RAG (Retrieval-Augmented Generation) Tutorials

Advanced Chunking Strategies for RAG

Comparing fixed-size, recursive, semantic, agentic, and late chunking methods for optimal retrieval quality

Agentic RAG: When Retrieval Needs Reasoning

Building RAG agents that plan queries, route to tools, self-reflect, and iteratively refine answers with LangGraph and LlamaIndex Workflows

Building a RAG Pipeline from Scratch

From document ingestion to answer generation: chunking strategies, embedding models, vector stores, retrieval, and LLM synthesis with LlamaIndex and LangChain

Embedding Models and Reranking for RAG

Selecting, fine-tuning, and combining embedding models with cross-encoder rerankers for production retrieval pipelines

Evaluating RAG Systems

Metrics, frameworks, and automated evaluation for retrieval quality, generation faithfulness, and end-to-end RAG performance with RAGAS, DeepEval, and LangSmith

Fine-tuning RAG Components: Embeddings, Retrievers, and Generators

Domain-adaptive training for each RAG stage — from contrastive embedding fine-tuning to retrieval-aware LLM training with RAFT

GraphRAG: Knowledge Graphs Meet Retrieval-Augmented Generation

Building and querying knowledge graphs for RAG with Neo4j, LlamaIndex, and Microsoft GraphRAG — from entity extraction to community summarization

Hybrid and Corrective RAG Architectures

Self-RAG, CRAG, Adaptive RAG, and query routing — building RAG systems that know when to retrieve, when to skip, and when to self-correct

RAG in Production: Scaling, Caching, and Observability

Vector database selection, semantic caching, query routing, hybrid search, monitoring, and cost optimization for enterprise RAG deployments

Retrieval over Images, Tables, and PDFs

Indexing and retrieving from complex documents with vision-language models, multi-vector retrieval, and LlamaParse