Advanced LLM App Development #rag#embeddings#vector-database#retrieval

RAG Pipeline Vocabulary

5 exercises — Master the English vocabulary for describing RAG architectures, chunking strategies, embedding models, and retrieval quality.

0 / 5 completed
Quick reference: RAG Pipeline
  • chunking — splitting source documents into segments for embedding and indexing
  • embedding — converting a text chunk into a dense numerical vector encoding its meaning
  • vector store — a database optimised to store and search embedding vectors (pgvector, Pinecone, Weaviate)
  • cosine similarity — similarity metric: cos(angle) between two vectors; 1.0 = identical direction
  • hybrid retrieval — combining dense (semantic) and sparse (BM25 keyword) search scores
1 / 5

During a RAG architecture review, a teammate says: "Our chunks are 2,000 tokens with no overlap — retrieval quality is terrible because the answer spans a chunk boundary." Which change best addresses this problem?