Retrieval
Chunking
Chunking splits source documents into smaller passages before embedding, so retrieval returns focused text.
Chunk size and overlap are load-bearing decisions, not implementation details to skip past.
Chunks too large dilute relevance and blow the context budget.
Chunks too small lose the surrounding context a passage needs to make sense.
Most RAG accuracy problems trace back to chunking, not to the model.
← Back to the full glossaryRelated terms
Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) retrieves relevant passages at query time and feeds them into an LLM's context. Embeddings Embeddings are numeric vectors that place similar content close together in vector space. Vector Search (Semantic Search) Vector search finds the nearest matches to a query by comparing embeddings, not exact keywords.