RAG: giving a model your documents
Retrieval-augmented generation (RAG) lets a model answer from documents it was never trained on, such as a company's manuals. The documents are split into chunks, turned into embeddings and stored in a vector database. When a question comes in, the chunks closest in meaning are found and added to the prompt, and the model answers from them, ideally citing them. It's far cheaper than retraining, stays current when the documents change, and cuts down on made-up answers.
Why it matters: RAG is how most business chatbots answer from their own information.
Builds on: Embeddings, Why models make things up
Learn it, then prove it
Sign in (free) to take this step's mastery check and save your journey.
Contact Us
Questions or feedback about anything? We'd love to hear from you.
You can reach us at: support@seriousmindware.com