// AI in Action

A hands-on, module-based curriculum for backend developers — from LLM fundamentals to production-ready systems

00. Modules

Module 01

How LLMs Work

Understand the engine: tokens, embeddings, the Transformer architecture, autoregressive generation, KV cache, and sampling strategies. Learn why these internals directly drive latency, cost, and architecture decisions.

tokens transformer attention streaming temperature
Module 02

Embeddings & Vector Search

Turn text into vectors, build semantic search, and implement a full RAG pipeline. Covers embedding models, FAISS, chunking strategies, cosine similarity, and the architecture behind every production RAG system.

embeddings FAISS cosine similarity chunking RAG
Module 03

Tool Use / Function Calling

Give LLMs the ability to call your APIs. Master the agentic loop, tool definitions, parallel tool calls, forced tool selection, and the security boundaries that make tool use safe in production.

agentic loop function calling tool_choice security multi-tool
Module 04

RAG — Retrieval-Augmented Generation

Ground LLMs in your own data. Build the full pipeline: document loading, chunking, embedding, vector search, prompt construction, and generation with citations. The pattern behind every production AI assistant.

RAG retrieval chunking grounding citations

01. Getting Started

# Clone and setup git clone <repo-url> learn-ai cd learn-ai # Create virtual environment python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate # Install all dependencies cp .env.example .env # add your ANTHROPIC_API_KEY pip install -r requirements.txt # Run any module cd 01-how-llms-work python app.py

02. Project Structure

learn-ai/ ├── .env.example # API key template ├── requirements.txt # All dependencies ├── styles.css # Shared design system ├── index.html # This page │ ├── 01-how-llms-work/ │ ├── index.html # Deep-dive guide │ └── app.py # Standalone demo │ ├── 02-embeddings-vector-search/ │ ├── index.html # Deep-dive guide │ ├── app.py # Standalone demo │ ├── chunking.py # Text chunking strategies │ └── vector_store.py # FAISS vector store │ ├── 03-tool-use/ │ ├── index.html # Deep-dive guide │ ├── app.py # Standalone demo │ └── tools.py # Tool definitions + implementations │ └── 04-rag/ ├── index.html # Deep-dive guide ├── app.py # Full RAG pipeline demo ├── chunking.py # Text chunking strategies ├── vector_store.py # FAISS vector store └── docs/ # Sample documents to index