RAG & Retrieval Vocabulary

Retrieval-Augmented Generation; enhancing models with external knowledge

“RAG enables the chatbot to answer questions about private company data.”

a database optimized for storing and querying high-dimensional embeddings

“We use a vector database to perform semantic search on millions of documents.”

searching by meaning rather than exact keyword matching

“Semantic search finds 'canine' when you search for 'dog'.”

combining keyword search and vector search for better accuracy

“Hybrid search catches both exact part numbers and conceptual queries.”

re-ordering search results using a more precise model

“A cross-encoder allows for reranking the top 50 results for better precision.”

splitting text into smaller segments for embedding

“Semantic chunking respects sentence boundaries better than fixed-size chunking.”

inserting retrieved information dynamically into the prompt

“Context injection provides the model with the necessary facts to answer.”