What is RAG (retrieval augmented generation)?
Retrieval-Augmented Generation (RAG) is the technique of pairing a language model with a vector database so the model answers using passages retrieved from your content rather than from what it memorized during training.
Why it matters
Retrieval gives a model source material to use when answering. It can improve relevance and make the source easier to inspect, but it does not eliminate incorrect answers. Missing, stale or conflicting documents still require handling.
The pipeline
Embed the query into a vector. Search your vector index for the top K nearest passages. Inject those passages into the prompt. Ask the model to answer using only the provided context. Optionally, require citations to specific passage IDs.
Message AI uses indexed knowledge to help answer business questions. Keep that knowledge accurate and configure the assistant’s handoff behavior. Source visibility and available tools depend on the workflow; not every response is a knowledge-base answer or includes a customer-visible citation.
See it working on message.com.
Unified inbox, grounded AI, flat pricing. 7-day free trial for chat and tickets. Credit card required.
Start free trial →