Retrieval-Augmented Generation (RAG)

Retrieval-Augmented Generation (RAG) is an architectural pattern that enhances LLMs by giving them access to external knowledge bases. Instead of relying solely on the model’s internal (potentially outdated) knowledge, RAG retrieves relevant documents from a database and includes them in the prompt context.

How RAG works:

1. A user query is converted into an embedding vector
2. The embedding is used to search a vector database for relevant documents
3. Retrieved documents are added to the prompt as context
4. The LLM generates a response grounded in the retrieved information

RAG addresses key limitations of LLMs: it reduces hallucinations, provides source attribution, and can access current information without retraining. It is commonly used for customer support, enterprise knowledge bases, legal research, and medical question answering.