passdrill
AI & LLM Engineering · RAG & Embeddings · Card 013/022 easy

A pipeline splits long documents into chunks by comparing the embedding similarity between each pair of adjacent sentences and starting a new chunk whenever that similarity drops sharply, rather than cutting every fixed number of characters regardless of content. What is this chunking approach called, and why can it retrieve better than fixed-size chunking on a document that mixes several unrelated topics?

  1. This is called cross-encoder reranking, and it retrieves better because a joint query-passage pass scores each chunk more accurately than comparing two independently computed embeddings
  2. This is called query expansion, and it retrieves better because appending related terms to the chunk's text before embedding gives the embedding model more signal to work with
  3. This is called semantic chunking, and it retrieves better because placing chunk boundaries where the topic actually shifts keeps each chunk focused on a single topic, so a chunk's embedding is not an average of unrelated content and a query about one of the topics is less likely to be diluted by the others sharing its chunk
  4. This is called vector quantization, and it retrieves better because compressing each chunk's embedding to lower numeric precision makes nearest-neighbor comparisons faster and therefore more accurate
Next card → Shuffle