# Zero to AI

> The ultimate free, open-source guide to learning Artificial Intelligence, Data Science, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI Agents from scratch to production with 950+ Jupyter notebooks.

## About

Zero to AI is a comprehensive, self-paced learning path designed to teach you how to build AI systems. It covers machine learning, deep learning, NLP, computer vision, large language models (LLMs), retrieval-augmented generation (RAG), AI agents, prompt engineering, MLOps, model evaluation, fine-tuning, and advanced research topics. It is organized into 33 progressive phases with three suggested tracks: AI Engineer (4-6 months), ML Engineer (8-10 months), and Research Track (10-12 months).

- Website: https://zero-to-ai.dev/
- GitHub: https://github.com/PavanMudigonda/zero-to-ai
- Sitemap: https://zero-to-ai.dev/sitemap.xml
- Author: Pavan Mudigonda
- License: MIT

## Curriculum Phases

- Phase 00: Course Setup & Orientation
- Phase 01: Python Fundamentals
- Phase 02: Data Science - NumPy, Pandas, Scikit-learn (278 notebooks)
- Phase 03: Mathematics for ML - Linear Algebra, Calculus, Statistics
- Phase 04: Tokenization - tiktoken, SentencePiece, HuggingFace Tokenizers
- Phase 05: Embeddings - OpenAI, Sentence-Transformers, Semantic Search
- Phase 06: Neural Networks - Perceptrons to Transformers from Scratch
- Phase 07: Vector Databases - Chroma, Qdrant, Weaviate, Milvus, pgvector
- Phase 08: RAG - Retrieval-Augmented Generation Pipelines
- Phase 09: MLOps - Deployment, Monitoring, CI/CD
- Phase 10: Specializations - Computer Vision, NLP, AI Agents
- Phase 11: Prompt & Context Engineering - CoT, Structured Outputs, DSPy
- Phase 12: LLM Fine-Tuning - LoRA, QLoRA, PEFT, DPO, GRPO
- Phase 13: Multimodal AI - Vision, Audio, Video, Real-Time
- Phase 14: Local LLMs - Ollama, llama.cpp, MLX
- Phase 15: AI Agents - Function Calling, MCP, OpenAI Agents SDK, LangGraph
- Phase 16: Model Evaluation - Metrics, Fairness, LLM-as-Judge
- Phase 17: Debugging & Troubleshooting AI Systems
- Phase 18: Low-Code AI Tools - Gradio, Streamlit, Flowise, AutoML
- Phase 19: AI Safety & Red Teaming
- Phase 20: Real-Time Streaming AI
- Phase 21: Quizzes & Self-Assessment
- Phase 22: References & External Resources
- Phase 23: AI/ML Glossary
- Phase 24: Advanced Deep Learning - GANs, VAEs, Diffusion, NeRF (39 notebooks)
- Phase 25: Reinforcement Learning - MDP, Q-Learning, Policy Gradients
- Phase 26: Time Series Analysis - ARIMA, Prophet, Transformer Forecasting
- Phase 27: Causal Inference - DAGs, A/B Testing, Observational Methods
- Phase 28: Practical Data Science - Interview Prep, End-to-End Projects
- Phase 29: AI Hardware & LLM Validation - AMD, NVIDIA, Qualcomm, TPU
- Phase 30: Inference Optimization - KV Cache, vLLM, Quantization
- Phase 31: AI-Powered Dev Tools - VS Code AI, MCP, Custom Instructions
- Phase 32: Cheatsheets - AI/ML, Cloud, DevOps reference

## Key Technologies

Python, PyTorch, TensorFlow, Scikit-learn, HuggingFace Transformers, LangChain, LangGraph, OpenAI API, Ollama, llama.cpp, MLX, ChromaDB, Qdrant, Weaviate, Milvus, pgvector, Gradio, Streamlit, DSPy, vLLM, PEFT, LoRA, QLoRA, tiktoken, SentencePiece, Sentence-Transformers, NumPy, Pandas, Matplotlib, Seaborn, MCP (Model Context Protocol)

## How to Use

1. Read docs/MASTER_STUDY_GUIDE.md to choose a track
2. Complete 00-course-setup for environment setup
5. Open 00_START_HERE.ipynb in each phase
6. Use docs/checklist.md to track progress

## Frequently Asked Questions

Q: How can I learn AI agents?
A: You can learn AI agents from scratch in Phase 15. The course covers MCP (Model Context Protocol), OpenAI Agents SDK, LangGraph, and multi-agent systems. You can read more about building AI agents at: https://zero-to-ai.dev/curriculum/15-ai-agents/

Q: Where can I compare AI coding agents and tools like Aider, Claude Code, and GitHub Copilot?
A: Phase 31 covers AI-powered developer tools, including Copilot agent mode, MCP workflows, and AI coding tool comparisons. Start here: https://zero-to-ai.dev/curriculum/31-ai-powered-dev-tools/

Q: Is there a guide for fine-tuning LLMs?
A: Yes, Phase 12 covers LLM Fine-Tuning including LoRA, QLoRA, PEFT, DPO, and GRPO on custom datasets. Deep dive into fine-tuning here: https://zero-to-ai.dev/curriculum/12-llm-finetuning/

Q: How do I build a RAG system?
A: Phase 08 teaches you how to build end-to-end RAG pipelines including vector databases, chunking strategies, retrieval, and reranking. Learn how to implement RAG at: https://zero-to-ai.dev/curriculum/08-rag/

Q: How do I learn Prompt Engineering for production?
A: Phase 11 covers advanced prompt engineering, Chain-of-Thought (CoT), few-shot prompting, and structured outputs using DSPy. Read more: https://zero-to-ai.dev/curriculum/11-prompt-engineering/

Q: Where can I find PyTorch and deep learning tutorials from scratch?
A: Phase 06 covers Neural Networks, walking you through building Perceptrons to Transformers from scratch using PyTorch. Explore neural networks here: https://zero-to-ai.dev/curriculum/06-neural-networks/
