Ray serve integrations

# 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()

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"]

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

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

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())