Glossary
Retrieval-Augmented Generation (RAG)
Grounding an LLM's answers in retrieved source documents instead of its training data alone.
Retrieval-Augmented Generation, or RAG, is a technique that fetches relevant passages from a knowledge base and feeds them to a language model as context before it answers. Instead of relying only on what the model memorised during training, the model responds from the documents you provide. This keeps answers current, specific to your business, and traceable back to a source.
A RAG pipeline has two halves. Retrieval finds the passages most relevant to a question, usually by comparing embeddings in a vector database, often combined with keyword search. Generation then passes those passages to the model with an instruction to answer using them and to cite them.
CertifChat uses RAG so the assistant answers from your crawled pages, docs, and PDFs rather than from generic web knowledge. Every reply carries inline citations and a confidence score, and when retrieval turns up nothing relevant the assistant hands off instead of guessing.
See how this works in practice across CertifChat's features.
Related terms
- EmbeddingsNumeric vectors that capture the meaning of text so similar passages sit close together.
- Vector DatabaseA store optimised for finding the embeddings most similar to a query vector.
- Semantic SearchSearching by meaning using embeddings, often combined with keyword search.
- ChunkingSplitting documents into passages small enough to embed and retrieve precisely.
- HallucinationWhen a language model states something confidently that isn't supported by its sources.
Put your knowledge to work today
Connect your sources, drop one snippet on your site, and start deflecting tickets. We are opening CertifChat to a first group soon.