explaingit

patchy631/ai-engineering-hub

★ 35,093Jupyter NotebookAudience · developerComplexity · 3/5ActiveLicenseSetup · moderate

TLDR

A collection of 90+ runnable tutorial projects teaching how to build real AI applications with language models, RAG systems, and AI agents, organized by difficulty level.

Mindmap

mindmap
  root((repo))
    What it does
      90+ tutorial projects
      LLM applications
      RAG systems
      AI agents
    Project types
      ChatGPT clones
      Document chat
      Multi-agent workflows
      Audio and video AI
      Model fine-tuning
      API deployment
    Tech stack
      Python
      LlamaIndex
      LangChain
      Ollama
      Vector databases
    Learning path
      Beginner projects
      Intermediate projects
      Advanced projects
    Format
      Jupyter Notebooks
      Runnable code
      Interactive learning

Things people build with this

USE CASE 1

Build a local ChatGPT clone using open-source models like Llama or Gemma that you can run on your own machine.

USE CASE 2

Create a document chat system that lets users ask questions about uploaded files using RAG to retrieve relevant context.

USE CASE 3

Set up multi-agent workflows where AI agents collaborate to solve complex tasks using frameworks like CrewAI.

USE CASE 4

Deploy an AI application as an API endpoint that other services can call to get AI-powered responses.

Tech stack

PythonJupyter NotebookLlamaIndexLangChainOllamaCrewAIAutoGenQdrant

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Python environment setup and downloading/running local LLM via Ollama or configuring API keys for external services.

Use freely for any purpose including commercial, as long as you keep the copyright notice.

In plain English

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.

Copy-paste prompts

Prompt 1
I want to build a chatbot that uses my own documents. Which project in this repo should I start with and what are the key steps?
Prompt 2
Show me how to set up a local LLM using Ollama and connect it to a Python application using LangChain.
Prompt 3
I need to create a multi-agent system where agents can call external tools. Which CrewAI or AutoGen example should I study first?
Prompt 4
Walk me through the RAG project to understand how to retrieve relevant document chunks and pass them to an LLM for better answers.
Prompt 5
How do I take one of these Jupyter notebook projects and turn it into a production API I can deploy?
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.