Complete Google Cloud Run for ML Tutorial: Serverless ML Deployment

Google Cloud Run provides a serverless platform for deploying containerized ML models. It offers auto-scaling, pay-per-use pricing, and seamless integration with Google Cloud services.

Why Cloud Run for ML?

• Serverless: No infrastructure management
• Auto-scaling: Scale to zero and up automatically
• Cost-effective: Pay only for actual usage
• Container-based: Deploy any framework
• Fast deployment: Deploy in seconds

Prerequisites

pip install google-cloud-run flask gunicorn

gcloud auth login
gcloud config set project your-project-id

Quick Start

1. Create ML Service

# app.py
from flask import Flask, request, jsonify
import joblib
import numpy as np

app = Flask(name)

Load model on startup
model = joblib.load("model.joblib")

@app.route("/predict", methods=["POST"])
def predict():
    data = request.getjson()

    features = np.array(data["features"]).reshape(1, -1)
    prediction = model.predict(features)
    probability = model.predictproba(features)

    return jsonify({
        "prediction": int(prediction[0]),
        "probability": probability[0].tolist()
    })

@app.route("/health", methods=["GET"])
def health():
    return jsonify({"status": "healthy"})

if name == "main":
    app.run(host="0.0.0.0", port=8080)

2. Create Dockerfile

FROM python:3.9-slim

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY model.joblib .
COPY app.py .

ENV PORT=8080
EXPOSE 8080

CMD exec gunicorn --bind :$PORT --workers 1 --threads 8 app:app

3. requirements.txt

flask==2.3.0
gunicorn==21.2.0
joblib==1.3.0
scikit-learn==1.3.0
numpy==1.24.0

4. Deploy to Cloud Run

# Build container
gcloud builds submit --tag gcr.io/your-project/ml-service

Deploy
gcloud run deploy ml-service \
  --image gcr.io/your-project/ml-service \
  --platform managed \
  --region us-central1 \
  --memory 2Gi \
  --cpu 2 \
  --min-instances 0 \
  --max-instances 10 \
  --allow-unauthenticated

FastAPI Service

1. FastAPI Application

# main.py
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
import joblib
import numpy as np

app = FastAPI(title="ML Prediction API")

Load model
model = joblib.load("model.joblib")

class PredictionRequest(BaseModel):
    features: list[float]

class PredictionResponse(BaseModel):
    prediction: int
    probability: list[float]

@app.post("/predict", responsemodel=PredictionResponse)

async def predict(request: PredictionRequest):
    try:
        features = np.array(request.features).reshape(1, -1)
        prediction = model.predict(features)
        probability = model.predictproba(features)

        return PredictionResponse(
            prediction=int(prediction[0]),
            probability=probability[0].tolist()
        )
    except Exception as e:
        raise HTTPException(statuscode=400, detail=str(e))


@app.get("/health")
async def health():
    return {"status": "healthy"}

FROM python:3.9-slim

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY model.joblib .
COPY main.py .

ENV PORT=8080
EXPOSE 8080

CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080"]

# servepytorch.py
from flask import Flask, request, jsonify
import torch
import torch.nn as nn
import numpy as np

app = Flask(name)

class SimpleNN(nn.Module):