Getting Started

Welcome to AI Engineering Projects. This platform provides hands-on tutorials for building production-ready AI systems.

Prerequisites

Before starting any project, ensure you have:

• Python 3.10+ installed
• Git for version control
• A code editor (VS Code recommended)
• Basic understanding of Python and APIs

Environment Setup

1. Install UV (Recommended)

UV is a fast Python package manager:

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Get API Keys

Most projects require an OpenAI API key:

1. Go to platform.openai.com
2. Create an account and add credits
3. Generate an API key
4. Store it securely in .env files

3. Choose Your Path

Select a learning path based on your goals:

Project Structure

Each project follows a consistent structure:

project-name/
├── src/           # Source code
├── tests/         # Test files
├── data/          # Sample data
├── .env           # Environment variables
└── README.md      # Project documentation

Difficulty Levels

Projects are organized by complexity:

Frequently Asked Questions

What is AI Engineering?

AI Engineering is the discipline of building production-ready AI systems. It combines machine learning knowledge with software engineering practices to create reliable, scalable AI applications. This includes RAG systems, LLM applications, AI agents, embeddings, and the infrastructure to deploy and monitor them.

Do I need machine learning experience to start?

No. These tutorials are designed for software engineers who want to build AI applications. You'll learn to use pre-trained models and APIs (OpenAI, LangChain, etc.) rather than training models from scratch. Basic Python knowledge is sufficient to start.

How much does it cost to follow these tutorials?

Most beginner projects cost under $1 in API fees. You can use OpenAI's GPT-4o-mini (very affordable) or free local models with Ollama. Our Small Language Models section covers running AI completely free on your laptop.

What's the best project to start with?

For most people, start with Intelligent Document Q&A. It teaches the RAG pattern - the most practical AI technique used in production today. If you prefer chatbots, try the Chatbot project.

Can I run AI models locally without API costs?

Yes. Our Small Language Models section teaches you to run models like Llama, Phi-3, and Gemma locally using Ollama. You can build complete applications without any API costs.

What's the difference between RAG and AI Agents?

RAG (Retrieval-Augmented Generation) retrieves relevant documents to answer questions from your data. AI Agents can take actions - they use tools, call APIs, and execute multi-step workflows autonomously. Many production systems combine both: agents that use RAG to access knowledge.

Next Steps

Ready to build? Start with the Intelligent Document Q&A project - our most popular beginner tutorial.