Tutorial Overview

Welcome to the LazyLLM tutorials!

This series helps you get started quickly and dive deep into every LazyLLM capability.

Tutorial Catalog

From Data to LLM

• From Data to LLM The English version will be published later. You can read the Chinese version first.

LazyLLM RAG Tutorials

• Chapter 1: Understanding the Principles of RAG — Making Retrieval-Augmented Generation No Longer a Black Box
  A thorough breakdown of RAG fundamentals and architecture.

• Chapter 2: Build a Minimal RAG System in 10 Minutes
  Build a minimal but working RAG system from scratch in minutes.

• Chapter 3: How Large Models Work — Understanding Call Logic and Prompt Engineering with LazyLLM
  Understand how LLM calls flow and how to structure prompts effectively.

• Chapter 4: Engineering Your First RAG Project — From Scripts to Modular and Maintainable Systems
  Learn to evolve RAG scripts into modular, maintainable projects.

• Chapter 5: Building Custom Reader Components — Easily Parse HTML, PDF, and Other Complex Document Formats
  Customize document readers to handle HTML, PDF, and more.

• Chapter 6: Retrieve with Higher Accuracy — Core Logic and Techniques for Improving RAG Recall Performance
  Learn the levers behind recall quality and how to optimize them.

• Chapter 7: Retrieval Upgrade in Practice — Build a “Smarter” Document Understanding System Yourself!
  Hands-on techniques to boost document understanding in practice.

• Chapter 8: Beyond Cosine — Matching Strategies Determine the Quality of Your Retrieval
  Compare vector matching strategies beyond cosine and when to use each.

• Chapter 9: Fine-Tuning in Practice — Help Large Models and Embedding Models Better Understand Your Domain
  Fine-tune embeddings and LLMs with your domain data.

• Chapter 10: Exploring Deepseek: Building a RAG system with stronger reasoning abilities
  Integrate DeepSeek-class models to strengthen multi-step reasoning.

• Chapter 11: Performance Optimization Guide: From cold start to responsive acceleration of your RAG
  End-to-end techniques for faster cold start and response latency.

• Chapter 12: Practice: Accelerate your RAG with caching, asynchronous and vector engines
  Accelerate RAG with caching, async workflows, and vector engines.

• Chapter 13: RAG + Multimodal — A Q&A System That Handles Images and Tables Alike
  Build multimodal RAG that digests images, tables, and text together.

• Chapter 14: Practical Session - Building a RAG System That Supports Complex Academic Paper Question Answering
  Craft paper-focused QA with structure-aware, context-rich retrieval.

• Chapter 15: Big Perspective Q&A: How does RAG support cross-document and cross-dimensional summarization?
  Support cross-document summaries and multi-dimensional QA.

• Chapter 16: Create a RAG system for paper Q&A with macro Q&A and chart generation functions
  Add macro summaries and chart generation for richer paper QA.

• Chapter 17: a full-link solution for permissions, sharing and content security
  Full-stack enterprise practices for access control and content safety.

• Chapter 18 High-level RAG: Agentic RAG
  Blend agents with RAG to orchestrate stronger task execution.

• Chapter 19: Advanced RAG — Knowledge-Graph-Based RAG
  Fuse knowledge graphs with generative QA for precise recall.

---

Ready to explore? Click any lecture to dive in 🚀