Legal RAG Explained

What is RAG?

RAG (Retrieval-Augmented Generation) is an AI architecture that combines two capabilities:

1. Retrieval: searches for relevant documents in a verified source database
2. Generation: uses an LLM to synthesize a response based on those documents

Why Is It Crucial for Law?

A "pure" LLM (without RAG) can:

• Invent non-existent articles ("hallucinations")
• Cite non-existent rulings
• Mix legislation from different countries
• Give outdated information

With RAG, the response is always grounded in real, verifiable documents.

How It Works Step by Step

1. User question: "What is the statute of limitations for non-contractual damages?"
2. Embedding: the question is converted into a numerical vector
3. Semantic search: the most similar fragments are found in the database (pgvector)
4. Context: relevant fragments are passed to the LLM along with the question
5. Generation: the LLM responds based only on the provided fragments
6. Citation: the response includes exact sources (article, ruling, BOE)

RAG Quality Metrics

• Precision: are the cited sources correct?
• Recall: were all relevant sources found?
• Faithfulness: is the response faithful to what the sources say?
• Relevance: are the sources pertinent to the question?