AI Tutorials

Practical AI tutorials for developers

Learn AI through focused tutorials covering inference, local assistants, RAG apps, prompt workflows, model selection, and production deployment. This hub is ready to grow as you add more AI tutorials.

RAG TrackStep by step

Complete RAG Tutorial for Developers

Learn retrieval-augmented generation from beginner concepts to production: chunking, embeddings, vector databases, retrieval, prompts, citations, code examples, RAGAS evaluation, and deployment.

Open tutorial
GPU Track7 lessons

GPU Tutorial for AI Developers

Learn GPU hardware, memory hierarchy, execution, CUDA basics, and framework layers that shape AI performance.

Open tutorial
FoundationalFull course

AI Inference Tutorial

A chapter-based learning path for serving models, choosing hardware, understanding runtimes, and moving toward production inference.

Open tutorial
Hands-on10 min read

Build a Local AI Assistant on an 8GB GPU

Create a practical local assistant with conservative memory settings, clear scope, and realistic quality checks.

Open tutorial
Project10 min read

Deploy a Small RAG App End-to-End

Build a small retrieval app with clean ingestion, tuned retrieval, grounded answers, and production monitoring basics.

Open tutorial

GPU tutorial

Learn GPUs for AI workloads

Follow the GPU learning path when you want to understand VRAM limits, throughput, CUDA execution, and why different models behave differently on real hardware.

Open GPU hub

Start with inference

Learn how model serving works before choosing providers, GPUs, or deployment frameworks.

Build real AI apps

Move from concepts to small projects such as local assistants, RAG apps, and prompt-driven workflows.

Make better decisions

Use tutorials alongside model comparison, GPU planning, and deployment checklists.

All AI tutorials

Tutorial library

View all guides