RAG (retrieval-augmented generation)
Retrieval-augmented generation (RAG) is a technique where an AI model retrieves relevant passages from a knowledge base, such as product documentation, and uses them to generate a grounded answer.
For documentation, RAG works in two steps. First, the docs are split into chunks and indexed as embeddings; when a user asks a question, the system retrieves the most relevant passages. Second, a language model writes an answer using only those passages as context.
The retrieval step is what separates a docs chatbot from a generic AI assistant. The model answers from your current documentation instead of its training data, so answers stay accurate after every release and can cite the exact page they came from.
RAG quality depends mostly on the retrieval side: how the docs are chunked, how well the index covers the site, and whether the system admits when nothing relevant was found. Biel.ai's chatbot is built on this pattern: it answers from your docs, cites sources, and says "I don't know" instead of guessing.
Frequently asked questions
How is RAG different from fine-tuning?
Fine-tuning bakes knowledge into model weights and goes stale as docs change. RAG looks up current documentation at question time, so updating the docs updates the answers.
Does RAG prevent hallucinations?
It reduces them substantially but does not eliminate them. Retrieval grounds the model in real passages, but the system also needs to decline to answer when retrieval finds nothing relevant.
What does RAG stand for?
Retrieval-augmented generation. The model's text generation is augmented with content retrieved from a knowledge base, such as your documentation site.