passdrill
AI & LLM Engineering · RAG & Embeddings · Card 002/012 easy

A team splits long internal manuals into fixed-size chunks before embedding them for a retrieval index, and configures each chunk to overlap with the next by roughly 10-20% of its length rather than starting exactly where the previous chunk ended. What is the main reason for using this overlap between adjacent chunks?

  1. It reduces the total number of chunks that must be embedded and stored, which lowers the cost of building the index
  2. It prevents a sentence or idea that spans a chunk boundary from being split apart so that neither resulting chunk contains it in full, which could leave either chunk incoherent or missing context on its own
  3. It guarantees that every chunk containing the overlapping text will be retrieved for any query relevant to that document, since duplicated content is matched more often
  4. It lets the embedding model process shorter chunks than the maximum input length it is otherwise capable of handling
Next card → Shuffle