patchy631/ai-engineering-hub

AI Engineering Hub is a collection of over 90 practical tutorial projects organized by difficulty, aimed at developers who want to learn how to build real applications with large language models, RAG (Retrieval-Augmented Generation) systems, and AI agents. The problem it addresses is that AI engineering is a rapidly evolving field where the gap between understanding concepts and knowing how to actually build something useful is large. This repository provides concrete, runnable examples that bridge that gap. Each project is a standalone folder containing Jupyter notebooks and supporting code you can clone and run locally. Projects span a wide range of applications: building a local ChatGPT clone using open models like Llama or Gemma, creating a document chat system using RAG, building multi-agent workflows with frameworks like CrewAI and AutoGen, processing audio and video with AI, calling external tools via the Model Context Protocol (a standard way for AI models to use external services), fine-tuning language models for specific tasks, and deploying AI applications as APIs. Projects are grouped into beginner, intermediate, and advanced tiers so you can start at an appropriate level. The tech stack varies by project but relies heavily on Python and popular AI libraries including LlamaIndex, LangChain, Ollama (for running local models), vector databases like Qdrant and Milvus, and various model providers. Jupyter Notebooks are the primary format, which means you can run each step interactively and see outputs as you go. You would use this repository when you want a concrete, working starting point for an AI feature, something you can run, inspect, and modify rather than read a theoretical tutorial. It is particularly useful for developers transitioning from traditional software development into AI-augmented application development.