Quiz lié à un guide · Moyen Niveau

Quiz sur les stratégies de regroupement de documents

Examinez les limites des blocs, le chevauchement, la division sémantique et structurelle, ainsi que la façon dont les résultats empiriques peuvent différer selon l'ensemble de données. Comparez les configurations sur le corpus.

Chemins de guidage associésStratégies de regroupement de documents
Question 1 de 8

What does Amazon Bedrock say its default chunking approach does?

Prévisualisez chaque question8 des questions

Les réponses et les explications apparaissent au fur et à mesure que vous répondez au quiz.

  1. What does Amazon Bedrock say its default chunking approach does?
    • Splits text into roughly 300-token chunks while preserving complete sentence boundaries
    • Splits every document into one token
    • Uses one chunk for every knowledge base regardless of size
    • Groups documents by alphabetical title
  2. Why can the buffer size matter in semantic chunking?
    • It changes the source document’s spelling
    • It determines how many neighboring sentences are included when creating embeddings
    • It identifies the correct speaker
    • It specifies the model’s output vocabulary
  3. Quel est le principal compromis entre les très petits et les très gros morceaux ?
    • Les petits morceaux sont toujours plus lents à intégrer
    • Les gros morceaux ne peuvent jamais être récupérés
    • Les petits morceaux sont précis mais perdent leur contexte ; les gros morceaux conservent le contexte mais diluent la pertinence
    • Il n'y a pas de différence significative
  4. In Amazon Bedrock, what may its parsed-content chunker preserve as logical boundaries?
    • Only individual characters
    • Image colors and crop boxes
    • The prompt’s output format
    • Pages or sections
  5. How does Amazon Bedrock describe hierarchical chunking at retrieval time?
    • It retrieves child chunks and can replace them with broader parent chunks
    • It discards parent text and never returns broader context
    • It merges all documents into one vector
    • It converts every chunk to an image
  6. How does Amazon Bedrock’s semantic chunking propose boundaries between sentences?
    • By sorting sentences alphabetically
    • Using sentence-distance thresholds to identify less-similar adjacent sentences
    • By splitting every document at the same character count
    • By detecting speaker identity
  7. What did a 2026 chunking study find about overlap in its tested Natural Questions setup?
    • It always doubled answer accuracy
    • It eliminated all retrieval errors
    • It increased indexing cost without a measurable answer-quality benefit
    • It reduced indexing cost to zero
  8. What happened when retrieved context grew beyond about 2,500 tokens in that study?
    • Accuracy rose without limit
    • All questions became exact matches
    • The retriever stopped using embeddings
    • Answer quality showed a context cliff