Retrieval & Agents
Retrieval-Augmented Generation
RAGA technique that looks up relevant documents and feeds them to a model so its answers are grounded in real sources.
RAG pairs a language model with a search step: before answering, the system retrieves relevant passages from your own documents or database and hands them to the model as context. This grounds the response in specific, up-to-date, verifiable material instead of relying only on what the model memorized during training. It is the most common way to build AI that can answer questions over a company’s private knowledge, and it reduces hallucination.
Reference: Wikipedia: Retrieval-Augmented Generation
Related terms
Vector Database
A database built to store embeddings and quickly find the items most similar in meaning to a query.
Embedding
A way of turning words, images, or other data into lists of numbers that capture their meaning, so a computer can compare them.
Semantic Search
Search that matches on meaning rather than exact keywords, so related ideas surface even with different wording.
Hallucination
When a model states something false or made up as if it were fact, fluently and confidently.