Course Wiki

Module 1: Agentic RAG — LLM Zoomcamp

Lessons, materials, and key concepts for module 1 of LLM Zoomcamp.

LLM Zoomcamp > Module 1: Agentic RAG

Module 1: Agentic RAG

In this module, we learn what LLMs are and build a simple RAG pipeline using keyword search. Then we make it agentic, so the LLM decides when and what to search instead of running a fixed pipeline.

Code: code/

Part 1: RAG

The first 10 lessons walk through building a working RAG pipeline from scratch with keyword search.

1. Introduction - What we’ll build and why
2. Environment Setup - Python, uv, OpenAI API
3. What is RAG - Why LLMs need context, the RAG architecture
4. The Course FAQ Dataset - Fetching and exploring the FAQ data
5. Search - Building a search en

Lessons

Key concepts

• RAG
• Agentic RAG
• Neural Networks
• Prompt Engineering
• OpenAI API
• Docker
• Vector Search
• Jupyter Notebooks
• Elasticsearch
• Gradient Boosting
• Keyword Search
• scikit-learn
• LLM Evaluation
• Function Calling
• LangChain
• Workflow Orchestration

Homework and deadlines live in the course repository: llm-zoomcamp.

Other modules in this course

• Module 2: Vector Search
• Module 3: Orchestration
• Module 4: Evaluation
• Module 5: Monitoring
• Module 6: Best Practices
• Module 7: End-to-End Project