Glossary · Definition
RAG (retrieval-augmented generation)
RAG is a technique where an AI system first searches your documents or data for relevant passages and then lets a language model answer using them, with citations.
By Nythrex EngineeringUpdated 1 min read
In plain words
Instead of relying on what a model memorised during training, RAG looks up the relevant pages in your own knowledge base for every question and hands them to the model as context. The model answers from those pages and can point to them.
When it matters to you
- Answers depend on private, recent or changing information
- Users or auditors need to see sources
- Different users may see different data
Common pitfalls
- Blaming the model when retrieval is the problem
- No test set to measure retrieval quality
- Forgetting permissions in the search index
Keep reading
ServiceRAG developmentRAG development: AI assistants that answer from your documents and data with citations, permissions and measured accuracy — built in your cloud.GuideRAG vs fine-tuning vs promptingRAG adds knowledge, fine-tuning changes behaviour, prompting is where you start. How to choose — with a decision tree, costs and pitfalls.GlossaryEmbeddingsEmbeddings are lists of numbers that represent the meaning of text, so a computer can find passages that mean similar things even when they use different words.GlossaryVector databaseA vector database stores embeddings and finds the most similar ones quickly, which is how RAG systems locate relevant passages among millions.
Want a second opinion on your project?
Tell us what you’re building and where you’re stuck. We’ll reply within one business day with the most practical next step — even if that step isn’t us.