Traditional retrieval augmented generation systems follow a process of chunking documents into workable pieces, embedding them into a vector database using an embedding model, then at runtime embedding the user query and calculating semantic similarity to retrieve the top N relevant chunks which are passed as context to the language model along with the original query.
factualpending
Speaker
Adam LucikEvidence Quote
“taking your document you chunk it into workable pieces of text that is all embedded into a vector database using an embedding model and then at runtime what happens is someone inputs a query that query is also embedded a semantic similarity calculation is ran across your vector database to retrieve semantically the top and relevant chunks”
Created: 8/11/2026, 7:35:39 AM
Your notes
Loading notes...