Chapter 5: AI as a Service (Model → API using Django)

This chapter introduces one of the most important real-world AI concepts:
AI as a Service.
In production systems, AI models are not used directly — they are deployed as
services (APIs) that applications, websites, mobile apps, and systems can access.

Using Django, we build production-grade AI services that are scalable, secure, and enterprise-ready.
Real AI is not notebooks — it is API-driven system architecture.

⭐ What is AI as a Service?

• AI model runs on server
• Model exposed via API
• Systems send data
• AI processes input
• API returns prediction

⭐ AI Service Architecture (Django)

Client/App → Django API → AI Model → Decision Logic → JSON Response

⭐ Why Django for AI Services?

• Production security
• Scalable architecture
• User management
• API authentication
• Database integration
• Enterprise deployment

⭐ Basic Django AI API Example

Simple AI API using Django views:

# views.py
from django.http import JsonResponse
from django.views.decorators.csrf import csrf_exempt
import json

@csrf_exempt
def ai_predict(request):
    if request.method == "POST":
        data = json.loads(request.body)
        value = data.get("value")

        processed = value * 2 + 10

        if processed > 100:
            decision = "Approved"
        else:
            decision = "Review"

        return JsonResponse({"decision": decision})

⭐ Django URL Mapping

# urls.py
from django.urls import path
from .views import ai_predict

urlpatterns = [
    path("predict/", ai_predict),
]

⭐ Testing the API

POST /predict/
{
  "value": 30
}

Response:

{
  "decision": "Approved"
}

⭐ Model-Based Django AI Service

Serving a trained AI model using Django:

# views.py
import tensorflow as tf
import numpy as np
from django.http import JsonResponse
from django.views.decorators.csrf import csrf_exempt
import json

model = tf.keras.models.load_model("model.h5")

@csrf_exempt
def model_predict(request):
    if request.method == "POST":
        data = json.loads(request.body)
        values = data.get("data")

        arr = np.array(values).reshape(1, -1)
        pred = model.predict(arr)[0][0]

        return JsonResponse({"prediction": float(pred)})

⭐ AI Microservice Concept (Django)

• One AI service per app
• Modular AI architecture
• Independent deployment
• Scalable services
• Enterprise system design

⭐ AI Service Pipeline

Data → Django API → AI Model → Logic → API Response → System Action

⭐ Mini Practical Task

Build a Django AI API that:

• Accepts JSON input
• Processes data
• Applies AI logic
• Returns JSON output

# views.py
@csrf_exempt
def risk_api(request):
    if request.method == "POST":
        data = json.loads(request.body)
        score = data.get("score")

        risk = score * 3

        if risk > 150:
            result = "High Risk"
        else:
            result = "Low Risk"

        return JsonResponse({"risk_level": result})

📌 Chapter Outcome

• Build AI services with Django
• Create AI APIs
• Deploy AI models as services
• Design AI microservices
• Integrate AI into real systems

📌 Core Principle

Models live in servers.
APIs bring AI to the world.
Django turns AI into enterprise systems.