Ray serve 集成

使用 LangChain Python 与 Ray serve 集成。

Ray Serve 是一个可扩展的模型服务库，用于构建在线推理API。Serve尤其适用于系统组合，使您能够通过Python代码构建包含多个链和业务逻辑的复杂推理服务。

本笔记本的目标

本笔记本展示了一个将OpenAI链部署到生产环境的简单示例。您可将其扩展以部署自托管模型，并轻松定义运行模型所需的硬件资源（GPU和CPU），从而高效实现生产部署。更多选项（包括自动扩缩容）请参阅Ray Serve的 文档。

配置ray serve

安装ray pip install ray[serve]。

通用骨架

部署服务的通用骨架如下：

# 0: Import ray serve and request from starlette
from ray import serve
from starlette.requests import Request


# 1: Define a Ray Serve deployment.
@serve.deployment
class LLMServe:
    def __init__(self) -> None:
        # All the initialization code goes here
        pass

    async def __call__(self, request: Request) -> str:
        # You can parse the request here
        # and return a response
        return "Hello World"


# 2: Bind the model to deployment
deployment = LLMServe.bind()

# 3: Run the deployment
serve.api.run(deployment)

# Shutdown the deployment
serve.api.shutdown()

OpenAI链的部署示例（含自定义提示词）

从 OpenAI API密钥页面 获取OpenAI API密钥。运行以下代码将提示您提供API密钥。

from langchain_classic.chains import LLMChain
from langchain_core.prompts import PromptTemplate
from langchain_openai import OpenAI

from getpass import getpass

OPENAI_API_KEY = getpass()

@serve.deployment
class DeployLLM:
    def __init__(self):
        # We initialize the LLM, template and the chain here
        llm = OpenAI(openai_api_key=OPENAI_API_KEY)
        template = "Question: {question}\n\nAnswer: Let's think step by step."
        prompt = PromptTemplate.from_template(template)
        self.chain = LLMChain(llm=llm, prompt=prompt)

    def _run_chain(self, text: str):
        return self.chain(text)

    async def __call__(self, request: Request):
        # 1. Parse the request
        text = request.query_params["text"]
        # 2. Run the chain
        resp = self._run_chain(text)
        # 3. Return the response
        return resp["text"]

现在可以绑定部署。

# Bind the model to deployment
deployment = DeployLLM.bind()

当需要运行部署时，可指定端口号和主机地址。

# Example port number
PORT_NUMBER = 8282
# Run the deployment
serve.api.run(deployment, port=PORT_NUMBER)

服务已部署在端口 localhost:8282，此时可通过POST请求获取结果。

import requests

text = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
response = requests.post(f"http://localhost:{PORT_NUMBER}/?text={text}")
print(response.content.decode())

---

官方原文：src/oss/python/integrations/providers/ray_serve.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。