AI Foundationsbeginner11 min · 9 steps
RAG and Vector Stores
Retrieval-augmented generation gives an LLM fresh, citable facts; vector stores such as Qdrant, Pinecone and Weaviate make the retrieval fast.
requesterrordatatokenresponse
ProblemStep 1 of 9
An LLM only knows what it read during training
A pre-trained model's knowledge is frozen at its training cut-off. It has never seen your internal documents, and it can't cite where an answer came from.
Asked anyway, it produces a fluent guess — a hallucination.
Watch outRetraining the model every time a document changes is slow and expensive. There is a simpler way.
← Previous lessonImage Generation: GANs and DiffusionNext lesson →AI Agents and Their Design Patterns
Lesson 7 of 34 in AI Foundations