RAG

Retrieval-augmented generation grounds a model's answers in your own data at query time, instead of relying only on what it learned during training.

• RAG (Retrieval-Augmented Generation) — RAG retrieves relevant documents at query time and feeds them to an LLM as context, so answers are grounded in your own data instead of just training data.
• Embeddings — an embedding turns text into a list of numbers positioned so similar meanings land near each other.
• Chunking — splits documents before you index them.
• Vector Database — finds the stored embeddings nearest a query.
• Reranking — a reranker re-scores the shortlist from your first search, reading query and document together.
• RAG Evaluation — scores retrieval quality and generation quality separately, because a RAG system can fail at either stage independently.

Comparisons

• RAG vs Fine-Tuning
• RAG vs Long Context
• RAG vs Memory
• Vector Search vs Keyword Search