LLM Agent Cookbook
Master the art of building production-ready LLM agents. This is a 4-week comprehensive course covering everything from basic ReAct patterns to advanced multi-agent orchestration.
Ready to start? Get Started → or jump right into Week 1
What You'll Learn
Prerequisites
- Basic Python programming experience
- Understanding of LLM concepts (prompts, tokens, API calls)
- Familiarity with Jupyter notebooks
Quick Start
# Clone the repository
git clone https://github.com/SOTAAZlab/LLM-Agent-Cookbook.git
cd LLM-Agent-Cookbook
# Create conda environment
conda create -n sotaaz python=3.11 -y
conda activate sotaaz
# Install dependencies
pip install -r requirements.txt
# Set up API keys
cp .env.example .env
# Edit .env and add your API keysArchitecture Overview
Course Structure
| Week | Focus | Key Technologies |
|---|---|---|
| 1 | Agent Basics | ReAct, Function Calling, Pydantic |
| 2 | Advanced Reasoning | RAG, LangGraph, CoT/ToT |
| 3 | Collaboration | CrewAI, MCP, A2A |
| 4 | Deployment | Guardrails, FastAPI, Docker |