Generative AI Masterclass: Real-World Applications

The GenAI App with Python & API Lab introduces learners to the fundamentals of building intelligent applications using Large Language Models (LLMs) through API integration. Designed for complete beginners, this lab provides hands-on experience in connecting Python applications to a Generative AI API and building a functional command-line assistant.

Through guided exercises, students learn how to:

• Configure a Python development environment

• Safely manage and use API keys

• Connect to a GenAI service provider using Python

• Send prompts and parameters to an AI model

• Receive and display AI-generated responses in real time

By constructing a simple yet powerful command-line AI assistant, learners gain practical skills in prompt engineering, API request/response handling, and interactive application design. This lab lays the foundation for more advanced AI development topics, including chat interfaces, automation workflows, AI agents, and backend integration.

The project serves as an ideal starting point for students who want to understand how modern AI systems are embedded into real-world applications—from chatbots to virtual assistants to AI-driven productivity tools.

The Retrieval-Augmented Generation (RAG) Lab provides learners with a practical, beginner-friendly introduction to building AI systems that can answer questions using custom data. In this hands-on lab, participants learn how modern AI assistants retrieve relevant information from documents and generate accurate, context-aware responses.

The lab walks students through the complete RAG workflow:

• Document ingestion using Python

• Text chunking to break large content into manageable sections

• Semantic embeddings using Sentence Transformer

• Similarity search with cosine similarity to identify the most relevant chunks

• Context-driven generation using an LLM (Groq Llama model or equivalent)

By completing this lab, learners gain foundational experience in how real-world AI search tools, enterprise knowledge assistants, and contextual chatbots are built. The Mini RAG pipeline created in this exercise demonstrates how to combine embeddings and LLMs to produce accurate answers grounded in user-provided documents.

This lab serves as a practical gateway into more advanced RAG topics, such as vector databases, multi-document retrieval, PDF ingestion, and full-stack AI assistant development.

This lab provides a hands-on introduction to AI-driven image generation and multimodal content creation. Students will learn how to craft effective prompts, generate and refine visual assets, compare design variations, and integrate text-based outputs to produce cohesive marketing-ready materials. Using Canva AI, participants will complete a full workflow—from concept to final image–caption deliverables.