AI Backend System Design & Implementation
- 5 minutes ago
- 5 min read
Course: AI Backend Engineering with FastAPI
Assignment Type: Applied Project Assignment
Difficulty Level: Medium → Advanced
Estimated Time: 12–18 hours
Submission Mode: Online LMS (Moodle / Canvas / Blackboard)
Assignment Context
Modern AI systems rarely consist of a single model endpoint. Instead, they involve multiple components working together such as:
API orchestration
model inference
retrieval systems
asynchronous processing
background workflows
logging and monitoring
In this assignment, you will design and implement a mini AI backend platform that integrates several of these components.
The purpose is to help you apply architectural thinking and implement production-style patterns that were discussed throughout the course.
Assignment Objective
The objective of this assignment is to build a multi-endpoint AI service that demonstrates the ability to:
structure backend systems using modular architecture
handle synchronous and asynchronous AI workloads
integrate retrieval pipelines
manage long-running processes
provide observable and maintainable APIs
Your system should resemble a simplified AI backend microservice.
Expected System Overview
Students must build a FastAPI-based backend that supports the following capabilities:
Conversational AI endpoint
Document retrieval endpoint
Streaming response endpoint
Background processing task
Monitoring/logging functionality
All components should work together as part of a single coherent backend system.
Functional Requirements
Your backend must implement at least four endpoints described below.
Chat Endpoint
Endpoint
POST /chat
Purpose
Handle conversational interactions with an AI model.
Required Behavior
The endpoint must:
accept a structured message format
validate request input using Pydantic
call an LLM service
return a generated response
Example Request
{
"messages": [
{"role": "user", "content": "What is FastAPI?"}
],
"temperature": 0.7
}
Example Response
{
"response": "FastAPI is a modern Python framework..."
}
Streaming Endpoint
Endpoint
POST /chat/stream
Purpose
Deliver responses progressively rather than all at once.
Required Behavior
The endpoint should:
generate tokens or words gradually
return a StreamingResponse
demonstrate asynchronous streaming behavior
The response should visibly stream output when tested in the browser or via API clients.
Retrieval Endpoint
Endpoint
GET /retrieve
Purpose
Simulate a retrieval system used in Retrieval-Augmented Generation (RAG).
Expected Behavior
The endpoint should:
accept a query parameter
return a list of retrieved documents
simulate vector search behavior
Example response:
{
"documents": [
"FastAPI is a high-performance web framework",
"RAG combines retrieval and generation"
]
}
The retrieval logic may be mocked or implemented using static documents.
Background Processing Endpoint
Endpoint
POST /process
Purpose
Trigger a long-running task.
Requirements
The endpoint must:
start a background task
immediately return a response to the client
execute the job asynchronously
Example use cases include:
document indexing
embedding generation
data analysis
Use: BackgroundTasks to implement the processing.
System Design Requirements
Students must organize their project using a layered architecture.
Required components include:
Routers
Handle HTTP interactions.
Example:
app/routers/
Services
Contain business logic and AI processing.
Example:
app/services/
Schemas
Define request and response models.
Example:
app/schemas/
Core utilities
Contain reusable functionality such as:
logging
configuration
middleware
Example:
app/core/
Logging and Monitoring
Your system must include logging functionality.
Logs should capture:
request start
request completion
errors
background job activity
A middleware-based logging system is recommended.
Async Programming Requirements
At least one endpoint must use asynchronous processing.
Examples include:
LLM service call
streaming endpoint
external API simulation
Use:
async def
await
appropriately where required.
Testing the System
Students should verify that the system works correctly using:
FastAPI Swagger UI (/docs)
Postman or similar API clients
browser testing for streaming responses
Evidence of testing should be included in the submission.
Implementation Guidelines
Students should follow these best practices:
Code Organization
avoid placing all logic in main.py
separate routers and services
keep functions small and focused
Naming Conventions
Use descriptive names for:
endpoints
services
functions
variables
Documentation
Add comments where necessary to explain important logic.
Project Deliverables
Students must submit the following materials.
Source Code
Upload a complete project folder containing all files.
Required structure:
project/
app/
routers/
services/
schemas/
core/
main.py
Compress the folder before submission.
README Documentation
The project must include a README.md file containing:
project overview
system architecture explanation
instructions to run the API
example API calls
Execution Evidence
Include screenshots showing:
API server running
Swagger documentation page
successful endpoint responses
streaming output
background task logs
Short Reflection Report
Students must submit a short document (1 page) explaining:
challenges faced
design decisions made
possible improvements
Submission Format
Submit a ZIP archive containing:
StudentID_AI_Backend_Project.zip
The archive should include:
project_code/
screenshots/
reflection.pdf
Upload the file through the LMS submission portal.
Assessment Criteria
Student submissions will be evaluated using the following criteria.
Category | Marks |
System Architecture | 20 |
API Endpoint Functionality | 25 |
Streaming Implementation | 15 |
Background Task Implementation | 15 |
Code Quality | 10 |
Documentation | 10 |
Testing Evidence | 5 |
Total Marks: 100
Important Guidelines
Students should:
start early
test each endpoint individually
focus on architecture rather than complexity
Do not attempt to implement unnecessary features beyond the scope unless seeking bonus credit.
Bonus Opportunities (Optional)
Students may earn additional marks for implementing:
authentication middleware
request rate limiting
real LLM integration
vector database integration
Celery task queue
Academic Integrity
All submitted work must be your own implementation.
Students may consult:
official documentation
course materials
reference resources
However, direct copying from external repositories is not allowed.
Instructor Notes
Students should treat this assignment as a mini production system design exercise, not just a coding task.
Focus on:
modularity
clarity
maintainability
Call to Action
Ready to transform your business with AI-powered intelligence that accelerates insights, enhances decision-making, and unlocks the full value of your data?
Codersarts is here to help you turn complex data workflows into efficient, scalable, and evidence-driven AI systems that empower teams to make smarter, faster, and more confident decisions.
Whether you’re a startup looking to build AI-driven products, an enterprise aiming to optimize operations through data science, or a research organization advancing innovation with intelligent data solutions, we bring the expertise and experience needed to design, develop, and deploy impactful AI systems that drive measurable business outcomes.
Get Started Today
Schedule an AI & Data Science Consultation:
Book a 30-minute discovery call with our AI strategists and data science experts to discuss your challenges, identify high-impact opportunities, and explore how intelligent AI solutions can transform your workflows and performance.
Request a Custom AI Demo:
Experience AI in action with a personalized demonstration built around your business use cases, datasets, operational environment, and decision workflows — showcasing practical value and real-world impact.
Email: contact@codersarts.com
Transform your organization from data accumulation to intelligent decision enablement — accelerating insight generation, improving operational efficiency, and strengthening competitive advantage.
Partner with Codersarts to build scalable AI solutions including RAG systems, predictive analytics platforms, intelligent automation tools, recommendation engines, and custom machine learning models that empower your teams to deliver exceptional results.
Contact us today and take the first step toward next-generation AI and data science capabilities that grow with your business ambitions.
Comments