all-in-rag is a full-stack practical guide to developing large-model applications with Retrieval-Augmented Generation (RAG). Contributors with experience in RAG, vector databases, Agentic RAG, or related technologies are invited to submit independent chapters to the Extra Chapter section after reviewing the contribution and PR guidelines.

The README covers RAG fundamentals and use cases; the complete data-processing workflow from loading and cleaning to chunking; embeddings, multimodal embeddings, vector databases, and index optimization; and advanced retrieval techniques such as hybrid retrieval, query construction, and Text2SQL.