RAG
RAG — Retrieval Augmented Generation
Ground LLMs in your private data with retrieval, reranking and citations.
Retrieval Augmented Generation (RAG) is the production-default pattern for grounding LLM responses in private or domain-specific data. This topic hub covers the full RAG stack: ingestion, chunking, embeddings, vector search, hybrid retrieval, reranking, generation, evaluation and production architecture. Whether you're building your first RAG system or debugging retrieval quality in production, start here.
Start Here
Begin with the fundamentals
The recommended first lesson for this topic.
Fundamentals
Architecture Patterns