.llms import Xinference
llm = Xinference(
server_url="http://0.0.0.0:9997",
model_uid = {model_uid} # replace model_uid with the model UID return from launching the model
)
llm(
prompt="Q: where can we visit in the capital of France? A:",
generate_config={"max_tokens": 1024, "stream": True},
)
```
### Usage
For more information and detailed examples, refer to the
[example notebook for xinference](../modules/models/llms/integrations/xinference.ipynb)
### Embeddings
Xinference also supports embedding queries and documents. See
[example notebook for xinference embeddings](../modules/data_connection/text_embedding/integrations/xinference.ipynb)
for a more detailed demo.