AI Engineering Hub

Active

GitHub Jupyter Notebook MIT

Description

In-depth tutorials on LLMs, RAGs and real-world AI agent applications. Rich notebook examples for learning AI engineering practices.

Key Features

93+ production-ready projects — Covering OCR, RAG, agents, voice, multimodal, and more
Three difficulty tiers — Beginner (22), intermediate (48), advanced (23) projects for progressive learning
LLM hands-on tutorials — Local deployment and applications with DeepSeek, Llama, Gemma, Qwen models
Agent workflow examples — Multi-framework agent implementations using CrewAI, AutoGen, MCP
Full RAG pipeline — Complete practice from basic RAG to Agentic RAG and multimodal RAG
Jupyter Notebook-based — Each project is a runnable notebook, ready to execute

Use Cases

💡 AI engineering beginners quickly get started with categorized projects

💡 Developers learn and compare different RAG/agent framework implementations

💡 Researchers reproduce and extend existing AI application cases

💡 Team internal training with a library of real project materials

Strengths & Limitations

✅ Strengths

• Actively maintained, recent updates
• High community interest (37.3k stars)
• Permissive open-source license (MIT)
• Responsive to issues, low backlog

Quick Start

git clone https://github.com/patchy631/ai-engineering-hub.git && cd ai-engineering-hub && pip install -r requirements.txt

Visit GitHub

Related Projects

txtai

12.9k · Python

Active A+

All-in-one AI framework for semantic search, LLM orchestration, and language model workflows with agent support, RAG, and vector database

semantic-searchragembeddings +4

· All-in-one AI framework for semantic search, LLM orchestration, and workflows
· Embeddings database combining vector indexes, graph networks, and relational DBs
· Multimodal embeddings for text, documents, audio, images, and video

View full details → View on GitHub

LangExtract

38.5k · Python

Active A+

A Python library by Google for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization, designed for data annotation and knowledge extraction workflows.

data-processingllmpython +2

· Precise source grounding — Every extraction maps to exact source text location with visual highlighting for traceability and verification
· Controlled structured outputs — Few-shot example enforced output schema, leveraging Gemini controlled generation for robust results
· Long document optimization — Text chunking, parallel processing, and multi-pass strategy to overcome needle-in-a-haystack challenges

View full details → View on GitHub

PromptTools

3.1k · Python

Stale B

PromptTools provides open-source tools for prompt testing and experimentation, supporting multiple LLMs (OpenAI, LLaMA) and vector databases (Chroma, Weaviate, LanceDB) to help developers systematically evaluate and optimize RAG systems.

prompt-testingragevaluation +3

· Open-source prompt testing and experimentation across multiple LLM providers
· Supports OpenAI, Anthropic, LLaMA, Mistral, Gemini, HuggingFace, and more
· Vector database evaluation: Chroma, Weaviate, Qdrant, LanceDB, Pinecone

View on GitHub

Docstrange

1.5k · Python